github-kb

0
0
Source

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.zip

Installs 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 gh or 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 language
  • stars:<n> or stars:><n> - Filter by star count
  • topic:<name> - Filter by topic
  • user:<owner> - Search within a user's repos
  • org:<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 repository
  • state:open|closed - Filter by issue state
  • author:<username> - Filter by author
  • label:<name> - Filter by label
  • language:<lang> - Filter by repo language
  • comments:<n> or comments:><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 repository
  • state:open|closed|merged - Filter by PR state
  • author:<username> - Filter by author
  • label:<name> - Filter by label
  • language:<lang> - Filter by repo language
  • is: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

  1. Read GITHUB_KB.md to understand what projects exist
  2. Locate the project directory under ${GITHUB_KB_PATH:-/home/node/clawd/github-kb}/

Cloning a New Repo to KB

  1. Search GitHub if the full repo name is not known
  2. Clone to KB directory:
    git clone https://github.com/<owner>/<name>.git ${GITHUB_KB_PATH:-/home/node/clawd/github-kb}/<name>
    
  3. Generate project description: Read README or key files to understand the project
  4. 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.).
    
  5. 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.

a-stock-analysis

openclaw

A股实时行情与分时量能分析。获取沪深股票实时价格、涨跌、成交量,分析分时量能分布(早盘/尾盘放量)、主力动向(抢筹/出货信号)、涨停封单。支持持仓管理和盈亏分析。Use when: (1) 查询A股实时行情, (2) 分析主力资金动向, (3) 查看分时成交量分布, (4) 管理股票持仓, (5) 分析持仓盈亏。

624243

research-paper-writer

openclaw

Creates formal academic research papers following IEEE/ACM formatting standards with proper structure, citations, and scholarly writing style. Use when the user asks to write a research paper, academic paper, or conference paper on any topic.

70164

fivem

openclaw

Fix, create, or validate FiveM server resources for QBCore/ESX (config.lua, fxmanifest.lua, items, housing/furniture, scripts, MLOs). Use when asked to debug resource errors, convert ESX↔QB, update fxmanifest versions, add items, or source scripts from GitHub. Also use for SSH key generation for SFTP access.

220145

keyword-research

openclaw

Discovers high-value keywords with search intent analysis, difficulty assessment, and content opportunity mapping. Essential for starting any SEO or GEO content strategy.

38490

weread

openclaw

WeChat Reading (微信读书) CLI tool for fetching notes and highlights. Use when: (1) user asks about weread/微信读书 notes or highlights, (2) fetching today's or recent reading notes, (3) exporting book highlights, (4) managing reading bookshelf, (5) any task involving reading notes from WeChat Reading.

9081

gog

openclaw

Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.

19479

You might also like

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."

2,2002,027

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.

2,0251,573

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.

2,0711,355

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.

2,9441,286

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.

2,0741,087

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.

1,754894