# Skylark Creations — Full Project Reference > AI-native product studio based in Colorado. Founded by David Kooi. We build human-friendly apps and partner with domain experts to ship new ones fast. Website: https://skylarkcreations.com Compact map: https://skylarkcreations.com/llms.txt Founder: https://davidkooi.com Newsletter: https://uncagedminds.substack.com This file describes every public Skylark project. Content is generated from the same data that renders the project pages, so it never drifts from what a reader sees. --- ## Magnifica Humanitas — the Pope's letter on AI, in 5 minutes (Featured Explainer) **Type:** Plain-language explainer / accessibility summary **Page:** https://skylarkcreations.com/magnifica-humanitas **Source text:** https://www.vatican.va/content/leo-xiv/en/encyclicals/documents/20260515-magnifica-humanitas.html A free, plain-language guide to *Magnifica Humanitas* ("The Grandeur of Humanity"), Pope Leo XIV's 2026 encyclical — the first papal letter written squarely about artificial intelligence. The encyclical's thesis is not a verdict on the technology but a question about us: in the age of machines, will we stay human? Technology is never neutral; it carries the values of whoever builds it. The real choice is whether we use AI to dominate one another or to rebuild a world where every person still counts. ### The central image: Babel vs. Jerusalem Leo XIV frames the whole AI moment through two biblical stories. **Babel** — the tower built to "make a name for ourselves" — is power chasing its own greatness, one system that erases difference for efficiency and reduces people to data and performance. **Jerusalem** — Nehemiah rebuilding the broken city wall by wall — is shared responsibility, relationships repaired before stones are laid, difference treated as a resource. His line: "the construction of Babel or the rebuilding of Jerusalem begins within each one of us." ### Seven core ideas 1. **AI imitates intelligence but has no self** — it can outrun us and simulate empathy, but has no body, conscience, or real understanding. Today's AI is "more 'cultivated' than 'built'"; developers create a framework within which the intelligence grows. Human conscience and freedom must stay in charge. (Chapter 3) 2. **Human dignity is unconditional** — the insidious modern idea is that worth must be earned through productivity. Dignity precedes achievement; a system that treats some lives as "less worthy" has already failed. (Chapter 2) 3. **Every answer has a hidden human cost** — the "silent work" of data labeling, model training, and content moderation (often disturbing material), and children extracting rare-earth elements. A new form of slavery; colonialism in a new shape, where data — health records, genetic maps — become "the new 'rare earths' of power." The Church recalls its own delayed condemnation of slavery as a call to vigilance. (Chapter 4) 4. **Don't delegate life-and-death decisions to machines** — AI lowers the threshold for force, shields people from responsibility, and reduces victims to "collateral damage." Calls for a shared international framework and accountable human control. (Chapter 5) 5. **"Disarm" AI rather than reject it** — AI "must be disarmed, welcoming and accessible," freed from monopoly control, made "human-friendly," restored to the plurality of human cultures. Breaking the "monopolies of AI." (Chapter 3) 6. **Human limits are not defects to patch** — a critique of transhumanism. Once the human is something "to be perfected or surpassed," it gets easier to treat some lives as "less worthy." We grow through our limits; the real "more than human" comes from grace, not a better machine. (Chapter 3) 7. **Truth and work are public goods** — AI super-charges disinformation and threatens minors online; he calls for an "ecology of communication." Automation should serve people, not only cut costs; businesses should treat "work and dignity as measures of success," not GDP alone. (Chapter 4) ### Key verbatim quotes - "Never has humanity had such power over itself." (Introduction) - "Let us disarm words and we will help to disarm the world." (Chapter 5) - Progress as "having more" without "being more." (Chapter 3) - "The construction of Babel or the rebuilding of Jerusalem begins within each one of us." (Chapter 3) This is an independent accessibility summary, not an official Church text — all positions are paraphrased and attributed to the encyclical, with quoted lines verbatim. For authoritative wording, see the Vatican source. --- # Shipped and live Products you can use right now — on the web, the App Store, or Google Play. --- ## Agentic Directory **Status:** Live **Platforms:** Web (Live) — https://agentic.ai **Project page:** https://skylarkcreations.com/projects/agentic-directory **Pricing summary:** Free to browse Find AI that actually does things. A curated directory of 300+ agentic AI products and services, independently scored on a 36-point rubric across nine dimensions — with decision reports, a public API, and an MCP server for agents that want to recommend tools. A curated, AI-first directory that helps you discover agentic AI products — tools and services that take autonomous action, not just chat. Every listing is independently scored on a 36-point agenticness rubric. ### Overview Agentic Directory is the default place people and their AI agents go to find, evaluate, or recommend agentic AI tools — because they trust what we say. Every product is independently scored on a 36-point rubric across nine dimensions including action capability, autonomy, planning, adaptation, state, reliability, interoperability, and safety. Vendors cannot pay to be ranked or excluded. The directory pairs a conversational "Ask" interface with structured discovery via categories, tags, and use cases. A public REST API (`/api/v1/`) and an MCP server expose the same data to AI agents that need to recommend tools, with a compound `recommend_tools` endpoint that returns scored, citation-backed matches. A vendor portal handles claims, profile editing, and Stripe-backed subscriptions; a background worker continuously crawls and re-evaluates listings as the agentic AI space changes. ### Why we built it The agentic AI space is exploding, but discovery is fragmented. Most directories lump chatbots in with genuinely autonomous systems. We built Agentic Directory to draw a clear line: this is for AI that acts. The scoring system gives users a fast, honest read on what a product can actually do on its own. ### How it works 1. **Browse or search** the directory by category, use case, or tag — or hit the public API directly 2. **Ask** — describe your problem in plain language and get matched to relevant products with citations 3. **Compare** — every listing shows an agenticness score across nine dimensions, plus a tier label 4. **Submit** — vendors can submit products, claim listings, and manage their profiles via Stripe-backed plans 5. **Stay current** — a background worker continuously crawls and re-evaluates listings; news mentions trigger re-scores ### Features - **36-Point Agenticness Score** — Nine-dimension evaluation including action capability, autonomy, planning, adaptation, state, reliability, interoperability, and safety - **Decision Reports** — a free instant verdict plus a one-off paid report recommending the best tool for your specific use case — judged by the rubric, not by who pays - **Conversational Discovery with Citations** — "Ask" interface matches plain-language needs to products using a hybrid keyword + semantic + reranked search pipeline - **Public API + MCP Server** — REST API at `/api/v1/` plus an MCP server with a compound `recommend_tools` endpoint, so AI agents can read or recommend from the directory - **Watch Primitive** — Get notified when a product's agenticness score moves or a category gets a new entry; dashboards surface "since your last visit" - **Vendor Portal** — Claim listings, manage profiles, upgrade plans via Stripe - **AI-Powered Enrichment** — Background worker crawls product sites with entity-match disambiguation gates and re-evaluates on news mentions - **Editorial Best-Of Pages** — Curated guides like "Best free coding agents" surface rubric strengths-and-weaknesses panels alongside the scores ### Notes - **Status:** Live and active. 300+ scored listings, public API + MCP server, daily newsletter, vendor portal with Stripe subscriptions. - **Tech Stack:** Next.js 16, TypeScript, React 19, Tailwind CSS 4, shadcn/ui, PostgreSQL (Neon) + Prisma + pgvector, Supabase Auth, Stripe, OpenAI GPT-5.4, Firecrawl, Cohere Rerank v3.5, SendGrid, Vitest + Playwright. Hosted on Render (web + background worker). - **For Whom:** Teams evaluating agentic AI tools, founders scouting competitors, developers building agentic products, and AI agents that need a curated, machine-readable index of the space. --- ## BloomEDU **Status:** Available on iOS & Android **Platforms:** iOS (Available on App Store) — https://apps.apple.com/us/app/bloomedu-learn-plants/id6749336509; Android (Available on Google Play) — https://play.google.com/store/apps/details?id=com.bloomedu.app; Web (Product website) — https://bloomedu.app/ **Project page:** https://skylarkcreations.com/projects/bloomedu **Pricing summary:** Free · Premium $4.99/mo **Privacy policy:** https://skylarkcreations.com/projects/bloomedu/privacy-policy **Terms of service:** https://skylarkcreations.com/projects/bloomedu/terms-of-service Snap a photo of a wildflower, then actually learn its name. BloomEDU pairs camera-based plant identification with spaced repetition quizzes so the species you spot today are still names you can recall weeks from now. Offline-capable across 46,000+ US wildflowers, on iOS and Android. ### Overview BloomEDU closes the gap between "this app told me what the plant is" and "I can name that plant myself." Snap a photo on a hike — the camera identifies the species using AI vision with location and seasonal context — then BloomEDU drops it straight into a personalized spaced repetition quiz, so the name actually sticks. Three weeks later, you still recognize it. The app covers 46,000+ US wildflower species with 337,000+ visual multiple-choice questions across state, family, bloom-season, and safety scopes. A 7-interval spaced repetition algorithm schedules reviews automatically — plants you miss return in a minute, mastered species cycle weekly — targeting durable recognition with minimal study time. The full database and core quizzes work offline via downloadable regional packs, so trail and meadow are first-class environments, not afterthoughts. Premium adds unlimited Plant ID scans, screenshot import from iNaturalist's Seek app (turn