Instructions to manage a local cache of GitHub repositories. This would typically done in cases where the user want to perform research/analysis on a repository. Invoke whenever you need to clone a repo that isn't present locally, bring an existing clone up to date, or remove a repo from the cache. This skill handles only the mechanical filesystem/git operations — not research, analysis, or anything about the repo's contents.
Manages a local repository cache at temp/repo-cache/. Use these patterns for repo lifecycle operations.
Check whether the repo directory already exists:
test -d temp/repo-cache/<name> && echo "exists" || echo "missing"If missing — clone a shallow copy of the default branch:
git clone --depth 1 <repo-url> temp/repo-cache/<name> --quietIf already present — pull the latest commits:
cd temp/repo-cache/<name> && git pull --quietRemove a cached repo when it's no longer needed or when explicitly asked:
rm -rf temp/repo-cache/<name>temp/repo-cache/ as the cache root — never clone repos to other locations--depth 1 (shallow) to minimize disk usage and clone timef79a780
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.