agentleFS
Tony363Tony363/SuperClaude/.claude/skills/sc-git/SKILL.md

sc-git

Skill19 starsChanged 7 months agoMITView on GitHub

Git operations with intelligent commit messages and workflow optimization. Use when committing changes, managing branches, or optimizing git workflows.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Analyze: - Check repository state and changes

    line 25
  2. Distinctive:

    Validate: - Ensure operation is appropriate

    line 26
  3. Distinctive:

    Execute: - Run git command with automation

    line 27
  4. Distinctive:

    Write: - Commit message generation

    line 210

≈ “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 Operations Skill

Intelligent git operations with smart commit generation.

Quick Start

# Status analysis
/sc:git status

# Smart commit
/sc:git commit --smart-commit

# Interactive merge
/sc:git merge feature-branch --interactive

Behavioral Flow

  1. Analyze - Check repository state and changes
  2. Validate - Ensure operation is appropriate
  3. Execute - Run git command with automation
  4. Optimize - Apply smart messages and patterns
  5. Report - Provide status and next steps

Flags

FlagTypeDefaultDescription
--smart-commitboolfalseGenerate conventional commit message
--interactiveboolfalseGuided operation mode

Evidence Requirements

This skill does NOT require hard evidence. Git operations are self-documenting through:

  • Commit history
  • Branch state
  • Repository logs

Operations

Status Analysis

/sc:git status
# Repository state with change summary
# Actionable recommendations

Smart Commit

/sc:git commit --smart-commit
# Analyzes changes
# Generates conventional commit message
# Format: type(scope): description

Branch Operations

/sc:git branch feature/new-feature
/sc:git checkout main
/sc:git merge feature-branch

Interactive Operations

/sc:git merge feature --interactive
# Guided merge with conflict resolution
# Step-by-step assistance

Commit Message Format

Smart commits follow Conventional Commits:

type(scope): description

[optional body]

[optional footer]

Types:

  • feat - New feature
  • fix - Bug fix
  • docs - Documentation
  • refactor - Code restructuring
  • test - Test additions
  • chore - Maintenance

Examples

Analyze Changes

/sc:git status
# Summary of staged/unstaged changes
# Recommended next actions

Commit with Analysis

/sc:git commit --smart-commit
# Scans diff, generates message:
# feat(auth): add JWT token refresh mechanism

Guided Merge

/sc:git merge feature/auth --interactive
# Conflict detection and resolution guidance
# Step-by-step assistance

MCP Integration

PAL MCP (Validation & Review)

ToolWhen to UsePurpose
mcp__pal__precommitBefore commitComprehensive change validation
mcp__pal__codereviewBefore mergeCode quality review of changes
mcp__pal__consensusMerge conflictsMulti-model resolution strategy
mcp__pal__debugGit issuesInvestigate repository problems

PAL Usage Patterns

# Pre-commit validation (--smart-commit)
mcp__pal__precommit(
    path="/path/to/repo",
    step="Validating changes before commit",
    findings="Security, completeness, test coverage",
    include_staged=True,
    include_unstaged=False
)

# Review before merge
mcp__pal__codereview(
    review_type="full",
    step="Reviewing feature branch before merge",
    findings="Quality, security, breaking changes",
    compare_to="main"
)

# Consensus on merge conflict resolution
mcp__pal__consensus(
    models=[{"model": "gpt-5.2", "stance": "neutral"}, {"model": "gemini-3-pro", "stance": "neutral"}],
    step="Evaluate: Which conflict resolution preserves intended behavior?"
)

Rube MCP (Automation & Notifications)

ToolWhen to UsePurpose
mcp__rube__RUBE_SEARCH_TOOLSGitHub/GitLabFind repository management tools
mcp__rube__RUBE_MULTI_EXECUTE_TOOLPR/notificationsCreate PRs, notify team, update issues
mcp__rube__RUBE_CREATE_UPDATE_RECIPEGit workflowsSave reusable git automation

Rube Usage Patterns

# Create PR and notify team after commit
mcp__rube__RUBE_MULTI_EXECUTE_TOOL(tools=[
    {"tool_slug": "GITHUB_CREATE_PULL_REQUEST", "arguments": {
        "repo": "myapp",
        "title": "feat: Add user authentication",
        "body": "## Summary\n- Added JWT auth\n- Added refresh tokens",
        "base": "main",
        "head": "feature/auth"
    }},
    {"tool_slug": "SLACK_SEND_MESSAGE", "arguments": {
        "channel": "#pull-requests",
        "text": "New PR ready for review: feat: Add user authentication"
    }}
])

# Update issue status on merge
mcp__rube__RUBE_MULTI_EXECUTE_TOOL(tools=[
    {"tool_slug": "JIRA_UPDATE_ISSUE", "arguments": {
        "issue_key": "PROJ-123",
        "status": "Done"
    }},
    {"tool_slug": "GITHUB_CREATE_ISSUE_COMMENT", "arguments": {
        "repo": "myapp",
        "issue_number": 456,
        "body": "Merged in PR #789"
    }}
])

Flags (Extended)

FlagTypeDefaultDescription
--pal-precommitboolfalseUse PAL precommit validation
--pal-reviewboolfalseUse PAL codereview before merge
--create-prboolfalseCreate PR via Rube after commit
--notifystring-Notify via Rube (slack, teams, email)

Tool Coordination

  • Bash - Git command execution
  • Read - Repository state analysis
  • Grep - Log parsing
  • Write - Commit message generation
  • PAL MCP - Pre-commit validation, code review, conflict resolution
  • Rube MCP - PR creation, team notifications, issue updates

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.