your existing observations into a learning queue), and a library of 5–7 minute AI-narrated podcasts for every species, covering field marks, ecology, and cultural context. ### Features - Plant ID camera with AI vision — identify wildflowers from a photo, with location and seasonal context (3 free scans/day, unlimited on Premium) - 46,000+ US wildflower species with common names, scientific names, family classifications, and regional distribution data - 337,000+ multiple-choice quiz questions across state, family, seasonal, safety, observation, and custom list scopes - 7-interval spaced repetition algorithm based on the spacing effect and forgetting curve research - Seek by iNaturalist screenshot import — pull plants from your existing observations into your learning queue (Premium) - AI-narrated podcasts for every species with background playback support (Premium) - Shareable wildflower collection cards — a visual snapshot of the species you've added - 100% offline-capable with downloadable regional data packs - Progress tracking and per-question performance analytics ### Pricing Free tier: one daily general quiz plus unlimited state, family, seasonal, and safety quizzes; the full 46,000+ plant database with offline regional packs; 3 Plant ID scans per day; device text-to-speech and rotating podcast samples. Premium ($4.99/month or $29.99/year, with a 7-day free trial): unlimited Plant ID scans, unlimited general quizzes, Seek screenshot import with observation quizzes, custom list and time-window quizzes, the full podcast library, premium AI voice with background playback, and priority support. --- ## Reframed **Status:** Live **Platforms:** Web (Live) — https://reframed.news/ **Project page:** https://skylarkcreations.com/projects/reframed **Pricing summary:** Free A daily news briefing that leads with cited consensus facts, then shows the same story through Left and Right framings — so you can see what's agreed, what's contested, and decide for yourself. Plus a paste-any-URL reframe tool. An attention-respecting daily briefing for people who want substance over spin. Consensus facts with citations first, then two contrasting framings - Left and Right - so you see both the agreement and the disagreement on every story. ### Overview Reframed is a daily briefing for people who want to understand the news without being told what to think. Each morning it delivers up to 18 stories across 6 categories — U.S. Politics, World Affairs, Business & Economy, Tech & Society, Science & Environment, Rights & Justice — built through a fully automated pipeline: events are scored for relevance, deduplicated, and assembled into cited consensus facts, then read through two contrasting value lenses. The main web experience is Quick Read: a per-story card with a 30-second Left framing, a 30-second Right framing, and a facts-only center. Each card also offers a 2-minute or 5-minute depth tier. Every factual claim cites at least one source. Beyond the daily brief, Reframed has two standalone tools. /reframe lets you paste any article URL and get a full seven-frame analysis with an interactive dial and shareable results — in about 60 seconds. The Values Quiz maps your own perspective across five real news scenarios into a named Lens Profile. A Field Guide catalogs 13 recurring patterns in news coverage — readers can see which patterns appear in today's stories. ### Why we built it Generic news feeds and keyword alerts are noisy and don't explain implications. Reframed is built to deliver signal over noise: fewer alerts, deduplicated coverage, and fast, role-aware interpretation with receipts. The dial gives readers agency over how much opinion they consume without sacrificing the underlying facts. ### How it works 1. **Ingest** — Events pulled from newsapi.ai with keyword pre-filtering and LLM relevance scoring, balanced across 6 categories (up to 18 stories) 2. **Generate** — Per story: screen all 9 value-frames for relevance, pick the best contrasting pair, generate consensus facts with src-N citations, then generate moderate + max content per selected frame 3. **Email** — Compose HTML + plain text digest and send via SendGrid to subscribers 4. **Read** — Browse the web app, use the dial to control commentary intensity, swap frames, tap citations to verify claims ### Features - **Interactive Dial** — Smooth slider across five content zones: Frame A, moderate Frame A, facts-only center, moderate Frame B, Frame B - **Cited Consensus Facts** — Every factual claim references at least one source; phantom citations stripped automatically - **7 Value-Frames** — Human Impact, Accountability, Freedom & Rights, Economic Stakes, Boundaries & Dignity, Order & Institutions, Belonging & Identity. Best contrasting pair selected per story; readers can swap via frame pills. - **6 News Categories** — U.S. Politics, World Affairs, Business & Economy, Tech & Society, Science & Environment, Rights & Justice - **Quick Read** — Per-story Left/Facts/Right toggle with 30-second, 2-minute, and 5-minute depth tiers. Convergence and divergence lines synthesized above each card. - **Daily Email** — Facts-only digest; two CTAs per story link to Quick Read and the full dial view - **/reframe** — Paste any article URL for a full seven-frame analysis, cited prose rewrites, and a shareable result page with an interactive dial - **Values Quiz** — Five-scenario quiz that maps your perspective to a named Lens Profile; quiz-aware email signup - **Field Guide** — Catalog of 13 named recurring patterns in news coverage; today's matching stories surface daily ### Notes - **Tech Stack:** Next.js 16, TypeScript, React 19, Tailwind CSS v4, Neon Postgres + Drizzle ORM, Supabase Auth (magic-link + Google/Apple OAuth), Anthropic Claude Opus 5 (writing) + OpenAI gpt-5.6 (gating, judgment, utility), newsapi.ai, SendGrid, Vitest - **Pipeline:** Fully automated daily cron at 6:00 AM ET via Render; retry logic for API failures, skip-and-continue for individual story failures, never sends broken or empty emails - **For Whom:** Anyone tired of spin — news readers who want to verify claims, compare perspectives, and control how much commentary they consume --- ## BuddhaUR **Status:** Available on iOS & Android **Platforms:** iOS (Available on App Store) — https://apps.apple.com/us/app/buddhaur-find-peace/id6752915041; Android (Available on Google Play) — https://play.google.com/store/apps/details?id=com.skylark.buddhaur; Web (Product website (app is iOS & Android only)) — https://buddha-ur.com/ **Project page:** https://skylarkcreations.com/projects/buddhaur **Pricing summary:** Free **Privacy policy:** https://skylarkcreations.com/projects/buddhaur/privacy-policy **Terms of service:** https://skylarkcreations.com/projects/buddhaur/terms-of-service Learn early Buddhism through conversation. Ask what you're actually dealing with—anger, craving, stress, attention, relationships—and get grounded guidance with tappable citations to the early suttas, so you can verify it for yourself. A mobile-first Buddhist learning and practice companion that teaches early Buddhist wisdom through conversation, grounded in authentic texts with tappable citations. ### Overview BuddhaUR is a conversational teacher in your pocket. Ask real questions about life, meditation, ethics, and Buddhist doctrine—anger, craving, stress, attention, relationships—and receive thoughtful answers in a warm, patient, Socratic tone. Every substantial claim includes citations you can tap to verify against early Buddhist sources. The app is built around a repeatable rhythm: Learn a topic through guided lessons, ask follow-ups in chat, reinforce with quizzes or adaptive practice, sit with a calm meditation timer and notes, then track your streaks and return tomorrow. It's a practice ecosystem where learning becomes interactive, practice becomes repeatable, and the app's memory makes guidance feel continuous across sessions. BuddhaUR is rooted in early Buddhist teachings (suttas + core frameworks), not generic self-help platitudes. The AI is constrained by retrieval of source material and is designed as a teacher, not a random answer generator. Whether you're a curious beginner wanting a friendly entry point, a meditator seeking consistent practice support, or a practitioner wanting doctrinal depth with warmth—BuddhaUR meets you where you are. ### Why we built it People bring sprawling questions to Buddhism and often get responses that feel smart but fall apart during practice. Most people don't know where to start in the Pali Canon's thousands of suttas, and modern meditation apps often present "mindfulness lite" disconnected from its philosophical foundations. BuddhaUR lets you ask your question, not just read the answer. You can verify teachings via citations to primary sources. You build a habit through streaks, daily practice, and gentle reminders of progress. The app learns your journey and adapts its guidance and suggestions over time—creating a truly personalized learning experience that remembers what matters. ### How it works **The Teach → Practice → Reinforce Loop:** 1. **Learn** a topic through structured lessons on the Buddha's core frameworks—Four Noble Truths, Eightfold Path, Five Aggregates, and more 2. **Chat** with the teacher using Socratic dialogue—request stories, metaphors, or practical applications 3. **Practice** with quizzes or adaptive practice that targets your knowledge gaps 4. **Meditate** using the calm timer with reflection notes and "chat about this session" to connect practice to insight 5. **Track** your streaks and return daily via personalized Daily Dhamma talks **How the AI Works:** When you ask a question, BuddhaUR retrieves relevant passages from its knowledge base of early Buddhist texts and answers using that context (RAG—retrieval-augmented generation). Citations link out to SuttaCentral (translations by Bhikkhu Sujato), so users can check the sources. The point is simple: you can verify everything. ### Features - **A Teacher You Can Talk To** - Ask anything and get answers designed to be warm, patient, and practical—not a generic chatbot - **Citations You Can Tap** - Answers grounded in early sources with tappable links to verify and read more - **Guided Lessons on Core Buddhist Frameworks** - Walk through the Four Noble Truths, Eightfold Path, Five Aggregates, Dependent Origination, and more, organized across foundations, ethics, meditation, wisdom, and stages of practice - **Quizzes + Adaptive Practice** - Turn "I read it" into "I know it" with practice that brings back what you miss - **Meditation Timer + Reflection Notes** - A clean timer that respects attention, with notes and "chat about this session" - **Daily Dhamma