agentleFS
JewgahJewgah/claude-code-skills/skills/commit/SKILL.md

commit

Skill2 starsChanged 3 months agoMITView on GitHub

Commit staged changes, update CLAUDE.md and memory if relevant

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

Show its rules and text

We split this skill into the rules it gives an agent

14 rules. 0 are common, 8 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 168 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run git status (never use -uall), git diff --cached, and git log --oneline -5 in parallel.

    line 10
  2. Very specific:

    Use conventional commits: feat:, fix:, refactor:, docs:, chore:, etc.

    line 12
  3. Very specific:

    NEVER include Co-Authored-By lines or mention Claude.

    line 14
  4. Very specific:

    Commit using a HEREDOC for the message.

    line 16
  5. Distinctive:

    Run git status to confirm success.

    line 17
  6. Very specific:

    After committing, update ROADMAP.md at the project root.

    line 21
  7. Very specific:

    Read the current ROADMAP.md (create it if it doesn't exist).

    line 24
  8. Distinctive:

    Keep entries concise and useful.

    line 39
  9. Distinctive:

    If the commit is trivial (typo fix, formatting), still add an entry but keep it minimal.

    line 40
  10. Distinctive:

    After committing, read the project's CLAUDE.md (if one exists) and review the committed diff against it.

    line 44
  11. Distinctive:

    Read the current CLAUDE.md.

    line 63
  12. Distinctive:

    If the file is growing long, consider condensing older info rather than appending.

    line 66
  13. Distinctive:

    After committing, check if any of these should be saved to memory:

    line 71
  14. Distinctive:

    If saving, write to the memory directory and update MEMORY.md index.

    line 84

“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 & Self-Maintain CLAUDE.md + Memory

Step 1: Commit

  1. Run git status (never use -uall), git diff --cached, and git log --oneline -5 in parallel.
  2. Analyze all staged changes. Draft a concise commit message:
    • Use conventional commits: feat:, fix:, refactor:, docs:, chore:, etc.
    • Focus on why, not what.
    • NEVER include Co-Authored-By lines or mention Claude.
  3. Stage relevant untracked files if needed (prefer specific files over git add .).
  4. Commit using a HEREDOC for the message. Do NOT use --no-verify.
  5. Run git status to confirm success.

Step 2: Update ROADMAP.md

After committing, update ROADMAP.md at the project root.

  1. Gitignore rule: ROADMAP.md should normally be tracked by git and committed alongside the changes it describes. Only leave it gitignored if that specific repo already does so.
  2. Read the current ROADMAP.md (create it if it doesn't exist).
  3. Prepend a new entry at the top (most recent first) with this format:
## [commit hash short] - [commit message] ([date YYYY-MM-DD])

**Problem:** [What was wrong or missing - 1-2 sentences]

**Solution:** [What was done to fix/implement it - 1-2 sentences]

**Files changed:** [list of key files touched, not exhaustive]

---
  1. Keep entries concise and useful. Focus on the why and the how, not line-by-line diffs.
  2. If the commit is trivial (typo fix, formatting), still add an entry but keep it minimal.

Step 3: Evaluate CLAUDE.md Relevance

After committing, read the project's CLAUDE.md (if one exists) and review the committed diff against it.

Update CLAUDE.md ONLY if the commit changed something the file already documents or should document:

  • A new backend function/endpoint/service → add to whatever list tracks those
  • A new data model/entity/schema → add to whatever list tracks those
  • A changed core flow (auth, payments, data pipeline, etc.) → update the relevant section
  • A new critical constraint or gotcha discovered → add to constraints/warnings section
  • An architecture shift (new library, new pattern, new convention) → update architecture docs
  • A removed or renamed component that CLAUDE.md references → fix the stale reference

Do NOT update CLAUDE.md for:

  • Bug fixes that don't change architecture
  • UI tweaks, styling, or cosmetic changes
  • Routine feature work that follows existing patterns
  • Anything speculative - only document confirmed facts

Step 4: If Updating CLAUDE.md

  1. Read the current CLAUDE.md.
  2. Make minimal, surgical edits - add a bullet, update a list, fix a stale reference.
  3. Respect the file's existing structure and style. Don't reorganize it.
  4. If the file is growing long, consider condensing older info rather than appending.
  5. Before committing CLAUDE.md, check if it's in .gitignore. If it is, skip the commit - just edit it locally. If it's NOT in .gitignore, create a separate commit: docs: update CLAUDE.md - [brief reason].

Step 5: Evaluate Memory Relevance

After committing, check if any of these should be saved to memory:

  • User feedback received during this session (corrections, preferences, "don't do X") → save as feedback memory
  • Project context learned (who's doing what, why, deadlines, business decisions) → save as project memory
  • Investigation/debugging findings discovered during this session (error patterns, log analysis results, root cause analysis, affected users, ongoing unresolved issues) → save as project memory with current status and key data points. When updating an existing project memory, preserve history: mark what was fixed vs what remains open.
  • User profile details learned (role, expertise, preferences) → save as user memory
  • External references discovered (where to find info, dashboards, tools) → save as reference memory

Do NOT save to memory:

  • Code patterns or architecture (that's what CLAUDE.md is for)
  • Anything already in CLAUDE.md or derivable from code/git
  • Ephemeral task details only relevant to current conversation

If saving, write to the memory directory and update MEMORY.md index.

Step 6: Report

Tell the user:

  • What was committed (short summary)
  • Whether ROADMAP.md was updated
  • Whether CLAUDE.md was updated and why (or "no update needed - [reason]")
  • Whether memory was updated and why (or "no memory update needed")

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.