github-kb
Manage a local GitHub knowledge base and provide GitHub search capabilities via gh CLI. Use when users ask about repos, PRs, issues, request to clone GitHub repositories, explore codebases, or need information about GitHub projects. Supports searching GitHub via gh CLI and managing local KB with GITHUB_KB.md catalog. Configure via GITHUB_TOKEN and GITHUB_KB_PATH environment variables.
Install
mkdir -p .claude/skills/github-kb && curl -L -o skill.zip "https://mcp.directory/api/skills/download/9059" && unzip -o skill.zip -d .claude/skills/github-kb && rm skill.zipInstalls to .claude/skills/github-kb
About this skill
GitHub Knowledge Base
Manage a local GitHub knowledge base and provide GitHub search capabilities via gh CLI. Key file: GITHUB_KB.md at the root of the KB directory catalogs all projects with brief descriptions.
Configuration
Set environment variables before use:
GITHUB_TOKEN- GitHub Personal Access Token (optional, for private repos)GITHUB_KB_PATH- Path to local KB directory (default:/home/node/clawd/github-kb)
Example:
export GITHUB_TOKEN="ghp_xxxx..."
export GITHUB_KB_PATH="/your/path/github-kb"
Token Privacy: Never hardcode tokens. Inject via environment variables or container secrets.
GitHub CLI (gh)
Requirement: GitHub CLI must be installed and authenticated.
Installation:
- macOS:
brew install gh - Linux:
apt install ghor see official install guide - Windows:
winget install GitHub.cli
Authentication:
# Interactive login
gh auth login
# Or use token from GITHUB_TOKEN env var
gh auth login --with-token <(echo "$GITHUB_TOKEN")
Verify: gh auth status
If gh is not installed or not authenticated, skip search operations and use only local KB features.
Searching Repos
# Search repos by keyword
gh search repos <query> [--limit <n>]
# Examples:
gh search repos "typescript cli" --limit 10
gh search repos "language:python stars:>1000" --limit 20
gh search repos "topic:mcp" --limit 15
Search qualifiers:
language:<lang>- Filter by programming languagestars:<n>orstars:><n>- Filter by star counttopic:<name>- Filter by topicuser:<owner>- Search within a user's reposorg:<org>- Search within an organization
Searching Issues
gh search issues "react hooks bug" --limit 20
gh search issues "repo:facebook/react state:open" --limit 30
gh search issues "language:typescript label:bug" --limit 15
Search qualifiers:
repo:<owner/repo>- Search in specific repositorystate:open|closed- Filter by issue stateauthor:<username>- Filter by authorlabel:<name>- Filter by labellanguage:<lang>- Filter by repo languagecomments:<n>orcomments:><n>- Filter by comment count
Searching Pull Requests
# Search PRs
gh search prs <query> [--limit <n>]
# Examples:
gh search prs "repo:vercel/next.js state:open" --limit 30
gh search prs "language:go is:merged" --limit 15
Search qualifiers:
repo:<owner/repo>- Search in specific repositorystate:open|closed|merged- Filter by PR stateauthor:<username>- Filter by authorlabel:<name>- Filter by labellanguage:<lang>- Filter by repo languageis:merged|unmerged- Filter by merge status
Viewing PR/Issue Details
# View issue/PR details
gh issue view <number> --repo <owner/repo>
gh pr view <number> --repo <owner/repo>
# View with comments
gh issue view <number> --repo <owner/repo> --comments
gh pr view <number> --repo <owner/repo> --comments
Local Knowledge Base Workflow
Querying About a Repo in KB
- Read GITHUB_KB.md to understand what projects exist
- Locate the project directory under ${GITHUB_KB_PATH:-/home/node/clawd/github-kb}/
Cloning a New Repo to KB
- Search GitHub if the full repo name is not known
- Clone to KB directory:
git clone https://github.com/<owner>/<name>.git ${GITHUB_KB_PATH:-/home/node/clawd/github-kb}/<name> - Generate project description: Read README or key files to understand the project
- Update GITHUB_KB.md: Add entry for the new repo following the existing format:
### [<name>](/<name>) Brief one-line description of what the project does. Additional context if useful (key features, tech stack, etc.). - Confirm completion: Tell user the repo was cloned and where to find it
Default Clone Location
If user says "clone X" without specifying a directory, default to ${GITHUB_KB_PATH:-/home/node/clawd/github-kb}/.
GITHUB_KB.md Format
The catalog file follows this structure:
# GitHub Knowledge Base
This directory contains X GitHub projects covering various domains.
---
## Category Name
### [project-name](/project-name)
Brief description of the project.
Maintain categorization and consistent formatting when updating.
More by openclaw
View all skills by openclaw →You might also like
flutter-development
aj-geddes
Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.
drawio-diagrams-enhanced
jgtolentino
Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.
ui-ux-pro-max
nextlevelbuilder
"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."
godot
bfollington
This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.
nano-banana-pro
garg-aayush
Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.
pdf-to-markdown
aliceisjustplaying
Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.
Related MCP Servers
Browse all serversConnect and manage Obsidian vaults with the Obsidian Local REST API for smarter note handling, semantic search, and seam
Automate system tasks securely with Shell Command Executor—perfect for knowledge database software and CRM relationship
Build persistent semantic networks for enterprise & engineering data management. Enable data persistence and memory acro
Chrome extension-based MCP server that exposes browser functionality to AI assistants. Control tabs, capture screenshots
Basic Memory is a knowledge management system that builds a persistent semantic graph in markdown, locally and securely.
Empower your CLI agents with NotebookLM—connect AI tools for citation-backed answers from your docs, grounded in your ow
Stay ahead of the MCP ecosystem
Get weekly updates on new skills and servers.