Talk** - Personalized daily teachings drawn from your interests, lessons, and recent conversations - **Story Mode** - Request Dhamma stories told in a narrative, warm tone grounded in themes and sources - **Smart Follow-Up Suggestions** - Tappable chips for deeper dives, related concepts, and practical applications - **Keep What Lands** - Save a teaching that resonates as a shareable card, tucked into your photos for re-reading or passing along - **Personalized Experience** - The app remembers your journey, preferences, and challenges to tailor suggestions - **Conversation History** - Review and resume past discussions; your path has a memory - **Daily Streaks & Achievements** - Track consistency across lessons, quizzes, meditation, and talks - **Beautiful, Calm Design** - Sage green accent, warm earth tones, generous whitespace, high readability ### Notes - **Pricing:** Free — every feature is free (dana model). Optional support plans: $5/month · $40/year · $100 lifetime. - **For Whom:** Curious beginners, daily meditators, experienced practitioners, busy people with real-life problems, anyone who wants perspective without the pedestal - **Not Medical Advice:** Educational and contemplative content only. Meditation can be challenging—practice with care. - **Privacy:** No ads, we don't sell your data. Account deletion available in-app (Settings → Account → Delete Account). - **Philosophy:** No gurus, no mystical drift—just authentic early Buddhist teachings you can verify for yourself. --- ## Agentic News **Status:** Live **Platforms:** Web (Live) — https://agentic-news.ai **Project page:** https://skylarkcreations.com/projects/agentic-ai **Pricing summary:** Free to start · $9/mo or $79/yr **Privacy policy:** https://skylarkcreations.com/projects/agentic-ai/privacy-policy **Terms of service:** https://skylarkcreations.com/projects/agentic-ai/terms-of-service AI-powered news intelligence that argues against every story before sending it to you. Agentic News clusters duplicate coverage into single stories, runs each one through a skeptical relevance check, interprets what survives through role-aware lenses, and lets you ask questions across your saved knowledge—with citations. From news overload to actionable insight—tailored to your roles and interests. ### Overview Agentic News is a news intelligence platform that watches the web for the topics you care about and delivers signal over noise. You create Agents—watchlists for the topics, companies, or niche interests you care about—and they match incoming coverage by meaning, not keyword spam. Near-identical articles are deduplicated into clean story Clusters backed by multiple sources. Every match runs through a two-stage editorial filter. A skeptical Devil's-Advocate gate rejects stories that don't actually fit what you asked for; only the survivors get a hook, a brief, and a place in your daily digest. The reasoning behind each pick is visible per story, so you can see why a story made the cut—or didn't. For accepted stories, role-aware AI Lenses explain what happened and why it matters from the perspective you choose—CEO, engineer, investor, parent. Save important clusters into Collections and use Collection Chat to ask questions across your saved knowledge, with answers that cite back to the underlying sources. ### Why we built it Keyword alerts are noisy, duplicate-ridden, and never explain implications. Agentic News is built to deliver fewer, better alerts—deduplicated coverage with fast, role-aware interpretation and receipts. It's the difference between drowning in headlines and understanding what actually matters to you. ### How it works 1. Create Agents for topics, companies, or interests you want to track 2. Incoming articles are deduplicated into story Clusters with multiple sources 3. AI Lenses interpret each cluster from your chosen perspective (factual, simplified, outlook, personal meaning) 4. Optionally monitor company websites for meaningful changes via Company Tracker 5. Save clusters to Collections and ask AI questions across your saved knowledge (with citations) 6. Get daily or weekly email briefings tailored to your timezone and schedule ### Features - Agents that track topics, competitors, and niche interests by meaning, not keywords - Deduplicated story Clusters that collapse repeated coverage into a single view with multiple sources - Two-stage editorial filter: a skeptical Devil's-Advocate gate that rejects off-topic matches before they reach you, with the reasoning visible per story - Role-aware AI Lenses: factual summary, ELI12, outlook, personal meaning, and integrated brief - Collections to save and organize important clusters - Collection Chat: ask AI questions across saved clusters with cited answers - MCP server with 26 tools and OAuth for Pro subscribers—pull briefings, save clusters, and refine agents from inside Claude, ChatGPT, and other AI clients - Preference learning that refines match quality over time based on your feedback - Configurable email briefings (daily/weekly, timezone-aware) - Adjustable match quality threshold so you control signal vs. coverage ### Pricing Free to start with no credit card — a 7-day activation grant — then $9 per month or $79 per year. Cancel anytime. No native apps required—runs in any browser, with optional MCP integration for AI clients on Pro. ### Notes - **Web App Only:** No native iOS/Android app; responsive web app - **Audience:** Competitive intelligence, research, investing, tech tracking, niche interests, anyone tired of noisy news alerts - **Disclaimers:** Links to original sources; does not republish full paywalled text - **Tech Stack (high-level):** Next.js 15 + Tailwind + shadcn/ui; Node (Fastify) API + BullMQ workers; Postgres (Neon) + pgvector + Drizzle ORM; Redis; OpenAI embeddings + GPT-5; NewsAPI.ai + RSS for ingestion; Render + Sentry + Amplitude --- ## Decomposer **Status:** Live **Platforms:** Web (Production MVP) — https://decomposer.io/ **Project page:** https://skylarkcreations.com/projects/decomposer **Pricing summary:** Free · Pro $10/mo Turn sprawling goals into structured, executable plans. Focus on one task at a time with per-task guidance, honest effort routing, and copy-ready prompts for every step. Honest effort routing. Quality scoring. Copy-ready prompts for every step. ### Overview Decomposer is an AI planning tool that takes a sprawling, multi-part goal and turns it into 8-14 concrete task cards -- each with a title, specific action items, dependencies, and a paste-ready sub-prompt you can run in any AI tool. Every card gets an honest effort label: You (👤), AI (🤖), or Expert (🧰) -- so you know exactly what to delegate, what to do yourself, and when to call in a specialist. After the plan is built, Focus View shows you one task at a time with a checkable action list (prerequisites, steps, verify, capture) and a paste-ready prompt -- so the plan is something you work through, not just a document you read. Plans are persistent, shareable, and editable. As you finish a task you can capture its output inline, and that output flows into dependent cards so downstream steps refine themselves automatically. ### Why we built it People bring big goals to AI and get paragraphs that sound smart but collapse during execution. Steps get missed, tasks overlap, and nothing tells you which parts actually need a human. You shouldn't need prompt-engineering skills to get a plan you can follow. Decomposer sits upstream of execution. It makes the problem legible, routes work honestly, and hands you structured prompts -- so when you do open your preferred AI tool, you already know exactly what to ask. ### How it works 1. **Describe your goal** -- Paste your objective and add context. Upload documents if you have them (PDF, Word, images, Markdown). Decomposer forms an observed brief and surfaces hidden assumptions you can accept or edit. 2. **Get a structured plan** -- The AI generates 8-14 task cards with titles, action items, effort labels, dependencies, and copy-ready sub-prompts. 3. **Review quality** -- A built-in evaluator scores coverage, redundancy, actionability, label routing, and synthesis fit, flagging gaps before you start working. 4. **Execute and refine** -- Track status per card, edit inline, capture outputs. Completed task outputs propagate to dependent cards so downstream prompts sharpen automatically. 5. **Take it anywhere** -- Copy sub-prompts into your preferred AI tool. Export to PDF or Markdown. Share persistent links with teammates. ### Features - **Planning** -- Works across any domain with no rigid templates - **Planning** -- Surfaces hidden assumptions and constraints before you start - **Planning** -- Coherent plan summary with cross-cutting risk identification - **Planning** -- Granularity coaching flags tasks that are too broad or too narrow - **Effort Routing & Quality** -- Honest labels: You (👤) / AI (🤖) / Expert (🧰) - **Effort Routing & Quality** -- Five-dimension quality evaluation that flags coverage, redundancy, and label-routing gaps before you start - **Execution** -- Focus View: work one task at a time with the rest of the plan parked behind a toggle - **Execution** -- Per-task action checklists with prerequisites, steps, verification, and an inline output-capture step - **Execution** -- Dependency flow: completed outputs auto-refine downstream tasks - **Execution** -- Inline editing, status tracking, and plan history with auto-save - **Execution** -- Document upload: PDF, Word, images, text, Markdown - **Portability** -- Copy-ready sub-prompts for ChatGPT, Claude, Gemini, or local models - **Portability** -- PDF export with professional formatting - **Portability** -- Markdown export for any tool - **Portability** -- Persistent shareable links - **Portability** -- Private by default -- we don't train on your data ### Pricing Free -- 3 plan generations. Pro -- $10/month -- Unlimited plan generations, daily progress digests, priority support. ### Notes - **Status:** Production -- Focus View, per-task action checklists, inline output capture, document upload, mobile-first, dependency tracking - **Model-Agnostic:** Thin adapter layer allows model swapping as quality and cost evolve - **No Lock-In:** Everything exports cleanly --- ## Learn the Dao **Status:** Live **Platforms:** Web (Live) — https://learnthedao.com **Project page:** https://skylarkcreations.com/projects/learn-the-dao **Pricing summary:** Free Internalize the Tao Te Ching, one verse at a time. A spaced-repetition companion that schedules each of the 81 chapters for the exact moment you're about to forget — so the text moves off the page and into memory. Start free, no account needed. Spaced repetition for the Tao Te Ching — a few minutes a day, scheduled for the moment you're about to forget. ### Overview Learn the Dao is a spaced-repetition companion for the Tao Te Ching, the 2,500-year-old Taoist classic. Instead of reading it once and forgetting it, you work through the 81 chapters verse by verse, and a proven memory algorithm (FSRS) schedules each review for the exact moment you're about to forget — so the text moves from the page into memory and stays there. Start without an account: "Begin without an account" drops you straight into your first chapter. Your progress and review schedule carry over when you decide to make an account. ### Why we built it The Tao Te Ching rewards return, not a single read — its lines land differently once they live in your head. But re-reading a book cover to cover is a poor way to remember any of it. Spaced repetition is the best-studied way to make something stick with minimal time; Learn the Dao applies it to a text worth keeping. ### How it works 1. **Begin without an account** — start your first chapter immediately, no signup gate. 2. **Read in two renderings** — the 1891 Legge translation and Dao De Kooi side by side, so you engage the meaning. 