Loading...
Loading...
Found 87 Skills
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.
Bug-to-test pipeline: reproduce the bug as a failing test first, then fix. The regression test lives forever.
Standardize requirement/feature changes in an existing codebase (especially Chrome extensions) by turning "改需求/需求变更/调整交互/改功能/重构流程" into a repeatable loop: clarify acceptance criteria, confirm current behavior from code, assess impact/risk, design the new logic, implement with small diffs, run a fixed regression checklist, and update docs/decision log. Use when the user feels the change process is chaotic, when edits tend to sprawl across files, or when changes touch manifest/service worker/OAuth/storage/UI and need reliable verification + rollback planning.
Reads documented bugs from bugs.md, analyzes root causes, implements fixes with regression tests, and validates the full test suite. Prioritizes fixes by severity (high to low). Updates bugs.md with correction status and generates a final bugfix report. Use when the user asks to fix bugs, resolve issues, or run the bugfix workflow for a feature. Do not use for new feature implementation, code review, or QA testing.
A disciplined diagnostic loop for tricky bugs and performance regressions. Reproduce → Minimize → Hypothesize → Instrument → Fix → Regression-test. Use this when the user says "diagnose this" / "debug this", reports a bug, states that something is broken/throwing errors/failing, or describes a performance regression.
Rigorous visual validation expert specializing in UI testing, design system compliance, and accessibility verification. Masters screenshot analysis, visual regression testing, and component validation. Use PROACTIVELY to verify UI modifications have achieved their intended goals through comprehensive visual analysis.
Storybook UI component development and testing. Use for component testing.
Hypothesis-driven autonomous debugging with real command validation
Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix evidence, and a ship-readiness summary. For report-only mode, use /qa-only.
Senior QA Automation Engineer with 10+ years E2E testing experience. Use when writing end-to-end tests for web apps with Playwright, mobile apps with Detox, testing critical user flows, cross-browser testing, or visual regression testing.
Builds end-to-end browser tests for critical user flows using Playwright or Cypress. Includes selector strategies, test data management, page objects, and visual regression testing. Use for "E2E testing", "browser tests", "Playwright", or "Cypress tests".
Use when validating automation builds before launch or after significant changes.