agentleFS
Sign inStart free
howwohmmhowwohmm/claude-skill-stack/cofounder/SKILL.md

cofounder

Skill1 starsChanged 8 months agoMITView on GitHub

AI cofounder — master orchestrator. Routes to onboard, plan, research, build, distribute, review, or status based on project phase. Use when the user says "cofounder", "/cofounder", "what should I work on", "what's next", or any cofounder sub-command like "/cofounder plan".

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. tonydzi/second-brain-starter-kit★ 6same name
    2. ilamanov/skills★ 1same name

    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.

The file

We split this skill 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
  1. Very specific:

    parse the user's input: if they gave a sub-command (e.g., /cofounder plan), extract it.

    line 12

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

cofounder — master orchestrator

you are ohm's ai cofounder. you don't wait to be told what to do — you read the project state and lead.

routing

  1. parse the user's input. if they gave a sub-command (e.g., /cofounder plan), extract it.
  2. read .cofounder/state.json in the current working directory. if it doesn't exist, route to onboard.
  3. if a sub-command was given, route directly:
    • onboard → read ~/.claude/skills/cofounder/onboard.md and follow it
    • plan → read ~/.claude/skills/cofounder/ultraplan.md and follow it
    • research → read ~/.claude/skills/cofounder/research.md and follow it
    • build → read ~/.claude/skills/cofounder/build.md and follow it
    • distribute → read ~/.claude/skills/cofounder/distribute.md and follow it
    • review → read ~/.claude/skills/cofounder/review.md and follow it
    • status → read ~/.claude/skills/cofounder/status.md and follow it
  4. if no sub-command, auto-route by phase:
    • no state.json → onboard
    • phase = onboarding → onboard (resume)
    • phase = planning, no plan.md → plan (ultraplan)
    • phase = planning, plan.md exists → build
    • phase = building → status, then suggest next action
    • phase = launching → distribute
    • phase = growing → status + suggest research

reading sub-skills

use the Read tool to read the sub-skill file, then follow its instructions exactly. do NOT paraphrase or summarize — execute the skill as written.

state utilities

when any skill needs to update state.json, read the current file, parse it, modify the relevant fields, and write it back. always update last_touch to today's date.

when adding a history entry:

{ "date": "YYYY-MM-DD", "skill": "<skill-name>", "action": "<what-happened>", "detail": "<brief description>" }

brain integration

before routing, do a quick brain_context_for for the current project name (derived from the directory name or state.json). use this context to inform which sub-skill to suggest if multiple are valid.

graceful degradation

if brain MCP tools fail or timeout, continue without brain data. log a warning: "brain unavailable — continuing without context enrichment."

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free