3. **Review on schedule** — the FSRS algorithm surfaces each verse right when you're on the edge of forgetting, so a few minutes a day compounds. 4. **Keep your progress** — make an account whenever you want; your schedule and history carry over. ### Features - **Spaced repetition (FSRS)** — reviews scheduled by a modern memory algorithm, not fixed intervals - **All 81 chapters** — work through the full Tao Te Ching verse by verse - **Open reading** — /read and all 81 chapter pages are publicly readable with no account, alongside the memorization practice - **No-account trial** — "Begin without an account" starts you instantly; progress carries over when you sign up - **Two renderings side by side** — the 1891 Legge translation and Dao De Kooi, an original rendering written for this project - **Progress that persists** — your review schedule and history follow you across sessions ### Pricing Free. ### Notes - **Status:** Live — free, no account required; learnthedao.com - **Method:** a modern spaced-repetition scheduler (FSRS) times each review for durable memory --- ## Urban Journeys **Status:** Live **Platforms:** Web (Live) — https://urban-journeys.com/ **Project page:** https://skylarkcreations.com/projects/urban-journeys **Pricing summary:** Free · Premium $7/mo or $60/yr Walk your city with intention. Discover it with delight. Urban Journeys composes themed walking routes with curated stops, engaging descriptions, and accurate distances — optimized for discovery, not speed. A journey composer — not a navigation app. Instead of optimizing for speed, it optimizes for discovery, theme, and delight. Tell it where you're starting, how far you want to walk, and what you want to see. ### Overview Urban Journeys is a journey composer — not a navigation app. Instead of optimizing for speed, it optimizes for discovery, theme, and delight. Tell it where you're starting, how far you want to walk, and what you want to see. It crafts an optimized walking route with curated stops, engaging descriptions, and accurate distances. The origin: instead of always driving to the mountains to hike, why not hike the city? The first experiment was "walk to every theater in Denver" — a 35-mile pilgrimage. That's when the real idea emerged: themed urban walks, optimized for humans, not cars. A 5-phase streaming pipeline discovers POIs from Google Places, curates the best stops with GPT-5.6-luna, optimizes route order with TSP algorithms, adjusts distance to hit your target within 15%, then narrates the whole journey. Progress streams to your browser in real time so you can watch each phase unfold. ### Why we built it Navigation apps answer "get me from A to B." Urban Journeys answers "give me an experience." Points aren't obstacles — they're the point. We built it to push past the same top-10 lists and star ratings and bring back serendipity to everyday life. The hybrid approach — LLMs for creativity, algorithms for math — ensures accurate distances while maintaining personalized, engaging content. ### How it works 1. **Enter your starting location** — Address autocomplete via Google Places 2. **Choose your journey size** — Quick Walk (1.5 mi / 45 min) to Epic Trek (12 mi / 6 hr) 3. **Pick your themes** — 12 discovery themes with real-time POI counts showing what's near you 4. **Compose** — Watch a 5-phase pipeline: Discovery (Google Places) → Curation (GPT-5.6-luna) → Optimization (TSP solver) → Distance Adjustment → Narration 5. **Export & Go** — Open in Google Maps, Apple Maps, or download GPX for your favorite hiking app ### Features - **12 Discovery Themes** — Theaters, street art, breweries, coffee shops, bookshops, live music, parks, historic buildings, food, architecture, vintage shops, markets - **6 Journey Sizes** — Quick Walk (1.5 mi) to Epic Trek (12 mi) with calibrated stop counts and search radii - **Hybrid AI + Algorithm Pipeline** — GPT-5.6-luna curates interesting stops; TSP algorithms (nearest-neighbor + 2-opt + or-opt) optimize route order - **Real-Time SSE Streaming** — Watch the 5-phase composition pipeline as it works - **Accurate Distances** — OpenRouteService walking directions keep routes within 15% of target - **Export Anywhere** — GPX download, Google Maps, Apple Maps - **City-Agnostic** — Works in any city worldwide via Google Places - **Loop or Point-to-Point** — Your choice ### Pricing Free — 3 walks a day and up to 5 saved journeys. Premium — $7/month or $60/year, unlimited. Without an account: 1 walk a day. ### Notes - **Tech Stack:** Next.js 15, TypeScript, React 19, Tailwind CSS, Mapbox GL JS, OpenAI GPT-5.6-luna (curation) + GPT-5.4-mini (narration), Google Places API, OpenRouteService - **Performance:** 60-90 second composition time, <2% error rate, 100% POI accuracy (verified via Google Places) - **For Whom:** Urban explorers, tourists, locals seeking new perspectives, anyone who'd rather discover than navigate --- ## AniMoment **Status:** Live **Platforms:** Web (Live — camera or photo upload) — https://animoment.app **Project page:** https://skylarkcreations.com/projects/animoment **Pricing summary:** Free to try **Privacy policy:** https://animoment.app/privacy Take a photo and receive a gentle, spoken animist reading of place. AniMoment honors the relational essence of everything—lake, tree, rock, soil—as different expressions of Earth. Warm, grounded, concrete — honoring the relational essence of place ### Overview AniMoment is a web application that transforms how we relate to the places we inhabit. Take a photo from your camera or photo library, and receive a gentle, spoken animist reading that honors the relational essence of everything around you—lake, tree, rock, soil, path, sky. Each reading is generated using AI vision technology, then spoken aloud, creating a moment of calm, grounded presence. AI reads the scene and writes a warm, grounded reading in AniMoment's animist voice. Each reading concludes with a tiny 10-30 second practice to help you pause and notice what's here. Your last 20 moments are stored locally on your device, creating a personal archive of presence. AniMoment is for anyone seeking a calmer, more relational way of being in place. No dogma, no cultural borrowing—just warm acknowledgment of the world as living matter expressing itself in infinite forms. Whether you're walking in nature, sitting in a park, or pausing in your daily routine, AniMoment invites you to greet the beings around you with presence and care. ### Why we built it In a world of constant noise and abstraction, we often move through places without truly noticing them. We see "scenery" or "environment" rather than recognizing that everything around us—water, stone, path, soil, tree—has presence and character. Ancient animist traditions understood this, but we wanted to create something contemporary and accessible, without appropriating specific cultural practices. AniMoment emerged from a simple question: What if technology could help us slow down and pay attention? What if AI could serve not just productivity, but presence? By combining computer vision with carefully crafted prompts, we created a tool that gently guides users to see their surroundings as relational beings worthy of acknowledgment. It's not about belief or spirituality—it's about practicing a warmer, more grounded way of being in the world. ### How it works 1. **Capture or Upload**: Open AniMoment in your browser and take a photo with your camera or upload one from your photo library. The image is automatically compressed client-side for privacy and efficiency. 2. **AI Interpretation**: The image is sent to GPT-5.4-mini with vision, which analyzes what's present in the scene. Our carefully crafted prompts guide the AI to generate a warm, concrete reading that acknowledges specific beings (path, water, sky, stone, plants) with light personification. 3. **Spoken Aloud**: The reading is converted to speech using either your device's Web Speech API (free, on-device) or optional ElevenLabs voices (premium). The audio plays automatically while you can read along. 