agentleFS
Sign inStart free
nurmdrafinurmdrafi/pi-native/skills/pidoc/SKILL.md

pidoc

Skill4 starsChanged 5 days agoMITView on GitHub

Checks pi harness setup health — node pin, cargo/pidx build, helper CLIs, rg PCRE2 pin, piread smoke, shell rc PATH pin, permission-gate, settings, hooks, writable dirs, session-audit fallback — and fixes what is safe. Use when the user says doctor, check my setup, diagnose the harness, is my setup ok, after cloning the harness on a new machine, or when pidx/session-audit misbehaves. NOT for skill authoring (skill-manager) or session cost audits (session-audit).

  • Pipes a download into a shell
  • Installs packages

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:

    After --fix, re-run the script.

    line 30

≈ “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

Pidoctor

One deterministic script, zero network, macOS + Linux. Also invoked automatically on every git pull by scripts/after-pull.sh (husky post-merge/post-rewrite) with --fix.

  1. Run node ~/.pi/agent/skills/pidoc/scripts/pidoc.mjs.
  2. Report the table as-is (path-style citation, no restating rows).
  3. FAIL rows first, then WARN. For each FAIL/WARN with a --fix route, run node ~/.pi/agent/skills/pidoc/scripts/pidoc.mjs --fix — it only applies safe fixes (pidx rebuild via cargo, all local).
  4. Installs (rustup, gh, rg, fd) are never run by the script. Tell the user the exact command and wait for approval:
    • rustup: curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --profile minimal
    • others: the system package manager (brew install gh ripgrep fd / apt install ripgrep fd-find).
  5. After --fix, re-run the script; only a clean table ends the task.

Exit codes: 0 = pass (warnings allowed), 1 = any FAIL. --json emits rows machine-readable.

What each check means and why it matters lives in references/checks.md — read it only when a row needs interpretation beyond its detail text.

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