commit
Skill1 starsChanged 6 months agoMITView on GitHub
Use when ready to commit — groups changes into atomic commits, proposes conventional commit messages, and requires explicit approval before each commit and before any push.
- Commits and pushes
188 other projects use a version of this.
Adopted by
Most recently taken up by
- daledesilva/obsidian_inktheir own version, first seen Nov 9, 2026
- thoughtbot/rails-consultanttheir own version, first seen Nov 8, 2026
- pedrohcgs/claude-code-my-workflowtheir own version, first seen Nov 8, 2026
- jisuzzzz/haechitheir own version, first seen Nov 8, 2026
- dirien/yet-another-agent-harnesstheir own version, first seen Nov 8, 2026
- denysdovhan/skillstheir own version, first seen Nov 8, 2026
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-dumasSkillvalidate-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
MicrosoftSkillact-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
decocmsSkilladd-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
MicrosoftSkillgenerate-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
mitsuhikoSkilloebb-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
mitsuhikoSkillpi-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
Other versions188 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 188
- microsoft/vscode★ 195ksame name
- TryGhost/Ghost★ 56ksame name
- ToolJet/ToolJet★ 41ksame name
- ShareX/ShareX★ 41ksame name
- openai/symphony★ 27ksame name
- ccusage/ccusage★ 19ksame name
- ryoppippi/ccusage★ 19ksame name
- windmill-labs/windmill★ 18ksame name
- EverMind-AI/EverMemOS★ 14ksame name
- EverMind-AI/EverOS★ 14ksame name
178 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- api-designSkill
- brainstormSkill
- code-reviewSkill
- evaluate-feedbackSkill
- go-apiSkill
- multi-agentSkill
- planSkill
- tddSkill
- ts-apiSkill
- workflowSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. 0 are common, 11 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 168 edited versions we read keep these.
11
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Ask-first, small atomic commit workflow.
- Distinctive: line 18
Run git diff --stat and git status.
- Distinctive: line 25
Never mix unrelated changes in the same commit
- Distinctive: line 38
After showing all proposed commits at once, start with the first and ask:
- Distinctive: line 44
Only run git commit after:
- Very specific: line 48
If user types n: skip this commit, move to next.
- Very specific: line 50
If user types edit message: show current message, let them type the new one, confirm before committing.
- Distinctive: line 66
Keep the description under 72 characters.
- Distinctive: line 70
After all commits, show the log:
- Very specific: line 82
Never run git push without explicit y.
- Distinctive: line 86
If there are changes unrelated to the current task (formatting cleanup, unrelated refactors), flag them separately:
- Distinctive: line 97
Never run git commit without user approval
- Distinctive: line 99
Never combine unrelated changes into one commit silently
- Very specific: line 100
Never use --no-verify to skip hooks
- Distinctive: line 101
Never amend commits that have already been confirmed — create a new one
“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.
Files
Commit
Ask-first, small atomic commit workflow. The user is always in control of what gets committed and when.
Recommended model: Haiku (simple git operations)
Rules
1. Show what changed
Run git diff --stat and git status. Show the summary to the user before doing anything else.
2. Group into smallest logical commits
Analyze the changes. Split into the smallest commits that are still logical and independent:
- One concern per commit
- A commit should do one thing: fix one bug, add one feature, or update one area
- Never mix unrelated changes in the same commit
3. Present each proposed commit
For each proposed commit, show:
Commit [N/M]:
Files: path/to/file.ts, path/to/other.ts
Message: feat(users): add email validation on registration
Why its own commit: standalone feature, no dependency on other changesAfter showing all proposed commits at once, start with the first and ask:
Commit 1/N ready. Commit this? [y / n / edit message]
4. Wait for explicit approval before each commit
Only run git commit after:
- User types
y, or - User provides an edited message
If user types n: skip this commit, move to next. Ask at the end if they want to revisit it.
If user types edit message: show current message, let them type the new one, confirm before committing.
5. Commit message format
type(scope?): descriptionTypes: feat, fix, refactor, test, chore, perf, docs
Examples:
feat(users): add email validation on registrationfix(auth): correct JWT expiry check to use <=refactor(shared): extract response envelope helpertest(users): add table-driven tests for createUser
Keep the description under 72 characters. Use imperative mood ("add", "fix", "extract" — not "added", "fixes", "extracting").
6. Never push without asking
After all commits, show the log:
Committed:
abc1234 feat(users): add email validation on registration
def5678 test(users): add tests for email validationThen ask:
Push to remote? [y / n]
Never run git push without explicit y.
7. Flag unrelated changes
If there are changes unrelated to the current task (formatting cleanup, unrelated refactors), flag them separately:
Unrelated changes detected:
path/to/file.ts(whitespace cleanup)Include in a chore commit? [y / n / separate commit]
What NOT to do
- Never run
git commitwithout user approval - Never run
git pushwithout user approval - Never combine unrelated changes into one commit silently
- Never use
--no-verifyto skip hooks - Never amend commits that have already been confirmed — create a new one
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
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.