4. **Save & Share**: Your moment is automatically saved to IndexedDB (last 20 moments), and you can share it via your device's native share sheet (requires HTTPS on mobile). The entire experience takes 5-10 seconds from photo to spoken reading, creating a gentle ritual of pause and presence wherever you are. ### Features - 📸 **Camera & Photo Upload** - Capture moments directly or upload from your library - 🎭 **A Warm Animist Voice** - Every reading is written in AniMoment's warm, grounded animist voice - 🔊 **Spoken Aloud** - Readings are automatically converted to speech for listening - 💾 **Local Storage** - Last 20 moments saved privately in your browser (IndexedDB) - 🌐 **Web Share API** - Share moments via your device's native share sheet - 🌙 **Wake Lock** - Screen stays awake during audio playback - 🎨 **Beautiful, Calm UI** - Earth tones, gentle gradients, and clear typography - ⚡ **Fast Generation** - 5-10 seconds from photo to spoken reading - 🔒 **Privacy-First** - Images compressed client-side; optional server TTS - 🆓 **Free to Try** - First 3 readings free, no sign-up. Credit packs: 20 for $5, 60 for $12, 200 for $30. Optional $6/mo subscription ### Notes - **Tech Stack**: Built with Vite, TypeScript, Node.js, OpenAI GPT-5.4-mini (vision), ElevenLabs (optional), Web Speech API, IndexedDB, and Web Share API - **For Whom**: Seekers, walkers, contemplatives, nature lovers, mindfulness practitioners, and anyone curious about relating more warmly to their surroundings - **Approach**: No dogma, no cultural borrowing—just calm acknowledgment of place as living presence - **Cost**: ~$0.004 per reading (measured); Web Speech API is free (on-device) - **Privacy**: Images processed via OpenAI's API; no permanent storage server-side; all moments stored locally in your browser - **Roadmap**: Place memory, time-aware readings, gentle ambient audio, "Dear Neighbor" social feed (opt-in), iOS native app, multi-language support --- ## Disunion Feed **Status:** Live **Platforms:** Web (Live) — https://disunionfeed.com/ **Project page:** https://skylarkcreations.com/projects/disunion-feed **Pricing summary:** Free The road to the Civil War, as a scrollable feed. Disunion Feed styles the real newspaper editorials, speeches, and letters of 1856–1861 as social-media cards — every one linked to its verified primary source — so you can read the actual American discourse as the country came apart. Real editorials, speeches, and letters from 1856–1861, styled as a scrollable social feed — every card linked to its verified primary source. ### Overview Disunion Feed takes the real newspaper editorials, speeches, and letters of 1856–1861 and presents them as a scrollable social feed, so you can read the actual American discourse on the road to the Civil War the way it unfolded — voice by voice. The site currently covers four events across 123 first-party-verified passages: John Brown's raid on Harpers Ferry, the caning of Charles Sumner, the Dred Scott decision, and the complete secession winter — from November 1860 through Fort Sumter in April 1861, told across five chapters. Every card links to its verified primary source, and a Method page documents how passages are verified. Each passage can be shared as an image with its citation and source domain baked in. There is no login, no install, and nothing to pay — a static site built to make primary sources readable. ### Why we built it Most accounts of the road to the Civil War are summaries. The primary sources — what editors, senators, and citizens actually published at the time — are scattered across archives and hard to read in sequence. Styling them as a feed makes the era's discourse legible in the format we already know how to read, without editorializing on top of it. ### Features - **Primary sources only** — every card links to its verified first-party source - **Four events, 123 verified passages** — Harpers Ferry, the Sumner caning, Dred Scott, and the complete secession winter (November 1860 → April 1861, in five chapters) - **A documented method** — the About page explains how each passage is verified - **Shareable cards** — every passage exports as an image with its citation and source domain baked in - **No account, no install** — free, responsive, works on any device ### Notes - **Status:** Live — free, no ads, no login. - **For Whom:** History readers, teachers, students — anyone who'd rather read what people actually wrote than a summary of it. --- ## QuickBite **Status:** Live **Platforms:** Web (Live - works on all devices) — https://quickbite.food/ **Project page:** https://skylarkcreations.com/projects/quickbite **Pricing summary:** Free · Pro $5/mo Turn a 30-minute "where should we eat?" debate into a 2-minute decision. QuickBite helps groups quickly agree on restaurants through fast, fair voting with transparent consensus scoring. The collaborative restaurant decision tool for groups who are tired of the 30-minute "where should we eat?" debate. Everyone votes on 10 curated restaurants, and our transparent algorithm instantly computes a fair winner. ### Overview QuickBite is a group decision-making app designed to solve one of life's most frustrating micro-debates: "Where should we eat?" Whether you're out with friends, planning a family dinner, or organizing team lunch, the endless back-and-forth of "I don't know, what do you want?" can waste 30+ minutes of everyone's time. With QuickBite, the process takes less than 2 minutes. The host creates a session by choosing a location and setting preferences (cuisine types, dietary restrictions, search radius). QuickBite then curates 10 restaurant candidates using Google Places data, filtered intelligently by cuisine, open hours, distance, and dietary needs. Each participant votes on all 10 restaurants with a simple three-option system: Yes (strong preference), Maybe (acceptable), or No (rather not). No lengthy deliberation—just quick, honest preferences. Once everyone votes, QuickBite instantly calculates a fair winner using a transparent scoring algorithm. The system considers vote preferences, distance penalties, price matching, and open hours to find the restaurant that best satisfies the whole group. Results show the top 3 options with detailed scoring breakdowns, so everyone understands why the winner was chosen. Voters never need an account, it works on any device, and it provides instant links to Google Maps for directions. ### Why we built it We've all been there: standing on a street corner with friends, or sitting in a Slack channel with coworkers, throwing out restaurant suggestions that get lukewarm responses. "How about Thai?" "Eh, I just had Thai yesterday." "Mexican?" "Too far." "That new burger place?" "Too expensive." The conversation spirals, people get hungry and cranky, and eventually someone just makes an executive decision that leaves others unsatisfied. This isn't a technology problem—it's a coordination problem. Groups struggle to aggregate individual preferences quickly and fairly. Existing solutions are either too slow (lengthy text discussions), too random (spinning a wheel feels arbitrary), or too complicated (spreadsheets, polls with unclear methodology). We built QuickBite to provide speed, fairness, and transparency: everyone's voice counts, the math is clear, and you get from "where should we eat?" to sitting down at a table in minutes instead of half an hour. ### How it works **Creating a Session:** The host starts by setting a search location (current location or entered address) and configuring preferences: search radius (1-50 miles), cuisine types (30+ options like Thai, Italian, Mexican, Sushi), facility types (restaurants, cafes, food trucks, bakeries), dietary restrictions (vegetarian, vegan, gluten-free, halal, kosher, etc.), and time slot ("now" or "tonight"). QuickBite queries the Google Places API to find up to 20 restaurants, then intelligently filters and scores them based on open hours, distance, cuisine matches, and dietary considerations. The system selects the best 10 candidates and stores them for the voting session. **Voting:** The host shares a simple link with the group (via text, email, Slack, etc.). Participants join by entering a nickname—no signup, no authentication. Everyone votes on the same 10 restaurants using a fast card-swipe interface. For each restaurant, you see a photo, name, cuisine types, rating, distance, price level, address, phone, and hours. You choose: 👍 Yes (I'd love to go here, +2 points), 🤷 Maybe (It's fine, +1 point), or 👎 No (I'd rather not, 0 points). The whole process takes about 90 seconds per person. **Results:** Once everyone expected has finished voting, the winner is revealed automatically using a fair, transparent algorithm: base score from votes, minus distance penalties (scaled by search radius), price mismatch penalties (if the group set a budget preference), and closed-restaurant penalties. The results page shows the top 3 restaurants with full scoring breakdowns, so everyone can see why the winner was chosen. Participants can open the winner directly in Google Maps and get directions. Late joiners can still vote, and their preferences are instantly reflected in the results. ### Features - **Location-based Discovery**: Use your current location or enter any address to find nearby restaurants within 1-50 miles - **Smart Filtering**: 30+ cuisine types, 8 facility types (restaurants, cafes, food trucks, etc.), 10 dietary restriction tags, and time-slot optimization ("now" vs "tonight") - **Dietary-Trust Tiering**: Dietary tags are labelled by what the data can actually verify — vegetarian is hard-gated on a structured field; everything else is shown as an unverified signal rather than a false checkmark - **Hours-Aware**: Automatically filters out closed restaurants and those closing soon; includes places opening within 30 minutes - **Fast Group Voting**: No authentication required—just enter a nickname and start voting in seconds - **Three-Option Voting**: 👍 Yes (+2), 🤷 Maybe (+1), 👎 No (0) for quick, intuitive preference expression - **Fair Consensus Algorithm**: Transparent scoring with distance penalties, price matching, and detailed breakdowns so everyone sees why the winner was chosen - **Mobile-Responsive**: Works on phones, tablets, and desktops with a touch-optimized voting interface - **Instant Results**: Top 3 ranked restaurants with scoring explanations and direct Google Maps integration - **Real-Time Participation**: See who's joined, who's voting, and who's completed in real-time - **Zero Friction for Voters**: No app downloads, no signups, no passwords for participants—the host shares a link and everyone votes ### Notes - **Current Status:** Live — fully deployed and functional. Hosts have accounts with a free tier (3 sessions/month) and Pro ($5/month) via Stripe; voters never need an account. - **Tech Stack:** Built with Next.js 15, TypeScript, React, Tailwind CSS, PostgreSQL, Prisma ORM, and integrates the Google Places API (New) - **Privacy:** No long-term user accounts required; sessions are ephemeral and auto-expire after 48 hours - **For whom:** Friend groups, families, coworkers, remote teams, anyone tired of the "where should we eat?" debate - **Scoring Philosophy:** Transparent > Random. Every penalty and tie-breaker is explained so groups trust the outcome - **Roadmap Highlights:** Auto-tally at 70% participation, better duplicate detection, host controls, re-roll alternatives, ordering integration (DoorDash/Uber Eats), optional user accounts with session history --- ## Quiet Tab **Status:** Available for Chrome **Platforms:** Web (Available — Chrome extension + landing page) — https://quiet-tab.com **Project page:** https://skylarkcreations.com/projects/quiet-tab **Privacy policy:** https://quiet-tab.com/privacy.html **Source:** https://github.com/u00dxk2/quiet-tab Hide Gmail's unread count in your tab title so you can focus and check email on your terms. A tiny Chrome extension that removes Gmail's unread count from your tab title—so you can focus and check email on your terms. ### Overview Quiet Tab is a tiny Chrome extension that removes the distracting unread email count (like "(4)") from Gmail's