Agent skill · Security

research-git-patterns

Git-aware skill for finding implementation patterns and retrieving story context from git history. Use when searching for similar implementations or understanding how a feature was built. To use this skill, you must have a story ID (e.g., "US-001-auth-login-admin"). Use research-user-stories skill to find the story ID.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill research-git-patterns --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 4 KB
Bundled scripts: none
Path: skills/analysis/research-git-patterns/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Research Git Patterns ## When to Use INVOKE when user asks about: - How a feature was implemented - Finding similar code patterns - Understanding implementation history - Retrieving story context ## Git Commands for Story Retrieval ### Find All Commits for a Story ```bash # Get full implementation history git log --grep="US-001-auth-login-admin" --oneline --graph # Get detailed changes with code git log --grep="US-001-auth-login-admin" -p --follow # Get just the files changed git diff --name-only main...$(git log --grep="US-001-auth-login-admin" -1 --format=%H) ``` ### Analyze Implementation Patterns ```bash # Find similar authentication implementations git log --grep="auth\|login\|clerk" --oneline # See how rate limiting was implemented across stories git log -S"RateLimiter" -p # Find all FastAPI endpoint additions git log --diff-filter=A -- "apps/server/src/api/**/*.py" ``` ### Extract Story Context ```bash # Get story implementation timeline git log --grep="US-001-auth-login-admin" --format="%ai %s" | sort # Calculate implementation time git log --grep="US-001-auth-login-admin" --format="%at" | awk 'NR==1{first=$1} END{print (last-first)/3600 " hours"}' # Get test coverage evo

What's inside
Steps it walks through
  1. When to Use
  2. Git Commands for Story Retrieval
  3. Find All Commits for a Story
  4. Analyze Implementation Patterns
  5. Extract Story Context
  6. Build Complete Context
  7. Pattern Mining
  8. Find Reusable Patterns
  9. Generate Implementation Template
  10. Context Building for Claude
  11. Integration with User Stories
  12. Efficiency Tips
  13. Error Recovery
  14. Performance Metrics
Ships with 1 file
  • metadata.json
Commands it runs
Get full implementation history
git log --grep="US-001-auth-login-admin" --oneline --graph
Get detailed changes with code
git log --grep="US-001-auth-login-admin" -p --follow
Get just the files changed
git diff --name-only main...$(git log --grep="US-001-auth-login-admin" -1 --format=%H)
Find similar authentication implementations
git log --grep="auth\|login\|clerk" --oneline
See how rate limiting was implemented across stories
git log -S"RateLimiter" -p
More from claude-skill-registry
All skills →
About this skill
What does the research-git-patterns skill do?

Git-aware skill for finding implementation patterns and retrieving story context from git history. Use when searching for similar implementations or understanding how a feature was built. To use this skill, you must have a story ID (e.g., "US-001-auth-login-admin"). Use research-user-stories skill to find the story ID.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill research-git-patterns --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going