agentleFS
Sign inStart free
rmarjirmarji/chiron-council/skills/coach/SKILL.md

coach

Skill1 starsChanged 23 days agoMITView on GitHub

Run a Chiron coaching session that frames the real decision, brings seats in as evidence, and drives the user to one committed call with a next action. Use when the user says "coach me", "walk me through this", "help me decide and keep me honest", or wants a working session rather than a one-shot answer.

27 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use research, review and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • NVIDIASkill

    research

    Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

    Also in 4 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 4 projects that use this

  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 3 projects that use this

The file

Create a free account to mount
Files
SKILL.md

Coach a decision

ChatGPT and Codex have no /chiron slash commands. This skill is that coach flow.

The plugin root is the directory that contains skills/ and scripts/. Follow commands/coach.md there, exactly. Wherever that file says ${CLAUDE_PLUGIN_ROOT}, use the plugin root. Run each python3 invocation as its own command. Do not wrap it in a shell substitution or chain it with ;.

Seat text lives in skills/<id>/SKILL.md and that seat's references/. Read those files. Do not copy a seat into this skill, and do not invent a seat that is not installed. The seats are evidence. The coach still owns the session and closes on one committed call.

User data stays in ~/.chiron (CHIRON_HOME overrides that directory). Logs, benches, and seats Chiron creates go there, through python3 <plugin-root>/scripts/memory.py and python3 <plugin-root>/scripts/benches.py. Never write under ~/.claude. A path under ~/.claude is legacy and read-only. Pass --home .chiron only when the host cannot write the home directory (Cowork).

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