browser tab title. It's built for anyone who keeps Gmail open while working and wants fewer attention triggers and less background anxiety. It runs only on mail.google.com, requires zero special permissions, and doesn't collect any data. ### Why we built it Gmail's unread badge in the tab title is a persistent attention trigger. Quiet Tab removes that trigger while keeping Gmail open and accessible when you choose to check it. ### How it works 1. **Install the extension** (Chrome Web Store listing pending) 2. **Open Gmail as usual** 3. **Quiet Tab watches for title changes** as Gmail updates unread counts 4. **It removes the "(number)" pattern locally** and updates the tab title 5. **Gmail stays open, but the nagging count disappears** ### Features - Removes the unread count from Gmail tab titles automatically - Zero special permissions; runs only on `https://mail.google.com/*` - No tracking, no analytics, no data collection - Open source and inspectable ### Notes - **Category:** Browser extension · Productivity / Focus - **Platform:** Chrome Extension (Manifest V3) - **Pricing:** Free (open source) - **Permissions:** None (`"permissions": []`); content script scoped to Gmail only - **Data:** Does not collect, store, transmit, or process personal data - **Attribution:** Skylark Creations — product concept, design, development, and landing page --- ## Sagent **Status:** Available on iOS **Platforms:** iOS (Available on App Store) — https://apps.apple.com/us/app/sagent-guidance-on-demand/id6747406673 **Project page:** https://skylarkcreations.com/projects/sagent **Privacy policy:** https://skylarkcreations.com/projects/sagent/privacy-policy **Terms of service:** https://skylarkcreations.com/projects/sagent/terms-of-service Sagent lets you consult timeless minds—Buddha, Epictetus, Laozi, Jesus, Carl Sagan, Mark Twain, Rumi, and Kurt Vonnegut—about modern dilemmas. Ask a question and get guidance in the voice and spirit of your chosen mentor. Choose a guide—Buddha, Epictetus, Laozi, Jesus, Carl Sagan, Mark Twain, Rumi, or Kurt Vonnegut—and get advice shaped by their voice and worldview. ### Overview Sagent (short for "sage agent") was my first solo project — a philosophical chatbot designed for modern life. Choose a guide—Buddha, Epictetus, Laozi, Jesus, Carl Sagan, Mark Twain, Rumi, or Kurt Vonnegut—and get advice that reflects their worldview and style. Whether you're seeking perspective, clarity, or a smart laugh, Sagent meets you where you are. ### Why we built it Most of us wish we had a wise mentor on call. Sagent makes that feeling accessible—anytime, anywhere—by channeling enduring ideas through approachable conversation. ### How it works We pair advanced language models with persona designs informed by primary texts and trusted summaries. Each philosopher's "voice" is carefully guided so the counsel feels timely without losing what makes the original thinker distinctive. ### Features - Eight distinct guides: Buddha • Epictetus • Laozi • Jesus • Carl Sagan • Mark Twain • Rumi • Kurt Vonnegut - Voice‑true counsel: answers shaped to each figure's tone and core ideas - Perspective switching: see your question reframed by different traditions - Modern relevance: ancient insight translated to practical next steps - Light when possible, deep when needed: from gentle re‑centering to bracing Stoic tough love—and the occasional Twain zinger ### Notes - For whom: founders, students, seekers, writers, overthinkers, under‑sleepers—anyone who wants perspective without the pedestal. - AI‑generated creative simulations inspired by historical figures—not direct quotes or endorsements—and not professional advice. --- ## Frolic **Status:** Live **Platforms:** Web (Live — Denver) — https://frolic.town/ **Project page:** https://skylarkcreations.com/projects/frolic **Pricing summary:** Free — no paywall, no save cap AI event discovery for Denver — natural-language search plus personalized picks across concerts, comedy, food, arts, sports, and free things to do. Deep Research agents and multi-source event data keep the inventory fresh; browsing is free, no signup required. AI-powered event discovery for Denver. Frolic combines Deep Research agents, multi-source event data, and a personalization engine that learns your preferences over time. ### Overview Frolic is a full-stack application that helps you discover events and things to do in Denver, tailored to your preferences. The platform combines AI-powered recommendations, automated event curation, and real-time data from multiple sources to deliver personalized experiences. A scheduled batch processing pipeline uses Deep Research agents to build a high-quality event inventory — a nightly run for Denver. Events are ingested from 21 scraping sources plus Ticketmaster, ESPN, 19hz and Eventbrite APIs, and Google Places, then normalized, geocoded, validated, deduplicated, and stored in MongoDB for fast geospatial and temporal queries. The AI recommendation engine considers your preferences and history (via a Memory Service that learns over time), current context (time, location, companions, budget), deterministic filters (distance, price, accessibility), and a scoring algorithm that balances distance, popularity, category match, and freshness. ### Why we built it Most discovery apps show the same top-10 lists and star ratings. Frolic is built to bring back serendipity — surfacing offbeat, delightful things to do right now, personalized to who you are and what you're in the mood for. The cache-first architecture means recommendations are instant, not waiting on slow API calls. ### How it works 1. **Tell Frolic what you're looking for** — or let context (time, location, companions, budget) guide the recommendations 2. **AI curates and ranks** — OpenAI scores and reranks events from the cached inventory based on your preferences and context 3. **Smart filtering** — Budget, distance, time slot, and companion-based filters narrow results to what's actually doable 4. **Personalization improves over time** — The Memory Service tracks your activity preferences, budget tendencies, location history, and feedback to refine future recommendations ### Features - **AI-Powered Recommendations** — OpenAI-driven personalization based on user preferences and context - **Automated Event Curation** — Scheduled Deep Research agents precompute the Denver event inventory in a nightly run - **Multi-Source Integration** — Combines 21 scraping sources plus Ticketmaster, ESPN, 19hz and Eventbrite APIs, and Google Places for broad coverage - **Cache-First Architecture** — MongoDB-backed for instant responses; events are pre-indexed for geospatial and temporal queries - **Smart Filtering** — Budget, distance, time, and companion-based filtering - **User Memory & Personalization** — Learns activity preferences, budget tendencies, and feedback over time - **Real-Time SSE Streaming** — Recommendations stream to the client as they're generated ### Notes - **Tech Stack:** Node.js + Express, MongoDB + Mongoose, OpenAI GPT-4, React Native (Expo), JWT + Apple Sign-In, Server-Sent Events, node-cron - **Data Sources:** 21 scraping sources plus Ticketmaster, ESPN, 19hz and Eventbrite APIs, and Google Places - **Current Scope:** Denver metro area; multi-city support in progress - **For Whom:** Anyone looking for something to do — solo, couples, families — who wants personalized suggestions beyond generic top-10 lists --- ## Syntopica **Status:** Live Beta **Platforms:** Web (Live beta) — https://syntopica.ai/ **Project page:** https://skylarkcreations.com/projects/syntopica **Pricing summary:** Free during beta Make your books think together. Syntopica imports your Amazon library and Kindle highlights, then helps you do cross-book synthesis — bringing together ideas from multiple books to form new understanding. An AI-powered reading companion for serious readers. Import your entire Amazon book library and Kindle highlights, then do what no other tool does: cross-book synthesis — bringing together ideas from multiple books to form new understanding. ### Overview Syntopica is an AI-powered reading companion named after syntopical reading — the highest level of reading described by Mortimer Adler in How to Read a Book: reading multiple books on a single subject and constructing an analysis that none of them contain individually. The Capture layer is complete: a Chrome extension imports your full Amazon library (Kindle, Audible, physical) and Kindle highlights with zero manual entry, using Amazon's GraphQL API for books and DOM scraping for highlights. Background sync keeps everything current on a 4-hour cycle. The web app provides a library grid with covers, book detail pages, and a highlights viewer. A three-source metadata enrichment pipeline (Google Books → OpenLibrary → Wikidata SPARQL) achieves 93% description coverage and 92% ISBN coverage. The Think layer is live: AI-powered collections for grouping books by theme, asking questions across them, and generating citation-backed synthesis. ### Why we built it Serious readers accumulate thousands of highlights across hundreds of books, but those ideas stay siloed. Goodreads tracks what you've read; Readwise resurfaces quotes. Neither helps you think across books. Syntopica is built for the reader who wants to ask "What do these five authors say about attention?" and get a cited, synthesized answer drawn from their own library. ### How it works 1. **Install the Chrome extension** — it reads your Amazon library and Kindle highlights automatically 2. **Import** — Books arrive in chunked uploads (150/chunk), highlights in batches of 300, with auto-retry and recovery 3. **Enrich** — A background worker progressively enriches books from Google Books, OpenLibrary, and Wikidata SPARQL 4. **Browse** — Library grid, book detail pages, all-highlights view with search and filtering 5. **Synthesize** — AI collections for cross-book questions, citation-backed synthesis, and single-book deep reading assists ### Features - **Full Amazon Library Import** — Kindle, Audible, and physical books via Chrome extension; 4,200+ books imported at scale with zero errors - **Kindle Highlight Extraction** — 29,000+ highlights imported via DOM scraping with multi-pass scroll strategy - **Background Auto-Sync** — 4-hour cycle keeps library and highlights current - **Three-Source Enrichment** — Google Books + OpenLibrary + Wikidata SPARQL for 93% description coverage - **Library Grid + Book Detail** — Cover images, metadata, highlights viewer, search and filters - **Cross-Book Synthesis** — AI collections, thematic grouping, citation-backed analysis ### Notes - **Tech Stack:** Next.js 16, TypeScript, React 19, Tailwind CSS 4, Neon PostgreSQL + Drizzle ORM, Supabase Auth, OpenAI (GPT-5.4 / GPT-5.6 class models + text-embedding-3-small + Whisper), Chrome Extension (Manifest V3), Sentry, Amplitude - **Chrome Extension:** live on the Chrome Web Store — https://chromewebstore.google.com/detail/gppcjaalakkmokmjoaljckfblibkmmcp - **Current Status:** Live beta — Capture and Think both complete. Cross-library synthesis via collections, syntopical briefs, and single-book deep reading are live; citations link to the reader's own highlights. - **For Whom:** Serious readers, researchers, lifelong learners who want their reading to compound --- # In development Being built now. Public pages describe what they are; the products aren't open yet. --- ## Dreamflyer **Status:** In Development **Platforms:** iOS (Planned); Android (Planned) **Project page:** https://skylarkcreations.com/projects/dreamflyer A first‑person, meditative flying game that recreates the feeling of dream‑flight using a gentle breaststroke motion. ### Overview Dreamflyer is about that weightless, lucid sensation so many of us know from sleep—gliding over rooftops, skimming treetops, drifting higher with calm, rhythmic strokes. Instead of adrenaline and speed, Dreamflyer aims for presence, ease, and flow—part flight sim, part moving meditation. ### Why we built it We wanted to bottle the specific way some dreams feel: you "swim" through the air with slow, smooth breaststroke pulls, and the world responds with effortless lift. ### How it works On mobile, arm sweeps (or small wrist motions) are tracked by device sensors to translate stroke cadence and amplitude into forward glide and gentle climbs. Subtle phone tilts guide heading and pitch. On the web, accessible controls mimic the same stroke‑to‑motion feel. Physics are tuned for dream logic—stable horizons, soft banking, forgiving stalls—so you can relax into the glide without motion sickness. ### Features - Optional breath‑to‑lift (mic‑based breathing sync) - Guided "flow flights" with ambient soundscapes - Free‑flight exploration over stylized landscapes - Comfort settings: vignette, horizon lock, etc. - Gentle challenges: thermals, rings, cloud currents ### Notes - Goal: a few minutes of calm, creative escape that genuinely feels like flying—one easy breaststroke at a time. --- ## Urban Beaver **Status:** In Development **Platforms:** iOS (In active development - iOS 16.0+ (Xcode prototype)); Android (Planned if iOS version successful) **Project page:** https://skylarkcreations.com/projects/urban-beaver A relaxing 2D puzzle game where you build beaver dams to stop water and fill ponds. Drag logs and twigs, watch water accumulate, and create your perfect pond sanctuary. A meditative puzzle experience where every log matters and every pond tells a story ### Overview Urban Beaver is a relaxing 2D puzzle game where you become nature's engineer. Using drag-and-drop controls, you place logs and twigs to build dams that stop flowing water and create serene beaver ponds. Watch as individual water particles collide with your structures, accumulate behind your dam, and gradually fill the pond to your target level. It's a meditative experience that combines physics-based puzzles with the satisfaction of creating something beautiful. Designed for anyone seeking a calm, focused puzzle experience. Whether you're decompressing after a long day, looking for a mindful mobile game, or just love nature-inspired challenges, Urban Beaver offers a unique blend of strategy and serenity. The game rewards thoughtful placement and experimentation—every gap in your dam matters, and every successful pond feels earned. Built from the ground up with Swift and SpriteKit, Urban Beaver features realistic physics simulation, smooth touch controls including two-finger rotation, and a growing variety of building materials. The landscape-only orientation maximizes your workspace, giving you the full riverbed canvas to express your inner architect. ### Why we built it Most mobile puzzle games rush you with timers, lives, and constant pressure. We wanted to create something different—a game that respects your pace and rewards thoughtful experimentation. The idea came from watching real beavers work: they're patient, methodical, and create something genuinely impressive through incremental effort. That felt like the perfect metaphor for a puzzle game that's actually relaxing. We also wanted to explore physics-based gameplay in a way that feels intuitive and satisfying. Every water particle, every collision, every leak in your dam is simulated in real-time. When your dam holds and the pond fills, it's not because the game scripted it that way—it's because your structure actually works. That cause-and-effect relationship creates a deeply satisfying gameplay loop that never gets old. ### How it works **Gameplay Flow:** 1. **Place Pieces:** Drag logs and twigs from your supply area and drop them anywhere in the riverbed. Use two-finger rotation to angle pieces perfectly. 2. **Stop the Flow:** Water particles continuously flow from left to right. When they hit your dam pieces, they splash and accumulate behind the structure. 3. **Build the Pond:** As water builds up behind your dam, a pond visual grows upward. Your goal is to reach and hold a target fill line for a few seconds. 4. **Mind the Gaps:** If your dam has gaps, water will leak through at those specific points. You'll see leak particles spawn and your pond level may drop. Plug the gaps with more pieces to maximize water retention. 5. **Win or Adapt:** Successfully hold the target water level to complete the level. If time runs out before you reach the goal, you can restart and try a new strategy. **Technical Approach:** Urban Beaver uses SpriteKit's physics engine for realistic collisions and settling behavior. A particle pooling system keeps the game performant even with hundreds of water particles on screen. The dam effectiveness algorithm scans vertical slices across your structure to calculate the maximum water height and identify leak points, creating emergent gameplay where every placement decision matters. ### Features - 🪵 **Drag & Drop Building** - Intuitive touch controls for placing logs and twigs - 🔄 **Two-Finger Rotation** - Precise angle control with multi-touch gestures - 💧 **Real-Time Water Physics** - Individual particle simulation with collision detection - 🌊 **Dynamic Pond System** - Watch water levels rise and fall based on dam effectiveness - 🔍 **Smart Leak Detection** - The game identifies gaps in your dam and spawns targeted leak particles - 📊 **Dam Effectiveness Scoring** - Real-time feedback on how well your structure blocks water - 🎯 **Target Fill Challenge** - Reach and maintain pond level goals with visual indicators - ⏱️ **Time-Based Objectives** - Complete levels before time runs out or hold water level thresholds - 🎨 **Landscape Canvas** - Full-screen horizontal gameplay optimized for building - 🧘 **Meditative Pacing** - No lives, no ads, just you and the river ### Notes - **Current Status:** Sprint 2 in progress - Core water simulation and dam mechanics complete; working on win/lose conditions and level progression - **Tech Stack:** Swift, SpriteKit, SwiftUI, OSLog for debugging - **Requirements:** iOS 16.0+, Xcode 15.0+ for development - **Orientation:** Landscape-only for optimal building experience - **For whom:** Puzzle lovers, nature enthusiasts, anyone seeking calm mobile gameplay - **Development Philosophy:** Iterative sprints with clear MVP goals; no feature creep - **Performance:** 60 FPS target with particle pooling and optimized physics --- ## Chat With Feels **Status:** In Development **Platforms:** Web (In development) **Project page:** https://skylarkcreations.com/projects/chat-with-feels With feeling, without fiction. A chatbot with a transparent, neuroscience-inspired emotion engine that modulates style and initiative — tone, cadence, emphasis — while keeping truth and safety intact. A modern chatbot with a transparent, stateful affect layer. The assistant's cognition comes from a frontier LLM, while its style and initiative are modulated by a neuroscience-inspired emotion engine. ### Overview Chat With Feels doesn't pretend to feel — it models a useful slice of the human emotional control loop to make conversations smoother, kinder, and more effective. The affect layer changes style, not substance: tone, cadence, emphasis, and initiative, while keeping truth and safety fully intact. The engine tracks 21 emotion families (anger, joy, awe, gratitude, confusion, nostalgia, and more) using mean-reverting Ornstein-Uhlenbeck dynamics with emotion couplings. A lightweight appraisal layer detects conversational signals and generates emotion deltas. A style transform converts the current affect state into style instructions for the LLM — never altering facts or safety constraints. The system also includes rolling summaries and embedding-based long-term recall for memory, plus time-based proactive check-ins that use current affect to decide when and how to re-engage. ### Why we built it Current chatbots are either flat (no emotional awareness) or performative (fake emotions for engagement). Chat With Feels takes a third path: transparent affect modeling grounded in neuroscience. The emotion engine is visible and honest — it shapes how the assistant communicates, not what it says. ### How it works 1. **Appraisal** — Lightweight keyword and intent detection reads conversational signals and generates emotion deltas 2. **Affect Engine** — 21 emotion families evolve via mean-reverting dynamics (Ornstein-Uhlenbeck) with cross-emotion couplings 3. **Style Transform** — Current affect state is converted to style instructions (tone, cadence, warmth, initiative level) 4. **LLM Generation** — Frontier model receives style instructions alongside the conversation; facts and safety are never altered 5. **Memory** — Rolling summaries + embedding-based long-term recall ensure continuity across sessions ### Features - **21 Emotion Families** — Anger, disgust, fear, sadness, shame, envy, surprise, joy, interest, love, awe, pride, gratitude, relief, calm, nostalgia, boredom, confusion, craving, lust, entrancement - **Mean-Reverting Dynamics** — Ornstein-Uhlenbeck process ensures emotions naturally decay toward baseline - **Emotion Couplings** — Cross-emotion interactions (e.g., joy suppresses sadness, fear amplifies surprise) - **Style-Only Modulation** — Affect changes tone and initiative, never facts or safety - **Long-Term Memory** — Rolling summaries + embedding-based recall for continuity - **Proactive Check-Ins** — Time-based re-engagement modulated by current affect state ### Notes - **Tech Stack:** Node.js 20+, TypeScript, OpenAI, MongoDB (Atlas or local), Vite frontend - **Philosophy:** "With feeling, without fiction" — transparent affect modeling, not simulated emotions - **For Whom:** Anyone who wants AI conversations that feel more natural without sacrificing honesty --- ## Billionaire Army **Status:** In Development **Platforms:** Web (In development — building in private) **Project page:** https://skylarkcreations.com/projects/billionaire-army Your billions. Our goals. Let's go. A civic-accountability platform where the public defines SMART goals and U.S. billionaires are tracked — with receipts — on whether they help solve them. A free, open civic-accountability platform where the public defines the goals and U.S. billionaires are measured against them — every fact sourced, every estimate labeled. ### Overview Billionaire Army is a civic-accountability platform where the public defines SMART goals — Specific, Measurable, Achievable, Relevant, Time-bound — and U.S. billionaires are tracked on whether they help solve them, with receipts. It pairs a sourced index of 1,083 U.S.