Execute qualquer Skill no Manus
com um clique

Execute qualquer Skill no Manus com um clique

Começar

commit

Estrelas1

Forks0

Atualizado30 de maio de 2026 às 02:46

Agent Skill for safely handling the git commit process. Use whenever the user asks to create commits

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Executar no Manus

Fonte

CXwudi

CXwudi/agent-config

Abrir repositório GitHub Ver repositórios do creator

Download

Executar no Manus

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Desenvolvedores de softwareInformática e Matemática·SOC 15-1252

SKILL.md

readonly

name	commit
description	Agent Skill for safely handling the git commit process. Use whenever the user asks to create commits

Commit Skill

This skill handles the git commit workflow with a focus on logical grouping and clear documentation.

Workflow

Analyze State
- Run git status to identify all untracked, modified, and deleted files.
- Run git diff (unstaged) and git diff --cached (staged) to examine the actual code changes.
Group Changes (Crucial Step)
- Analyze the purpose of changes across all files.
- Decision:
  - Single Commit: If all changes are small or serve a single purpose (e.g., "fix login bug" involved 3 files), keep them together.
  - Multiple Commits: If changes cover distinct, unrelated tasks (e.g., "update documentation" AND "refactor database code"), split them into separate commits.
- Plan: If multiple commits are needed, list which files go into which commit.
Draft Commit Messages For each identified commit group:
- Header: gitmoji <type>(<scope>): <subject>
  - Gitmoji: Use the Gitmoji Guide (e.g., ✨ for features, 🐛 for bugs, ♻️ for refactor, 📝 for docs).
  - Type: feat, fix, docs, style, refactor, test, chore.
  - Subject: Imperative mood, concise.
- Body (Optional/Context-Dependent):
  - Small/Simple changes: No body or 1-2 sentences explaining why.
  - Large/Complex changes: Use a bulleted list to detail specific changes.
Execute Commits For each group:
1. git add <specific_files> (Do not lazy use git add . unless all changes truly belong to one commit).
2. git commit -m "header" -m "body"
3. Verify success.

Important Rules

NEVER commit secrets, API keys, or .env files.
Atomic Commits: Prefer smaller, focused commits over giant "dump" commits.
Verification: Always run git status after operations to ensure the working directory state is what you expect.

Examples

Scenario 1: Mixed Changes

Changes: auth.py (bug fix), README.md (typo fix).
Action: Split into two commits.
1. git add auth.py -> git commit -m "🐛 fix(auth): resolve token expiration issue"
2. git add README.md -> git commit -m "📝 docs: fix typo in installation guide"

Scenario 2: Large Feature

Changes: 5 files related to a new "Dark Mode".

Action: Single commit.

Title: ✨ feat(ui): implement dark mode theming

Body:

```text
- Add theme context provider
- Update color palette in tailwind config
- Add toggle switch to settings page
- Fix contrast issues on dashboard
```

Mais deste repositório

mesmo repositório

plan

CXwudi/agent-config

Agent Skill for planning implementation work into comprehensive, testable steps. Use before implementation to create a clear roadmap for execution.

2026-06-231

design-spec

CXwudi/agent-config

Agent Skill for writing and reviewing durable design specs. Use when the user asks to write, formalize, save, review, or approve a spec, design document, RFC, or implementation-ready proposal. If the direction is still vague or unsettled, use `brainstorming` first before producing the spec. If the direction is already clear and no spec is needed, use `plan`.

2026-06-231

tmux-tui-agent

CXwudi/agent-config

Agent Skill for spawning new AI agents with interactive TUI in tmux. Use when work can be offloaded to new or existing AI agents (exploration, code review, second opinions, parallel work, etc.). Can also be used if spawning new agents with different model families (e.g. Spawn GPT models when you are Claude Code, Spawn Claude models when you are Codex, Or spawn any other models (e.g. DeepSeek, Gemini) with Pi). Prefer harness's own subagent tools when no need for a different model.

2026-06-231

opencli

CXwudi/agent-config

Agent Skill for OpenCLI. Use when the user wants to control websites through the `opencli` CLI, run or inspect OpenCLI site/app/external adapters, use the OpenCLI browser bridge/CDP automation

2026-06-131

brainstorming

CXwudi/agent-config

Agent Skill for collaborative brainstorming and design exploration. Use when the user wants to think through an idea, compare options, clarify trade-offs, or get a quick recommendation, without forcing a written artifact. If the user wants a saved, reviewed design spec, use `design-spec`.

2026-06-061

python

CXwudi/agent-config

Agent Skill for working with Python. Use when writing, editing, or reviewing Python code and scripts.

2026-06-031

Commit Skill

This skill handles the git commit workflow with a focus on logical grouping and clear documentation.

Workflow

Analyze State

Run git status to identify all untracked, modified, and deleted files.
Run git diff (unstaged) and git diff --cached (staged) to examine the actual code changes.

Group Changes (Crucial Step)

Analyze the purpose of changes across all files.
Decision:
- Single Commit: If all changes are small or serve a single purpose (e.g., "fix login bug" involved 3 files), keep them together.
- Multiple Commits: If changes cover distinct, unrelated tasks (e.g., "update documentation" AND "refactor database code"), split them into separate commits.
Plan: If multiple commits are needed, list which files go into which commit.

Draft Commit Messages For each identified commit group:

Header: gitmoji <type>(<scope>): <subject>
- Gitmoji: Use the Gitmoji Guide (e.g., ✨ for features, 🐛 for bugs, ♻️ for refactor, 📝 for docs).
- Type: feat, fix, docs, style, refactor, test, chore.
- Subject: Imperative mood, concise.
Body (Optional/Context-Dependent):
- Small/Simple changes: No body or 1-2 sentences explaining why.
- Large/Complex changes: Use a bulleted list to detail specific changes.

Execute Commits For each group:

git add <specific_files> (Do not lazy use git add . unless all changes truly belong to one commit).
git commit -m "header" -m "body"
Verify success.

Important Rules

NEVER commit secrets, API keys, or .env files.

Atomic Commits: Prefer smaller, focused commits over giant "dump" commits.

Verification: Always run git status after operations to ensure the working directory state is what you expect.

Examples

Scenario 1: Mixed Changes

Changes: auth.py (bug fix), README.md (typo fix).

Action: Split into two commits.

git add auth.py -> git commit -m "🐛 fix(auth): resolve token expiration issue"
git add README.md -> git commit -m "📝 docs: fix typo in installation guide"

Scenario 2: Large Feature

Changes: 5 files related to a new "Dark Mode".

Action: Single commit.

Title: ✨ feat(ui): implement dark mode theming

Body:

```text
- Add theme context provider
- Update color palette in tailwind config
- Add toggle switch to settings page
- Fix contrast issues on dashboard
```