claude-skills
CLAUDE.md1 starsChanged 5 months agoMITView on GitHub
This is the startup-os repository. This file contains the startup profile and build tracking for the complete company operating system.
In this repository3 other files it gives its agents.
- startup-osSkill
- commit-writerSkill
- startup-osSkill
The file
We split this CLAUDE.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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 72
Run the complete build:
≈ “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
Startup OS — Project Instructions
This is the startup-os repository. This file contains the startup profile and build tracking for the complete company operating system.
Startup Profile
<!-- Auto-populated by /startup-os build -->- Company Name: [PENDING]
- One-line: [PENDING]
- Industry: [PENDING]
- Business Model: [PENDING]
- Target Customer: [PENDING]
- Problem: [PENDING]
- Stage: idea
- Location: [PENDING]
- Founders: [PENDING]
- Revenue: $0
- Fundraising Goal: [PENDING]
- Launch Target: [PENDING]
Build Log
<!-- Auto-updated as each department completes -->| Department | Agent | MD | CSV | HTML | SVG | Status | |
| strategy | - | - | - | - | - | - | ⬜ pending |
| brand | - | - | - | - | - | - | ⬜ pending |
| product | - | - | - | - | - | - | ⬜ pending |
| finance | model | - | - | - | - | - | ⬜ pending |
| finance | fpa | - | - | - | - | - | ⬜ pending |
| finance | controller | - | - | - | - | - | ⬜ pending |
| marketing | - | - | - | - | - | - | ⬜ pending |
| sales | - | - | - | - | - | - | ⬜ pending |
| legal | - | - | - | - | - | - | ⬜ pending |
| people | - | - | - | - | - | - | ⬜ pending |
| operations | - | - | - | - | - | - | ⬜ pending |
| metrics | - | - | - | - | - | - | ⬜ pending |
| security | - | - | - | - | - | - | ⬜ pending |
| engineering | - | - | - | - | - | - | ⬜ pending |
| design | ui-designer | - | - | - | - | - | ⬜ pending |
| design | ux-designer | - | - | - | - | - | ⬜ pending |
| design | canvas-designer | - | - | - | - | - | ⬜ pending |
| design | brand-designer | - | - | - | - | - | ⬜ pending |
| design | design-systems-engineer | - | - | - | - | - | ⬜ pending |
| design | motion-designer | - | - | - | - | - | ⬜ pending |
| design | ux-researcher | - | - | - | - | - | ⬜ pending |
| executive | ceo | - | - | - | - | - | ⬜ pending |
| executive | cto | - | - | - | - | - | ⬜ pending |
| executive | cfo | - | - | - | - | - | ⬜ pending |
| executive | cmo | - | - | - | - | - | ⬜ pending |
| executive | cpo | - | - | - | - | - | ⬜ pending |
| executive | coo | - | - | - | - | - | ⬜ pending |
| growth | growth-hacker | - | - | - | - | - | ⬜ pending |
| growth | demand-gen | - | - | - | - | - | ⬜ pending |
| growth | seo-specialist | - | - | - | - | - | ⬜ pending |
| growth | content-strategist | - | - | - | - | - | ⬜ pending |
| data | data-analyst | - | - | - | - | - | ⬜ pending |
| data | ml-engineer | - | - | - | - | - | ⬜ pending |
| data | bi-analyst | - | - | - | - | - | ⬜ pending |
| customer | customer-success | - | - | - | - | - | ⬜ pending |
| customer | customer-support | - | - | - | - | - | ⬜ pending |
| customer | cx-designer | - | - | - | - | - | ⬜ pending |
Usage
Run the complete build:
/startup-os build "Your startup idea here"Check status:
/startup-os statusRe-run a department or agent:
/startup-os run finance
/startup-os run product roadmapReset everything:
/startup-os resetNotes
- The build runs 12 departments sequentially with dependency chains
- Each department writes to its
output/folder - Security and engineering write to
_reports/ - The Build Log above tracks completion status in real-time
- Cross-department consistency is validated automatically
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.