commit — community commit, LLM-ENGINEERS-HANDBOOK, community, ide skills

v1.0.0

このスキルについて

コードレビューエージェントが正確なGitコミット管理とバージョン管理を必要とする場合に最適 Stage changes, run pre-commit hooks, and create a well-formatted git commit

captainsparrow10 captainsparrow10
[0]
[0]
Updated: 2/27/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 9/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution Quality floor passed for review
Review Score
9/11
Quality Score
51
Canonical Locale
en
Detected Body Locale
en

コードレビューエージェントが正確なGitコミット管理とバージョン管理を必要とする場合に最適 Stage changes, run pre-commit hooks, and create a well-formatted git commit

このスキルを使用する理由

エージェントが選択的なファイルステージングと有意義なコミットメッセージを使用して、クリーンで文書化されたGitコミットを作成できるようにし、`git status`、`git diff`、`git add`などのGitプロトコルを活用する

おすすめ

コードレビューエージェントが正確なGitコミット管理とバージョン管理を必要とする場合に最適

実現可能なユースケース for commit

コミットメッセージの自動作成
`git diff --stat`を使用して変更の要約を生成する
選択的なファイルステージングを使用してコミットの問題をデバッグする

! セキュリティと制限

  • Gitのインストールと設定が必要
  • `.env`などの、`HUGGINGFACE_ACCESS_TOKEN`などの機密情報を含むファイルはコミットしない

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

After The Review

Decide The Next Action Before You Keep Reading Repository Material

Killer-Skills should not stop at opening repository instructions. It should help you decide whether to install this skill, when to cross-check against trusted collections, and when to move into workflow rollout.

Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is commit?

コードレビューエージェントが正確なGitコミット管理とバージョン管理を必要とする場合に最適 Stage changes, run pre-commit hooks, and create a well-formatted git commit

How do I install commit?

Run the command: npx killer-skills add captainsparrow10/LLM-ENGINEERS-HANDBOOK/commit. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for commit?

Key use cases include: コミットメッセージの自動作成, `git diff --stat`を使用して変更の要約を生成する, 選択的なファイルステージングを使用してコミットの問題をデバッグする.

Which IDEs are compatible with commit?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for commit?

Gitのインストールと設定が必要. `.env`などの、`HUGGINGFACE_ACCESS_TOKEN`などの機密情報を含むファイルはコミットしない.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add captainsparrow10/LLM-ENGINEERS-HANDBOOK/commit. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use commit immediately in the current project.

! Reference-Only Mode

This page remains useful for installation and reference, but Killer-Skills no longer treats it as a primary indexable landing page. Read the review above before relying on the upstream repository instructions.

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

commit

Install commit, an AI agent skill for AI agent workflows and automation. Review the use cases, limitations, and setup path before rollout.

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Git Commit Workflow

Create a clean, well-documented git commit following this project's conventions.

Step 1: Review changes

bash
1git status 2git diff --stat

Show the user a summary of what will be committed.

Step 2: Stage files

Stage files selectively (never git add . or git add -A blindly):

bash
1# Stage specific files 2git add <file1> <file2> ...

Files to NEVER commit

PatternReason
.envContains HUGGINGFACE_ACCESS_TOKEN
*.pyc, __pycache__/Compiled Python
.DS_StoremacOS junk
model_output/Downloaded models
data/eval_results/Generated evaluation data
output/Pipeline outputs
.claude/settings.local.jsonPersonal Claude settings
.claude/CLAUDE.local.mdPersonal Claude memory

If $ARGUMENTS says "all" or "todo", stage all modified/untracked files except those above.

Step 3: Pre-commit hooks

This project has pre-commit hooks configured in .pre-commit-config.yaml:

  • ruff (linter) - auto-fixes code style
  • ruff-format (formatter) - auto-formats code
  • gitleaks - scans for leaked secrets

If a hook fails:

  1. The commit is aborted (it did NOT happen)
  2. Fix the issues (ruff usually auto-fixes, just re-stage)
  3. Create a NEW commit (never --amend after a hook failure - that would modify the wrong commit)

Step 4: Commit message format

Use Conventional Commits:

<type>(<scope>): <description>

[optional body]

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Types

TypeWhen to use
featNew feature or functionality
fixBug fix
docsDocumentation changes (README, CLAUDE.md, comments)
refactorCode restructuring without behavior change
choreMaintenance (deps, configs, cleanup)
styleFormatting, linting (no logic change)
testAdding or modifying tests
perfPerformance improvements
ciCI/CD changes

Scopes (optional, use the most relevant)

ScopeFiles
inferencemodel/inference/, infrastructure/inference_pipeline_api.py
ragapplication/rag/
evalmodel/evaluation/
trainingmodel/finetuning/
etlapplication/crawlers/, configs/digital_data_etl_*
datasetapplication/dataset/
settingssettings.py, .env, configs/
depspyproject.toml, poetry.lock
infradocker-compose.yml, ZenML configs

Examples

feat(rag): Add author filtering to Qdrant search
fix(inference): Add task parameter to HuggingFaceEndpoint
docs: Rewrite README for local-only setup
chore(deps): Upgrade langchain-huggingface to 1.2.0
refactor(eval): Replace OpenAI judge with HuggingFace

Step 5: Create the commit

Use HEREDOC for proper message formatting:

bash
1git commit -m "$(cat <<'EOF' 2<type>(<scope>): <description> 3 4<body if needed> 5 6Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> 7EOF 8)"

Step 6: Verify

bash
1git log --oneline -3

Show the user the new commit hash and message.

After the commit

Do NOT push automatically. Tell the user they can push with /push or git push.

If pre-commit hook fails

  1. Check what failed: usually ruff auto-fixed files
  2. Re-stage the auto-fixed files: git add <fixed-files>
  3. Create a NEW commit (do NOT use --amend)
  4. If gitleaks fails: a secret was detected. Remove it from the staged files before retrying.

関連スキル

Looking for an alternative to commit or another community skill for your workflow? Explore these related open-source skills.

すべて表示

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

333.8k
0
AI

widget-generator

Logo of f
f

カスタマイズ可能なウィジェットプラグインをprompts.chatのフィードシステム用に生成する

149.6k
0
AI

flags

Logo of vercel
vercel

React フレームワーク

138.4k
0
ブラウザ

pr-review

Logo of pytorch
pytorch

Pythonにおけるテンソルと動的ニューラルネットワーク(強力なGPUアクセラレーション)

98.6k
0
開発者