agentleFS
jcarlosrodiciojcarlosrodicio/norma/skills/commit/SKILL.md

commit

Skill1 starsChanged 2 months agoMITView on GitHub

Use when the user asks to commit, to create a pull request, or when a change is verified and ready to land - produces atomic commits that stage only the files belonging to the change, with a message and PR body written from the actual diff.

  • Reads credentials

188 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

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

  • 0

    Common

    Most of the 168 edited versions we read keep these.

  • 3

    Distinctive

    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
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Never commit unrelated work: Run git status first. If the tree contains modifications outside the change, list them to the user and stage …

    line 14
  2. Very specific:

    Never commit secrets or local config: Check the diff for keys, tokens, .env values and absolute paths from this machine before staging.

    line 17
  3. Distinctive:

    Write the body from the diff you actually staged.

    line 42
  4. Distinctive:

    When a PR is requested, the body carries:

    line 47

“Common” is measured: kept by at least 6 in 10 of the 168 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

Rules

  • Atomic. One commit per logical change. Never git add -A or git add .; stage the specific paths this change touched.
  • Never commit unrelated work. Run git status first. If the tree contains modifications outside the change, list them to the user and stage only what belongs. Do not stash or revert someone else's work-in-progress.
  • Never commit secrets or local config. Check the diff for keys, tokens, .env values and absolute paths from this machine before staging.
  • English, imperative mood, as required by the project language standard.
  • Do not commit unless asked. The harness loop stops before delivery so the human reviews first.

Branch

Work on a feature branch, never directly on the default branch. These projects use phase-based naming - follow whatever the repository already does (for example phase-NN-<slug>), and if no convention is visible, ask instead of inventing one.

Message format

<type>: <what changed, imperative, under 72 chars>

<why it changed - the problem, not a restatement of the diff>

<what to know when reading it later: decisions taken, trade-offs,
what was deliberately left out>

Types: feat, fix, refactor, test, docs, chore, perf.

Write the body from the diff you actually staged. Do not describe files you did not change, and do not claim tests pass unless you ran them in this session.

Pull request

When a PR is requested, the body carries:

  • What - the behaviour change, in product terms.
  • Why - the problem or the roadmap phase it belongs to.
  • How - the approach and the decisions worth questioning.
  • Verification - the commands actually run and their results, plus what was not covered.
  • Risk - what could break, and the rollback.

Link the change artifacts (OpenSpec change folder, spec or ADR) rather than duplicating their content.

Before finishing

Report the commit hash and the exact paths staged, so the human can check nothing extra travelled with it.

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.