start-here
Skill1 starsChanged 4 days agoMITView on GitHub
Start here to build software with Hyper Taste - picks the next skill for where the work is, from idea to shipped app (Mac, web or phone), and says which comes after.
12 other projects use a version of this.
Adopted by
Most recently taken up by
- kevinph4n/skillstheir own version, first seen Nov 8, 2026
- chartergroup/topopttheir own version, first seen Nov 8, 2026
- advisorppc-org/advisorseo-claude-plugintheir own version, first seen Nov 1, 2026
- CorvusWing/CorvusWingtheir own version, first seen Oct 25, 2026
- impactbrussels/AINativeOStheir own version, first seen Oct 20, 2026
- AndyMelnykov/pm-loopstheir own version, first seen Oct 20, 2026
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- AIDevGTM/gtm-cofounder★ 340same name
- Abilityai/cornelius★ 109same name
- chartergroup/topopt★ 26same name
- ZICXR/A-Stock-Skills★ 26same name
- impactbrussels/FounderOS★ 2same name
- jordnlvr/MendixToolkit★ 2same name
- AndyMelnykov/pm-loops★ 1same name
- CorvusWing/CorvusWing★ 1same name
- impactbrussels/AINativeOS★ 1same name
- kevinph4n/skills★ 1same name
2 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agents-mdSkill
- app-iconSkill
- buildSkill
- cloneSkill
- debugSkill
- design-systemSkill
- docker-optimizeSkill
- improve-loopSkill
- mac-appSkill
- mac-designSkill
- product-briefSkill
- quality-barSkill
- refactorSkill
- researchSkill
- reviewSkill
- stop-overthinkingSkill
- ui-directorSkill
- user-storiesSkill
- ux-designSkill
The file
Files
Hyper Taste
Find where the work is, call the Skill tool with the skill for that step, and tell the user which skill comes after it. One owner per job: each skill points to the others instead of repeating them.
idea -> research -> clone (optional) -> product-brief -> user-stories -> quality-bar
-> design (ui-director / mac-design + design-system + ux-design + app-icon)
-> improve-loop (build each story, review each milestone) -> repeatPlan
| The user has | Skill |
| A vague idea, or asks "what should I build" | research, then product-brief |
| An app they want to replace or learn from | clone |
| An idea or a rough spec, no brief | product-brief |
| A brief, no backlog | user-stories |
| No written quality bar, or agents will run unattended | quality-bar |
Design
| The user wants | Skill |
| A landing page, web app, dashboard or phone app that doesn't look generated | ui-director |
| A Mac app that looks and behaves native (SwiftUI, Electron, Tauri) | mac-design, plus ui-director for the content |
| Tokens, components, a brand or accent color, the look of an app they name | design-system |
| Names, flow, modals, states, words, accessibility for one feature | ux-design |
| A Mac app icon | app-icon |
Build
| The user wants | Skill |
| Write code for a feature or story | build |
| Start, run, test or speed up a Mac app | mac-app |
| Fix a bug, a failing test or a broken build | debug |
| A Dockerfile, image, Compose stack or container build to write or speed up | docker-optimize |
| Review a diff or audit a codebase | review |
| Restructure, simplify or de-bloat existing code | review to find what to fix, then refactor |
| Work through the backlog on its own | improve-loop |
| A quick call when work goes in circles: is it ready, what's next | stop-overthinking |
Keep AGENTS.md / CLAUDE.md small and in sync | agents-md |
Done when
You named the step, called its skill, and told the user which skill comes after it.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

