agentleFS
Sign inStart free
mustafahasanainmustafahasanain/frappe-workflow/skills/git-finalization/SKILL.md

git-finalization

Skill0 starsChanged 3 months agoMITView on GitHub

Post-approval finalization and commit preparation - finalization gate, documentation timing, Conventional Commit message generation, exact staging commands, and commit verification.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    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. Very specific:

    After user-requested execution: verified commit, hash/subject recorded, stage committed.

    line 33
  2. Very specific:

    Commit executed and verified → record hash/subject, state transition committed, hand to the deployment question.

    line 49

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Git Finalization Skill

Turns an approved implementation into a verified task commit. Prepares everything; executes the commit only when the user explicitly asks.

When to Use

  • Right after a valid APPROVED (finalization: documentation updates + gate) — invoked from the codex-review flow.
  • The commit action (stage ready_for_commit).
  • Resuming into ready_for_commit.

Inputs

  • Approved state (fingerprint recorded), docs/ai-context/TASK_PLAN.md, the actual diff, bin/frappe-workflow git inspect / changed-files.

Outputs

  • Finalized docs: docs/ai-context/FEATURE_CHANGELOG.md updated (feature-changelog skill), docs/ai-context/PROJECT_CONTEXT.md when architecture changed (project-context skill), docs/ai-context/TASK_PLAN.md status codex_approved + review record.
  • A prepared commit: Conventional Commit subject (+ optional body), exact git add -- <path> commands, excluded-files list.
  • After user-requested execution: verified commit, hash/subject recorded, stage committed.

Procedure

Gate: references/finalization-gate.md. Message: references/conventional-commits.md. Staging: references/task-file-staging.md.

Preconditions

  • bin/frappe-workflow validate finalization-gate passes (approval valid, fingerprint matches, secret scan clean).

Stopping Conditions

  • Commit executed and verified → record hash/subject, state transition committed, hand to the deployment question. Done.
  • User has not asked to execute → stop after presenting the prepared commit; the workflow waits.
  • Unrelated files already staged → stop and report (never commit around them).

Prohibited

  • git add . / -A in any form; staging .claude/ machine-local state (deployment.local.json, task-workflow.lock) or unrelated files.
  • Executing the commit without an explicit user request this session.
  • --amend (unless the user explicitly asks and nothing was pushed), force-push, AI attribution (Co-Authored-By, Claude, Codex, AI-generated) in the message.
  • Updating documentation outside this finalization window.

Shared Rules

git-safety-rules.md, security-rules.md, shared-workflow-rules.md.

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.

Check your setup, free