audit-claude-settings
Use when auditing Claude Code settings and env vars against the latest docs and suggest tailored changes
best-practices
Use when about to choose, configure, or refine a tool, library, config format, API pattern, or project setup, or before proposing a design of your own — research current guidance, pitfalls, and prior art first; already knowing an approach, or assuming no prior art exists, is not an exemption. Also use when the user asks about best practices, gotchas, or recommended patterns
blindspot
Use when the user asks for a blindspot pass or to find their unknown unknowns, or signals unfamiliarity with a domain, tool, or codebase area ("never used X", "first time doing Y", "no idea where to start", "don't know what I don't know") before working there. Maps the areas their request leaves unnamed, purpose and shape before mechanics, shows how people usually answer each and why, and asks which to explore next, so unknown unknowns become known unknowns they can prompt with. Recommendations on a tool already chosen belong to best-practices
difference
Compare A vs B, weigh pros and cons of A, B, C, ..., or explain the nuance between sentences — a quick answer from what the model already knows
fuck-over-engineering
Use when the user asks what could be deleted or reduced to simplify a codebase, says "simplify", "over-engineered", or wants a repo-, folder-, or file-wide audit for over-engineering — hunts dead code, reinvented stdlib, needless dependencies, and single-implementation abstractions, reports ranked cuts, applies only the picks. Not a diff review and not a bug hunt
pr
Use when the user explicitly asks to push the current branch and open a PR, rewrite an open PR's body from its commits, or wait for CI and merge it
refactor-agents-md
Use when about to refactor or refine a user-level or project-level AGENTS.md
refactor-claude-md
Use when about to refactor or refine a user-level or project-level CLAUDE.md
refactor-memory
Use when refactoring Claude Code or Codex memories to remove stale or derivable entries, resolve contradictions, promote standing instructions, or reorganize recall. Not for standalone CLAUDE.md, AGENTS.md, or rules cleanup
refactor-skill
Use when about to refactor or refine an existing skill, its SKILL.md or sibling files, from a full restructure down to a one-line wording fix; a change that looks too small to need this skill is not an exemption. Not for creating a skill from scratch or for fixing only its allowed-tools
simple-english
Use when the user explicitly asks for simple English, plain English, or for text a non-native English speaker can read easily — rewrites docs, READMEs, issues, comments, or UI text into plain words and translation-friendly grammar, still native-sounding. Prose the user signs in their own voice goes to write-like-me instead
write-like-me
Use before producing any English text the user signs — READMEs, PRs, issues, PR and issue comments, code comments, emails, blog posts, human-facing docs — drafted or rewritten at native fluency in the voice of the skill's author, Vinta Chen. Fires mid-task too: a comment drafted inside another skill's workflow, or text the user will approve before it ships. Not for text addressed to agents unless the user asks
commit
Use when making any git commit. Always pass what was wrong before the changes as the argument; when nothing was wrong, pass what the changes do instead — never an invented why.
update-allowed-tools
Use when creating or editing a skill that uses Bash commands, file writes, or external tools and the allowed-tools frontmatter may be incomplete or carry entries that grant nothing