Claude-skill-registry gitingest
Use when the user wants to fetch and contextualize a GitHub repository for future reference.
install
source · Clone the upstream repo
git clone https://github.com/majiayu000/claude-skill-registry
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data/gitingest" ~/.claude/skills/majiayu000-claude-skill-registry-gitingest && rm -rf "$T"
manifest:
skills/data/gitingest/SKILL.mdsource content
Fetch GitHub Repository Context
Arguments
$ARGUMENTS
Instructions
1. Parse Input
- Full URL: use directly
- user/repo: construct
https://github.com/{user/repo} - Single name: infer canonical repo (e.g., "rails" → "rails/rails"); if ambiguous, ask
2. Parse Filters
Natural language filters map to options:
- "only Python files" →
-i "*.py" - "exclude tests" →
-e "test/*" -e "*_test.py" - "branch develop" →
-b develop
3. Build Command
mkdir -p docs/reference/ gitingest [OPTIONS] -o docs/reference/<user>-<repo>.txt <url>
Options:
| Flag | Purpose |
|---|---|
| Output file (required) |
| Include pattern (repeatable) |
| Exclude pattern (repeatable) |
| Branch |
| Max file size |
| Include .gitignore'd files |
| Include submodules |
| GitHub PAT for private repos |
4. Execute & Confirm
- Run the command
- Read generated file to understand repo
- Report: repo name, purpose, file location, filters applied
Examples
/gitingest rails → rails/rails to docs/reference/rails-rails.txt /gitingest jdx/mise only rust → -i "*.rs" filter /gitingest user/repo exclude tests → -e "test/*" -e "*_test.py" /gitingest https://github.com/x/y branch main