start-here
Skill1 starsChanged 5 months agoApache-2.0View on GitHub
Use when a founder is unsure where to begin or what to do next on an AI build - when they say "where do I start", "I want to build with AI", "is my idea AI-native or a wrapper", "what's the next step", "should I add a billing page now", "I have an idea but no plan", "I'm overwhelmed", or are about to pour months into the exciting work instead of the riskiest. Triggers on any founder lost on the build arc or asking which skill to run. Produces the Remove-the-AI verdict, their stage, and exactly one next skill to run.
11 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
- AndyMelnykov/pm-loopstheir own version, first seen Oct 20, 2026
- Abilityai/corneliustheir own version, first seen Oct 8, 2026
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- AIDevGTM/gtm-cofounder★ 334same 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
- kevinph4n/skills★ 1same name
- advisorppc-org/advisorseo-claude-plugin★ 0same name
1 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 repository27 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/ai-native-os.mdcCursor rule
- agentic-build-loopSkill
- ai-assisted-salesSkill
- apply-ai-native-modelsSkill
- architect-before-codeSkill
- capture-learningSkill
- cognitive-architecture-reviewSkill
- compliance-readinessSkill
- customer-discovery-that-doesnt-lieSkill
- design-a-loopSkill
- design-the-mvaSkill
- eval-and-safety-harnessSkill
- frame-the-hypothesisSkill
- gateway-agent-opsSkill
- geo-contentSkill
- hypothesis-miningSkill
- map-the-terrainSkill
- measure-ai-native-pmfSkill
- moat-strategySkill
- pay-down-agentic-debtSkill
- red-team-the-agentSkill
- secure-the-connectorsSkill
- self-healing-fallbacksSkill
- share-of-model-auditSkill
- write-the-claude-mdSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 24
Ask: *take the AI out of your product, does it still work?* If yes, you have an AI feature, not an AI-native company.
- Distinctive: line 30
Place the founder on the build arc by what they can't yet answer:
- Distinctive: line 43
When two stages fit, send them upstream.
- Distinctive: line 54
Don't skip the Remove-the-AI test to be encouraging: a wrapper diagnosed early saves months.
“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Start Here
Founders rarely fail for lack of effort; they fail by pouring months into the wrong thing for the stage they're at. This skill's only job is to tell you where you are and the single next thing to do, then get out of the way. It also runs the one test that decides whether you're building a company or a feature.
The method
Diagnose the stage, run the Remove-the-AI test, route to one skill. Full build-arc map, the test in
full, the symptom-to-skill table, a worked diagnosis, and anti-patterns:
references/stage-diagnosis.md.
Step 1: Run the Remove-the-AI test
Ask: take the AI out of your product, does it still work? If yes, you have an AI feature, not an AI-native company. Before anything else, find the closed loop that would make it break without the intelligence. If there isn't one, that is the work.
Step 2: Locate the stage
Place the founder on the build arc by what they can't yet answer:
| If they can't answer… | They're at | Run next |
| "What's the sharp, falsifiable bet?" | Frame | frame-the-hypothesis |
| "Who's the market, and where's the regulatory/competitive wedge?" | Frame | map-the-terrain |
| "What's the system, before any code?" | Architect | architect-before-code |
| "How do I build it with agents without it collapsing?" | Build | agentic-build-loop |
| "How is this safe enough to act on a human?" | Trust | eval-and-safety-harness |
| "What's the smallest agent that proves the loop?" | Ship | design-the-mva |
| "Is it actually working?" | Grow | measure-ai-native-pmf |
Step 3: Route to the earliest unvalidated assumption
When two stages fit, send them upstream. The highest-value work is almost always the riskiest belief they haven't tested yet, not the most exciting one.
Output
- The result of the Remove-the-AI test, stated plainly (native or wrapper, and what's missing).
- The founder's current stage and the one skill to run next, with a one-line reason.
Constraints
- Route to exactly one next skill. A list of five is the same as no answer.
- Don't skip the Remove-the-AI test to be encouraging: a wrapper diagnosed early saves months.
- Stay theme-agnostic; the founder supplies the domain.
Dictionary
the Remove-the-AI test · AI-native vs wrapper · data flywheel
Copy-paste version
For non-coders: paste into any chatbot (Claude.ai, ChatGPT, Gemini).
Act as my AI-native build coach. My idea: [ONE_LINER]. Who it's for: [ICP]. Domain: [DOMAIN].
1. Run the "Remove-the-AI test": if I take the AI out, does my product still work? If yes, tell me
I have a feature not an AI-native company, and help me find the closed loop that would make it
break without the intelligence.
2. Diagnose my stage: Frame, Architect, Build, Trust, Ship, Grow, or Defend - based on the riskiest
thing I can't yet answer.
3. Tell me the ONE next thing to do, and why it's the highest-value work right now. Just one.
Don't flatter me; route me to the earliest unvalidated assumption.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.