agentleFS
mrlemoosmrlemoos/galicia/.claude/skills/commit/SKILL.md

commit

Skill1 starsChanged 6 days agoMITView on GitHub

Splits agreed work into small commits, each proven by a unit, behavioural, or e2e test. Use when the user asks for commits, commit slices, a tested history, or /commit.

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, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 167 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the agreed spec, ticket, or stated task, the current diff, and the nearest tests.

    line 12
  2. Distinctive:

    No behaviour change (move, rename, format): no new test.

    line 17
  3. Distinctive:

    Run the new test alone, then the relevant suite and the project's lint and type check.

    line 21

“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

Short evidence, no emojis. No agreed change named: reply "Please mention the work that you want me to help you split into commits." and stop.

Owns git history for one agreed change. Ticket files belong in breakdown. Test writing belongs in unit-test, behavioural-test, or e2e-test: read that skill and follow it. Do not restate its rules.

  1. Read the agreed spec, ticket, or stated task, the current diff, and the nearest tests. Missing agreement: ask. Never invent scope.
  2. Draft the commit list before editing. Each commit:
    • One behaviour, or one prefactor that makes the next behaviour commit safe.
    • Stays green: the build and the tests that cover it pass.
    • A behaviour change includes the test that locks it, in the same commit. Lowest sphere that proves it: unit-test for one function, class, or branch; behavioural-test for one user-facing scope; e2e-test for one critical journey. Name any higher sphere skipped and why.
    • No behaviour change (move, rename, format): no new test. Say why. Existing tests still pass.
    • Revertable alone. Two behaviours means two commits. One behaviour stays one commit.
  3. Show numbered titles, paths, sphere, and the proof command. Ask approval. Do not stage or commit before approval.
  4. Land one approved commit at a time. Write its test by following the named skill, then the smallest production change that makes that test pass. Production edits only for the behaviour this commit claims. Do not weaken a test. Failure outside this slice: stop and ask.
  5. Run the new test alone, then the relevant suite and the project's lint and type check. Red: fix this commit only. Do not start the next one.
  6. Stage only this commit's files. Read status, diff, and recent message style. Leave unrelated and untracked work unstaged. Never stage secrets or credentials. Subject: short imperative. Body: behaviour and the test that proves it. No amend, rebase, push, empty commit, or skipped hooks unless the user asks.
  7. Repeat 4-6. Stop on conflict, hook failure, or a slice that cannot go green. Report each hash, test command, and result, plus anything left uncommitted. Never claim green or committed without command output.

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.