Skillkeel
- 8 skills
- 0 followers
- 10 hours ago last updated
- ▌ Claude Md Init · skillkeelUse when a repo has no CLAUDE.md, or the user asks to create/refresh CLAUDE.md or project instructions for Claude Code. Generates a short, verified CLAUDE.md from the repo's real build/test/lint commands and layout, and never invents commands.
- ▌ Commit Message · skillkeelUse when the user asks to commit, write a commit message, or stage-and-commit changes. Produces a Conventional Commits message derived from the actual staged diff, never from memory of what was edited.
- ▌ Pr Description · skillkeelUse when the user asks to open a pull request, write a PR description, or summarise a branch for review. Builds the description from the full branch diff against the base and from commit messages, and includes a test plan with real commands.
- ▌ Readme Refresh · skillkeelUse when the user asks to update, fix, or audit README.md, or when README commands look stale. Checks every command, path, and claim in the README against the actual repo and proposes a minimal diff; never rewrites the whole file unasked.
- ▌ Test Gap Finder · skillkeelUse when the user asks what to test next, where coverage is weak, or before a refactor of untested code. Maps source modules to existing tests, ranks untested modules by churn and size, and proposes the five highest-value tests with concrete names and cases, without writing them unasked.
- ▌ Dependency Audit · skillkeelUse when the user asks to check dependencies for vulnerabilities, outdated packages, or before a release. Runs the ecosystem's real audit tool, separates fixable from unfixable, and proposes minimal safe upgrades with lockfile changes reviewed, never bulk-upgrading blindly.
- ▌ Changelog · skillkeelUse when the user asks to update or generate CHANGELOG.md, prepare release notes, or cut a version. Builds entries from git history since the last tag (or a given range) in Keep a Changelog format, grouped by change type, never from memory.
- ▌ Secret Audit · skillkeelUse when the user asks whether secrets were committed, before open-sourcing a repo, or after a leak scare. Scans the working tree and full git history for credentials, reports findings with commit and path, and gives a remediation plan (rotate first, then purge).