agentleFS
schen22schen22/claude-config/skills/commit/SKILL.md

commit

Skill0 starsChanged 2 days agoMITView on GitHub

Default commit rules for any of Sarah's projects — branches, one-thing-per-commit, message shape. Use whenever about to commit. If the project has its own commit-workflow skill, follow that too; it wins on conflict.

187 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use validate-plan, act-on-feedback and 10 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.
  • shawn-dumasSkill

    validate-plan

    Validate an orchestration plan after pre-flight certification. Runs adversarial review, deep review (verify prompt data against codebase), and PoC gate for risky approaches. Auto-invoked by orchestrate-* skills at Step 8.

    Also in 5 projects that use this

  • MicrosoftSkill

    act-on-feedback

    Act on user feedback attached to the current session. Use when the user submits feedback on the session's changes via the Submit Feedback button.

    Also in 3 projects that use this

  • decocmsSkill

    add-mcp-tools

    Guide for adding new MCP tools with consistent patterns for schemas, tool definitions, registry updates, and Better Auth integration

    Also in 3 projects that use this

  • MicrosoftSkill

    generate-run-commands

    Generate or modify run commands for the current session. Use when the user wants to set up or update run commands that appear in the session's Run button.

    Also in 3 projects that use this

  • mitsuhikoSkill

    oebb-scotty

    Austrian rail travel planner (ÖBB Scotty). Use when planning train journeys in Austria, checking departures/arrivals at stations, or looking for service disruptions. Covers ÖBB trains, S-Bahn, regional trains, and connections to neighboring countries.

    Also in 3 projects that use this

  • mitsuhikoSkill

    pi-share

    Load and parse session transcripts from shittycodingagent.ai/buildwithpi.ai/buildwithpi.com/pi.dev (pi-share) URLs. Fetches gists, decodes embedded session data, and extracts conversation history.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 167 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never push; pushing is Sarah's call.

    line 14
  2. Very specific:

    After the full gate passes on the working branch, clean up the lane in the same step: git worktree remove <path> and git branch -d …

    line 18
  3. Very specific:

    Before staging: git status and ListAgents.

    line 22

“Common” is measured: kept by at least 6 in 10 of the 167 edited versions of this file we could read. “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

Commit

Branches

  • Orchestrator (the session Sarah talks to) commits on the project's working branch. Never push; pushing is Sarah's call.
  • Helpers commit only on lane/<name> in their own worktree. Never touch the working branch, never merge, never push.
  • Integrate a lane: git rebase <main> lane/<name> then git merge --ff-only lane/<name>.
  • After the full gate passes on the working branch, clean up the lane in the same step: git worktree remove <path> and git branch -d lane/<name> (plus any worktree-agent-* branch). A leftover lane is easy to mistake for unfinished work.
  • git log --oneline -5 before the first commit — never assume repo state.
  • Before staging: git status and ListAgents. If a peer session is busy in the same working tree (files change under you), stop and ask Sarah: wait for it to commit, or move it to its own worktree. Never commit around its half-done edits.

One commit does one thing

  • One commit per PLAN.md item (or one clearly named part of one).
  • A test ships in the same commit as the change it proves.
  • Shared docs (PLAN.md, CLAUDE.md, README.md, docs/) are orchestrator-only. Helpers list doc-worthy facts in their report instead.
  • Docs go in their own commit, after the code they describe.
  • Each commit passes the full gate on its own. After committing a partial working tree, run ~/.claude/skills/commit/gate-head.sh (gate on a clean checkout of HEAD). A check tightened in one commit can fail data that only lands in a later one — order commits so each passes.
  • Plan the commit stack before the first commit. > ~6 commits → split across helpers or sessions (see delegate).

Message shape

Match the repo's existing style. Default: imperative subject, sentence case, ≤ 60 chars, no "and" (two things → two commits).

<Imperative subject>

<Why: PLAN item / review IDs and any non-obvious reasoning. Don't restate the diff.>

Verified: <full gate result>; <build/inspection done>. New test <name> fails before,
passes after.
Review: <SHIP|BLOCKED> — <one clause per finding and how it was handled>.

<Co-Authored-By trailer from the session's attribution instructions>

Checklist

[ ] right branch; nothing pushed; no peer session busy in this tree
[ ] partial tree committed → gate-head.sh passed
[ ] one item per commit; its test in the same commit
[ ] helpers: no shared-doc edits
[ ] subject imperative, <= 60 chars, no "and"
[ ] Verified + Review lines; full gate passed

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.