startup-skills
CLAUDE.md1 starsChanged 5 months agoMITView on GitHub
A public Agent Skills collection for AI-native startup founders — the hub founder-playbook plus 12 per-function skills — packaged for skills.sh. No build, no app; just portable skill folders installed via npx skills add samuelcastro/startup-skills/<skill>. AGENTS.md is the full guide — read it. It's provider-agnostic and applies here unchanged. The rules below are the ones you can't infer from the files; treat them as IMPORTANT.
In this repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- business-modelSkill
- customer-successSkill
- finance-accountingSkill
- founder-playbookSkill
- fundraisingSkill
- go-to-marketSkill
- growth-analyticsSkill
- idea-validationSkill
- legal-complianceSkill
- marketing-brandSkill
- operationsSkill
- productSkill
- salesSkill
The file
We split this CLAUDE.md into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Public repo — never leak private context: No private-repo names, internal knowledge bases, or machine-local paths (/Users/...).
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
CLAUDE.md — Startup Skills
A public Agent Skills collection for AI-native startup founders — the hub founder-playbook plus 12 per-function skills — packaged for skills.sh. No build, no app; just portable skill folders installed via npx skills add samuelcastro/startup-skills/<skill>.
AGENTS.md is the full guide — read it. It's provider-agnostic and applies here unchanged. The rules below are the ones you can't infer from the files; treat them as IMPORTANT.
IMPORTANT
- Adapted, not original — keep attribution. The 12 per-function skills credit Linas Beliūnas / The One-Person Unicorn;
founder-playbookcredits Anthropic. Never reword anything to claim original authorship; never drop a credit line. - Public repo — never leak private context. No private-repo names, internal knowledge bases, or machine-local paths (
/Users/...). Every skill must stand alone and make sense to a stranger. descriptionis the trigger and has a hard ≤1024-char limit. Over it, loaders silently skip the skill. Keep descriptions specific, a little "pushy," and under ~1000 chars.
Conventions
- One folder per skill, each with
SKILL.mdwhosenameequals the folder. KeepSKILL.mdlean (<500 lines); push depth intoreferences/. - Install is per-skill via skills.sh — there is no
install.sh. - To improve a skill, use the autoresearch eval loop (binary evals, one file changed per round, keep-if-+10pts / revert). Details in AGENTS.md.
Before committing
- Public-safety:
grep -rn '/Users/' . --include='*.md'→ expect no matches. - Spec: every
namematches its folder; everydescription≤ 1024 chars (npx skills-ref validate ./<skill>).
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.

