About
This skill enables full-text search across all your GitHub repositories, including private ones, by using a local mirror and ripgrep. It's ideal for finding code snippets or files when GitHub's API search is unreliable for private repos. The search operates on a synced local copy and returns results in milliseconds.
Quick Install
Claude Code
Recommendednpx skills add ykdojo/claude-code-tips -a claude-code/plugin add https://github.com/ykdojo/claude-code-tipsgit clone https://github.com/ykdojo/claude-code-tips.git ~/.claude/skills/private-github-searchCopy and paste this command in Claude Code to install this skill
Documentation
Private GitHub search
GitHub's modern code search (the one that indexes private repos) is web-only; gh search code uses the legacy engine and often returns nothing for private repos. Instead, search a local mirror of all the user's repos - it covers the same content as GitHub's index (default branch, non-fork) and a full search takes milliseconds.
Searching
Find the bundled sync script (works for plugin installs and manual symlinks):
find ~/.claude -name "private-github-search-sync.sh" 2>/dev/null | sort -V | tail -1
Always refresh first - it exits instantly if the mirror was synced within the last hour, and takes ~15s otherwise (--force syncs regardless of age):
bash <script-path>
rg -il 'pattern' ~/repo-mirror/repos # which files
rg -in 'pattern' ~/repo-mirror/repos | head # matching lines
First-time setup
If ~/repo-mirror/owners.txt doesn't exist: ask the user which GitHub accounts to mirror (don't guess - they may manage several), write them one per line to ~/repo-mirror/owners.txt, then run the sync script in the background (initial clone takes a few minutes; needs gh auth with access to those accounts).
Caveats
- Only the default-branch tip is mirrored - for history or other branches, use
git log -Sin a full clone or GitHub web search. - The mirror may contain private data: keep it out of synced folders and never commit or publish its contents.
GitHub Repository
Frequently asked questions
What is the private-github-search skill?
private-github-search is a Claude Skill by ykdojo. Skills package instructions and resources that Claude loads on demand, so Claude can perform private-github-search-related tasks without extra prompting.
How do I install private-github-search?
Use the install commands on this page: add private-github-search to Claude Code as a plugin, or clone its repository into your skills directory, then restart Claude so it picks up the skill.
What category does private-github-search belong to?
private-github-search is in the Development category, tagged api.
Is private-github-search free to use?
Yes. private-github-search is listed on AIMCP and free to install. It runs inside Claude, so no separate service account is required to use the skill itself.
Related Skills
qmd is a local search and indexing CLI tool that enables developers to index and search through local files using hybrid search combining BM25, vector embeddings, and reranking. It supports both command-line usage and MCP (Model Context Protocol) mode for integration with Claude. The tool uses Ollama for embeddings and stores indexes locally, making it ideal for searching documentation or codebases directly from the terminal.
This skill executes implementation plans by dispatching a fresh subagent for each independent task, with code review between tasks. It enables fast iteration while maintaining quality gates through this review process. Use it when working on mostly independent tasks within the same session to ensure continuous progress with built-in quality checks.
The mcporter skill enables developers to manage and call Model Context Protocol (MCP) servers directly from Claude. It provides commands to list available servers, call their tools with arguments, and handle authentication and daemon lifecycle. Use this skill for integrating and testing MCP server functionality in your development workflow.
This skill deploys and orchestrates Vertex AI ADK agents using A2A protocol, managing AgentCard discovery, task submission, and supporting tools like Code Execution Sandbox and Memory Bank. It enables building multi-agent systems with sequential, parallel, or loop orchestration patterns in Python, Java, or Go. Use it when asked to deploy ADK agents or orchestrate agent workflows on Google Cloud.