GitHub API operations - repositories, issues, pull requests, actions, code security, discussions, gists, and more. Use for GitHub-related tasks like managing PRs, issues, searching code, and monitoring workflows.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Mode: Cognitive/Prompt-Driven — No standalone utility script; use via agent context.
This skill provides access to the official GitHub MCP server with progressive disclosure for optimal context usage.
Context Savings: ~95% reduction
GITHUB_PERSONAL_ACCESS_TOKEN environment variable setThe server provides 80+ tools across 19 toolsets:
| Toolset | Description |
|---|---|
actions | Workflow management, runs, jobs, artifacts |
code_security | Scanning alerts, code analysis |
discussions | Forum interactions |
gists | Code snippets management |
issues | Issue creation, updates, commenting |
labels | Label management and filtering |
projects | GitHub Projects board management |
pull_requests | PR creation, review, merging |
repos | Code search, commits, releases, branches |
users | User search and management |
orgs | Organization and team management |
notifications | Notification management |
secret_scanning | Secret scanning alerts |
context | Context about the user |
Use the gh CLI for GitHub operations:
# Get repository info
gh repo view anthropics/claude-code
# List issues
gh issue list --repo anthropics/claude-code
# Search code
gh search code "language:python MCP"
# Create issue
gh issue create --repo me/myrepo --title "Bug" --body "Description"
# List pull requests
gh pr list --repo anthropics/claude-code
search_repositories - Search for repositoriescreate_repository - Create a new repositoryfork_repository - Fork a repositorylist_commits - List repository commitsget_commit - Get commit detailsget_file_contents - Get file contents from a repositorycreate_or_update_file - Create or update a filedelete_file - Delete a filepush_files - Push multiple filessearch_code - Search for code across GitHublist_branches - List repository branchescreate_branch - Create a new branchlist_tags - List repository tagsget_tag - Get tag detailslist_releases - List releasesget_latest_release - Get latest releaseget_release_by_tag - Get release by taglist_issues - List repository issuesissue_read - Read issue detailsissue_write - Create/update issuesadd_issue_comment - Add a comment to an issuesearch_issues - Search for issueslist_issue_types - List issue types (for organizations)get_label - Get label detailssub_issue_write - Manage sub-issuesassign_copilot_to_issue - Assign Copilot to an issuelist_pull_requests - List repository pull requestspull_request_read - Read PR detailscreate_pull_request - Create a new PRupdate_pull_request - Update a PRupdate_pull_request_branch - Update PR branchmerge_pull_request - Merge a PRsearch_pull_requests - Search for pull requestspull_request_review_write - Create/submit PR reviewsadd_comment_to_pending_review - Add comments to pending reviewrequest_copilot_review - Request Copilot reviewget_me - Get current authenticated usersearch_users - Search for usersget_teams - Get organization teamsget_team_members - Get team membersThe skill uses Docker to run the official GitHub MCP server:
ghcr.io/github/github-mcp-serverGITHUB_PERSONAL_ACCESS_TOKEN environment variable| Variable | Required | Description |
|---|---|---|
GITHUB_PERSONAL_ACCESS_TOKEN | Yes | GitHub PAT for authentication |
GITHUB_HOST | No | For GitHub Enterprise (default: github.com) |
GITHUB_TOOLSETS | No | Comma-separated toolsets to enable |
GITHUB_READ_ONLY | No | Set to 1 for read-only mode |
When using MCP, configure toolsets via environment variables:
# Only repos and issues
GITHUB_TOOLSETS=repos,issues
# Only pull requests and code security
GITHUB_TOOLSETS=pull_requests,code_security
If operations fail:
docker psecho $GITHUB_PERSONAL_ACCESS_TOKENgh auth status to verify authenticationBefore starting:
Read .claude/context/memory/learnings.md
After completing:
.claude/context/memory/learnings.md.claude/context/memory/issues.md.claude/context/memory/decisions.mdASSUME INTERRUPTION: If it's not in memory, it didn't happen.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
The English summary is being prepared. Showing the original description.
Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.
The English summary is being prepared. Showing the original description.
N-round opposing-stance debates for trade-off analysis. Assigns pro/con roles to agents, runs structured debate rounds with quality scoring, and produces a moderator synthesis with confidence-rated recommendation. Generalizable to architecture, technology, security, and design decisions.
The English summary is being prepared. Showing the original description.
Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze
The English summary is being prepared. Showing the original description.
Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suitable agent for a task. Enables self-evolution by generating persistent agents.
The English summary is being prepared. Showing the original description.
LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations
The English summary is being prepared. Showing the original description.