-connected billionaires (net worth, FEC contributions, SEC filings, foundation 990s, news coverage) with an open, versioned Public Benefit Score whose every component shows its weight, sources, and known limitations in the UI. Facts and commentary are always separated, and every stored fact carries its source, retrieval date, and estimation method. ### Features - **Billionaire index** — 1,083 U.S.-connected billionaires with sourced profiles and inline citations - **Public Benefit Score** — an open, versioned scoring formula; every component shows its weight and sources - **SMART goals** — the public proposes and rates goals; goal pages show which billionaires are positioned to move each one - **Accountability Feed** — a daily AI-curated news feed about the index - **Receipts on everything** — every stored fact carries its source URL, retrieval date, and estimation method ### Notes - **Status:** Pre-launch — the product is fully functional but deliberately unpromoted; public launch is gated on partnership and review. - **Principles:** Facts separated from commentary; no private or personal-security information, ever; donation-funded only (hard cap $100/person/year, no ads, no premium tier). - **For Whom:** Anyone who wants transparent, sourced accountability for concentrated wealth — and a say in what it should accomplish. --- ## Bank-See **Status:** In Development **Platforms:** Web (In development — building toward launch) **Project page:** https://skylarkcreations.com/projects/bank-see GPT-powered adaptive financial literacy for teens (13–18). Money lessons + quizzes run as one swipeable mission with mastery tracking — fronted by Rocco, a sardonic raccoon who makes finance feel like counterculture, not a bank. An adaptive, GPT-powered financial-literacy app for teens — lessons and quizzes delivered as one swipeable mission, with spaced-repetition mastery, in a voice that respects them. ### Overview Bank-See teaches teens (ages 13–18) how money actually works — budgeting, credit, saving, investing — through short, adaptive lessons and quizzes that run as a single swipeable "mission" rather than a read-then-test slog. Lessons are GPT-generated and cached, mastery is tracked with an SM-2 spaced-repetition engine and XP, and the whole surface wears a dark, editorial, anti-establishment design system — fronted by Rocco, a sardonic raccoon mascot. The thesis: financial literacy lands better when it feels like counterculture, not a classroom. ### Features - **Swipeable missions** — each topic's lesson + quiz run as one bounded-swipe flow, not a read-then-test slog - **Adaptive + GPT-generated** — lessons generated and cached per topic; difficulty adapts to the learner - **Mastery that sticks** — SM-2 spaced-repetition + XP track real retention, not just completion - **A voice teens trust** — Rocco the raccoon + a dark editorial design (Space Grotesk / Space Mono, film grain) that respects the audience ### Notes - **Status:** Pre-launch — the product runs in production; public launch is gated on review. - **For Whom:** Teens (13–18) — and the parents and educators who want them money-literate without the lecture. --- # Experiments and archive Built, learned from, and either kept running quietly or retired. --- ## Walk And **Status:** In Personal Use, Sometimes **Platforms:** Web (In personal use) — https://walk-and-web.onrender.com/ **Project page:** https://skylarkcreations.com/projects/walk-and Minimum viable movement. A daily movement coach built around a routine you actually do — self-contained workouts, daily reminders, and a GitHub-style heatmap to visualize consistency. A daily movement coach built around a routine you actually do. Low friction, self-contained coaching, and a heatmap that makes consistency visible. ### Overview Walk And is a daily movement coach designed around one idea: the best workout is the one you actually do. Instead of elaborate programs or gym-centric plans, Walk And pairs with your daily walk and gives you self-contained coaching sessions you can start in under 10 seconds. The app features calendar export for daily reminders, a GitHub-style contribution heatmap to visualize your movement consistency, and a focus on low-friction sessions that fit into the rhythm of your day. ### Features - **Self-Contained Coaching** — Complete workouts without leaving the app - **Daily Reminders** — Calendar export to stay consistent - **GitHub-Style Heatmap** — Visualize your movement contributions over time - **Low Friction** — Start a session in under 10 seconds ### Notes - **Tech Stack:** React 18, TypeScript, Vite, Tailwind CSS, Node.js + Express, Prisma ORM, PostgreSQL - **Hosting:** Render (static frontend + API service + PostgreSQL) - **For Whom:** Anyone who wants a simple, consistent movement habit without the overhead of a full fitness app --- ## Cursor Environment Docs **Status:** Deprecated **Platforms:** Web (Deprecated — GitHub repository) — https://github.com/u00dxk2/cursor-kooi-env-docs **Project page:** https://skylarkcreations.com/projects/cursor-environment-docs **Source:** https://github.com/u00dxk2/cursor-kooi-env-docs Auto-updating environment documentation that keeps Cursor smart about your project. Stop wasting time explaining your environment setup in every conversation. An intelligent documentation system designed for Cursor developers. Automatically maintains fresh environment context, captures mistakes so you never repeat them, and carries across all your AI conversations. ### Overview Cursor Environment Docs is an open-source documentation system specifically designed for developers using Cursor AI. It solves the frustrating problem of repeatedly explaining your development environment setup to AI assistants in every new conversation. The system installs a smart documentation framework in your project's .cursor/ directory that AI automatically reads at session start, checks for staleness, and updates in real-time as you develop. With a simple one-line installation, you get auto-updating documentation that captures your directory structure, shell environment, common commands, tech stack, and—most importantly—environment gotchas and mistakes so you never hit them twice. It's framework-agnostic, git-friendly, and works across Windows, macOS, and Linux. Unlike static documentation that quickly becomes outdated, this system actively maintains itself. Every 7 days (or whenever the AI detects changes), it prompts for a review and update, ensuring your documentation stays synchronized with your actual development environment. ### Why we built it This project was born from real frustration with AI pair programming workflows in Cursor. As a developer working with AI assistants, you constantly encounter the same problems: wasting time explaining your shell syntax (PowerShell vs Bash), hitting the same environment gotchas repeatedly, having AI suggest commands that don't work in your environment, and dealing with inconsistent behavior between different AI conversations. Traditional documentation sits in a README that gets stale within weeks. You need living documentation that AI assistants can automatically consume and maintain. This system bridges that gap—giving AI the environmental context it needs while requiring minimal maintenance from you. ### How it works The system works through Cursor's native ability to read the .cursor/ directory. When installed, it creates a structured template and AI behavior rules that guide documentation creation and maintenance. At the start of every Cursor conversation, the AI automatically reads your project-environment.md file, checks the "Last Updated" timestamp, and offers to update if it's been more than 7 days. During development, the AI updates documentation in real-time when it discovers changes—new dependencies, command syntax issues, environment quirks, or tech stack modifications. You also get platform-specific staleness checker scripts you can run manually anytime. The entire .cursor/ directory is designed to be committed to version control, so your whole team benefits from consistent, shared environmental context. ### Features - 🤖 Auto-Updating Documentation - AI checks every conversation and updates in real-time as you develop - 📝 Self-Documenting System - Automatically captures gotchas and mistakes so you never repeat them - 🔄 Cross-Session Consistency - Carries across all Cursor conversations - ⚡ 5-Minute Setup - One-line installation, minimal configuration required - 🔍 Staleness Checker - Know exactly when your docs need attention - 🎯 Framework Agnostic - Works with any tech stack (Node.js, Python, Rust, Go, etc.) - 💾 Git-Friendly - Version-controlled documentation your whole team can use - 🖥️ Cross-Platform - Full support for Windows, macOS, and Linux - 🤝 Multi-Platform Teams - Documents all team members' platforms in one file - 📚 Complete Examples - Includes working examples for Node.js/Express and Python/Flask ### Notes - Note: This project has been deprecated. It was a developer tool designed for the Cursor AI IDE, leveraging Cursor's ability to automatically read .cursor/ directories and apply maintenance rules. - Open Source: Released under MIT License on GitHub - Team-Friendly: The entire .cursor/ directory should be committed to git—it's shared project documentation, not personal IDE settings --- ## Contact - Studio: https://skylarkcreations.com (contact form on the home page) - Founder: https://davidkooi.com - Newsletter: https://uncagedminds.substack.com Partnership shape: you bring domain expertise and distribution, Skylark builds the product. Engagements typically run 8-12 weeks on equity, flat fee, or revenue share.