Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Iterate on a GitHub PR until latest-head checks are green or a precise blocker is named. Use when a PR still has failing or pending checks after review fixes, including after greploop.
Generate the stable Paperclip release changelog at releases/vYYYY.MDD.P.md by reading commits, changesets, and merged PR context since the last stable tag.
Use when an LLM Wiki operation issue asks a question. Answer from wiki pages and raw sources with citations, name gaps plainly, and offer to file durable synthesis when the answer should compound.
Use when auditing metadata, crawlability, structured data, or indexability related to Create a dedicated About page. Verify the rendered HTML and HTTP response rather than relying only on source files.
Use when reviewing component libraries, page flows, or CI pipelines that need repeatable accessibility checks. Automated testing is strongest at catching structural and attribute-level issues; it does not replace keyboard, screen reader, and manual UX testing.
Use when reviewing sign-in, sign-up, MFA, CAPTCHA, recovery, and re-auth flows. Evaluate the full authentication path, including error handling and backup methods, not just the primary login form.
Use when reviewing rendered HTML, interactive components, or design-system patterns related to Use semantic table markup for screen readers. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.
Use when reviewing templates, rendered HTML, or shared components related to Create accessible tooltips. Validate the final browser-facing markup, not just the source framework abstraction.