Browse Skills

Code Reviewer reviews completed implementation batches for spec compliance and code quality. Use it after execution waves, before merging, or at a review gate to verify changes and act on feedback.

Vercel React Best Practices gives React and Next.js performance rules for writing, reviewing, and refactoring code. Use it for data fetching, bundle size, rendering, and re-render optimization.

Web Interface Guidelines reviews UI code against Web Interface Guidelines and reports findings in terse file:line format. Use it to audit a site, check accessibility, or review UX and design best practices.

Makepad 2.0 Troubleshooting helps diagnose common Makepad 2.0 and Splash issues like invisible UI, missing text, failed clicks, hot reload problems, and build errors. Use it to find the likely cause and the correct fix.

Makepad Performance helps debug Makepad 2.0 rendering, batching, garbage collection, and UI freezes. Use it when text disappears, scrolling stutters, or you need to tune draw order, caching, or GC behavior.

AP Implementer builds one approved feature from a roadmap item or frozen plan using strict TDD and real test runs. It is used for direct implementation work and reports PLAN-CONFLICT if the plan no longer fits.

Ap Juror renders a binary PASS/FAIL sign-off on opened evidence for an Autoprompt run. Use it as a final review seat for mission alignment, coverage, tests, and blocker checks.

Depth Prober derives the deepest cause of a bug from issue text and code, then checks whether a proposed fix reaches that layer. It is used for terminal analysis where shallower causes must be rejected.

Framework Validator checks a generated framework descriptor for HRN-5 soundness before it is driven. It verifies gate mapping, terminal DONE structure, the BLOCKED invariant, and a non-empty acceptance set.

Fresh Verifier checks a candidate roadmap or plan against the mission and repository, then returns APPROVE or REJECT. It is used for blind validation with explicit failure by default when requirements, tests, or evidence are missing.

Goal Checker verifies whether a delivered result satisfies the original mission text, checking scope, evidence, coverage, and potential flaws. Use it when you need an adversarial pass/fail review of an agent run.

Azure App Testing provides guidance for Azure Load Testing and Playwright Workspaces. Use it for troubleshooting, architecture, security, quotas, CI/CD, and test authoring with JMeter, Locust, and Playwright.