Agent skill · Code Review & Quality

github-summary

Generate an AI-synthesised summary of your GitHub activity (issues, PRs, commits) for a specified organisation and time period. Creates a natural language narrative with inline URL references. Use when user wants to summarise their work, review their contributions, or generate a work log.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill claude-github-summary-gokhanarkan-claude-github-summar-2 --agent claude-code

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

Facts
Files in the skill folder: 2
SKILL.md size: 15 KB
Bundled scripts: none
Path: skills/analysis/claude-github-summary-gokhanarkan-claude-github-summar-2/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

# GitHub Summary Generate a comprehensive, AI-written summary of your GitHub activity including issues, pull requests (authored and reviewed), and commits. ## Instructions When the user wants a GitHub activity summary: ### 1. Check Data Source Availability Check which data sources are available: **Check GitHub MCP Server:** Look for MCP tools: `search_issues`, `search_pull_requests`, `list_issues`, `issue_read`, `pull_request_read`, `list_commits` **Check gh CLI:** ```bash gh auth status ``` **Decision logic:** 1. **Both available:** Use `AskUserQuestion` to let the user choose: - "GitHub MCP Server (Recommended)" - richer context, faster for large queries - "GitHub CLI (gh)" - direct API access, useful for debugging 2. **Only MCP available:** Use MCP automatically, inform user 3. **Only gh CLI available:** Use gh CLI automatically, inform user 4. **Neither available:** Stop and guide user to either: - Configure GitHub MCP Server, or - Run `gh auth login` to authenticate the CLI ### 2. Fetch Available Organisations **Using MCP:** ```bash search_orgs or equivalent org listing tool ``` **Using gh CLI:** ```bash gh api user/orgs --jq '.[].login' ``` Also get the authenticated username

What's inside
Steps it walks through
  1. Instructions
  2. 1. Check Data Source Availability
  3. 2. Fetch Available Organisations
  4. 3. Ask for Organisation
  5. 4. Ask for Time Period
  6. 5. Phase 1: Discover Activity Items
  7. 6. Phase 2: Fetch Deep Context
  8. 7. Synthesise and Write Summary
  9. 8. Report Completion
  10. Edge Cases
  11. No Organisations Found
  12. No Activity Found
  13. API Rate Limits
  14. Large Result Sets
Ships with 1 file
  • metadata.json
Commands it runs
gh auth status
search_orgs or equivalent org listing tool
gh api user/orgs --jq '.[].login'
gh api user --jq '.login'
Issues created by user in date range
Issues where user is involved (assigned, commented, mentioned) but didn't create
PRs authored by user in date range
PRs reviewed by user in date range
Commits by user
Less accurate - requires post-filtering
More from claude-skill-registry
All skills →
About this skill
What does the github-summary skill do?

Generate an AI-synthesised summary of your GitHub activity (issues, PRs, commits) for a specified organisation and time period. Creates a natural language narrative with inline URL references. Use when user wants to summarise their work, review their contributions, or generate a work log.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill claude-github-summary-gokhanarkan-claude-github-summar-2 --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