CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

commit-craft

Turn a mix of changes into clean, reviewable commits with good messages, blocking staged secrets and .env files. Use whenever the user says commit this, wants to split work into commits, write a commit message, or is about to push.

SKILL.md
Quality
Evals
Security

Commit Craft

Portability: 3 stdlib Python scripts that call git read-only. No network. The scripts never stage, commit or push. You do, one group at a time, after the gate passes.

Agents leave large mixed diffs: a feature, a reformat, a dependency bump and a stray .env, all in one tree. Committed as one blob, that diff cannot be reviewed, reverted or bisected. This skill turns it into a series where each commit is one logical change, builds on its own, holds no secrets and says why.

Workflow

# 1 - Plan: which commits, in which order, staged how?
python scripts/commit_planner.py                 # working tree vs HEAD, untracked included
# 2 - For each group: stage exactly its files, then gate what is staged
git add -- <files of group N>                     # or git add -p for MIXED_FORMATTING files
python scripts/secret_gate.py                     # blocks before the commit exists
# 3 - Write the message, lint it, commit
python scripts/message_linter.py -m "<message>" --staged && git commit -m "<message>"
# 4 - Before push: the whole series, and proof every commit builds
python scripts/message_linter.py --range @{upstream}..HEAD
git rebase -x "<test command>" @{upstream}

Step 1 groups files: manifest with lockfile, pure moves, whitespace-only files, each module's changes with their tests, then docs and CI. It holds back .env, keys and tfstate (exit 4), flags files that mix formatting with real hunks, and flags a move whose callers' import edits sit in another group, since that commit would not build. It never picks feat vs fix: decide from what the change does.

Step 2 scans only the added lines of what is staged: provider-shaped tokens, high-entropy values assigned to key/secret/token/password, sensitive files and conflict markers. Output is redacted. A false positive is waived in .commit-craft-allow by fingerprint or path, with a reason.

Step 3 blocks vague subjects ("fix", "update"), subjects over 72 characters, no blank line after the subject, and a change of 40+ lines or 4+ files with no body. It enforces Conventional Commits only if the repo already uses them.

Step 4 also blocks fixup!/squash!/WIP commits and warns on duplicates and revert pairs. Install assets/hooks/ to run steps 2 to 4 on every commit and push.

Hard rules

  • Never git add -A or git add . on a mixed tree. Stage each group by name or by hunk.
  • A blocked gate means no commit. Remove the value and load it at runtime. Never --no-verify, never waive a real secret.
  • A pushed secret is rotated first. Deleting it in a new commit leaves it in history (references/secret_response.md).
  • Each commit builds. Tests ride with their change; moves carry their callers.
  • The body says why. The diff already says what.
  • Rewrite only unpushed history. Rebasing or amending shared commits is the user's call.

Scripts

ScriptRoleExit codes
scripts/commit_planner.pyGroups, order, staging commands, MOVE/MIXED/SIZE flags0 one commit · 2 split · 3 bad input · 4 secrets file held back
scripts/secret_gate.pyStaged or range scan for credentials, sensitive files, conflict markers0 · 2 warnings · 3 · 4 blocked
scripts/message_linter.pyOne message (-m, --message-file) or a series (--range)0 · 2 warnings · 3 · 4 blocked

All support --help, --sample and --output json.

References and assets

  • references/commit_series_design.md: split, order and verify, with sources (7)
  • references/message_discipline.md: subject, why-body, breaking changes, trailers (7)
  • references/secret_response.md: what the gate catches, its limits, and the leak response order (7)
  • assets/hooks/: pre-commit, commit-msg, pre-push
  • assets/commit-craft-allow.example: waiver format
  • assets/series_checklist.md: pre-push sign-off
Repository

alirezarezvani/claude-skills

Path

engineering/commit-craft/skills/commit-craft/SKILL.md

Last updated
First committed

Also appears in

alirezarezvani/claude-skills
In sync

since Oct 31, 2026

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.