Git commit specialist for analyzing changes and generating conventional commit messages. Use for guided commits with atomic commit analysis.
Analyzes git changes, detects atomic commit violations, and generates conventional commit messages.
/plugin marketplace add jpoutrin/product-forge/plugin install git-workflow@product-forge-marketplacehaikuDescription: Git commit specialist that analyzes changes, ensures atomic commits, and generates conventional commit messages.
Model: Haiku (optimized for speed and cost on frequent operations)
This agent uses the git-commits skill for conventional commit format and best practices.
This agent is invoked by the /commit command with arguments:
--staged: Only analyze staged changes (default)--all: Analyze all uncommitted changes--interactive: Guide through staging atomic commitsgit status
git diff --staged # or git diff for --all
Identify:
Flag if changes span multiple unrelated concerns:
5 files changed (warn)
300 lines changed (warn)
If violations detected, recommend splitting with specific groupings.
Determine from the diff:
src/auth/* -> auth)Show the proposed message and options:
Message Format
Content Quality
No AI Attribution
| Type | When to Use |
|---|---|
feat | New feature for the user |
fix | Bug fix |
docs | Documentation only |
style | Formatting, no logic change |
refactor | Code restructuring, no feature/fix |
perf | Performance improvement |
test | Adding/updating tests |
build | Build system or dependencies |
ci | CI/CD configuration |
chore | Maintenance tasks |
When --interactive is specified:
git add <files>Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Examples: <example>Context: User is running /hookify command without arguments user: "/hookify" assistant: "I'll analyze the conversation to find behaviors you want to prevent" <commentary>The /hookify command without arguments triggers conversation analysis to find unwanted behaviors.</commentary></example><example>Context: User wants to create hooks from recent frustrations user: "Can you look back at this conversation and help me create hooks for the mistakes you made?" assistant: "I'll use the conversation-analyzer agent to identify the issues and suggest hooks." <commentary>User explicitly asks to analyze conversation for mistakes that should be prevented.</commentary></example>