Review a GitHub PR or local diff for the @ilamy/calendar repo. Drafts findings as Conventional Comments and waits for explicit approval before posting anything to GitHub. Use when the user says "review this PR", "review PR
Reviews code changes for reuse, composition, codebase consistency, and slop. Use when asked to review PRs/diffs, check code reuse, composition, cleanliness, or whether code fits the codebase.
Cut a new release of @ilamy/calendar — analyze commits since the last tag, suggest a semver bump, draft a CHANGELOG entry in the project's existing style, run the CI gate, commit, tag, push to origin, and create the GitHub release page (marked as `latest`). Pauses for the user to run `bun run release` (build + publish) interactively, then (on their signal) updates and deploys the docs site (`apps/website`, with demo/playground updates when needed) and comments on every issue closed by the release, closing any still open. Use whenever the user says "release a new version", "cut a release", "ship v1.x", "bump the version", "prep a release", "publish the next version", "I just published X", "close the released issues", or anything that implies a new version should go out or a shipped version needs its issue follow-ups.
Use when finishing a feature, fixing a bug, before committing React code, or when the user types `/doctor`, asks to scan, triage, or clean up React diagnostics. Covers lint, accessibility, bundle size, architecture. Includes a regression check and a full local-triage workflow that fetches the canonical playbook.
Systematically reduce the shipped bundle size of a JS/TS library without sacrificing code readability or breaking consumer APIs. Use this skill whenever the user mentions bundle size, tree-shaking, code duplication to cut, "reduce size of", "make lighter", "shrink output", looks for wins in `dist/`, or asks to audit a library's heaviest files. Also trigger when the user pastes a `bun run build` / `npm run build` / `bunup` / `tsup` / `rollup` output showing `dist/index.js` size and asks for reductions. Prefer this over vague "refactor to be smaller" answers — it enforces a measure-first loop, concrete opportunity categories, and readability guardrails.