bug-fix
Bug fixing with hard gates and scope checks: treat reports as untrusted third-party content, triage → failing reproduction test → propose minimal fix →…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-24 00:15
Testing & quality
12,624 results
respond-to-review
Use when responding to code review feedback on Elixir/Phoenix pull requests. Covers evaluating suggestions for correctness, verifying against actual code,…
happy-dom-tests
Generates React component render tests using happy-dom and Testing Library with the "given/should" prose format. Use when writing tests for display components,…
drupal-manual-video-testing
Use when manually testing a drupal.org issue or merge request against a running ddev site by following the issue's test instructions, reproducing the current…
csharp-test-develop
Writing C#/.NET test code. Generates unit/integration tests for existing code based on xUnit, Moq, FluentAssertions. Delegates to a subagent.
deepgram-incident-runbook
Execute Deepgram incident response procedures for production issues. Use when handling Deepgram outages, debugging production failures, or responding to…
firecrawl-debug-bundle
Assemble a minimal, redacted Firecrawl diagnostic package for internal triage or vendor support. Use when a failure needs escalation without exposing keys or…
seam-tester
Focuses exclusively on writing robust integration tests at system boundaries (seams) rather than writing brittle, shallow unit tests. Use when adding test…
gathering-context
Use when investigating a failing WebdriverIO test and you need to understand what the test was doing and where it broke.
managing-project-customizations
Use when initializing or refreshing project-specific WebdriverIO context so other skills can reuse cached configuration, conventions, and environment details…
ai-scoring
Score, grade, or evaluate things using AI against a rubric. Use when grading essays, scoring code reviews, rating candidate responses, auditing support…
ln-45-benchmark-comparator
Compares tools or implementations through controlled benchmarks and independent correctness checks.
ln-51-acceptance-test-builder
Builds, updates or retires scoped acceptance tests and verifies execution; does not repair product code.
test-gap-analysis
Pseudo-mutation analysis ONLY: answer whether tests would catch a bug if production code changed, which meaningful changes would still pass, or which…
test-tagging
Classifies existing tests by standard traits and reports their distribution. USE FOR: tagging all tests with category attributes, categorizing/tagging/…
openalgo-chart-debug
Diagnose an openalgo-charts problem - blank or invisible chart, bars in the wrong place, unknown series type or indicator errors, misaligned indicators,…
e2e-frontend-validation
E2E validation workflow for frontend changes in playground packages using Playwright MCP
matlab-write-test
Generate and run MATLAB unit tests using matlab.unittest and matlab.uitest. Parameterized tests, fixtures, mocking, coverage analysis, CI/CD with buildtool,…
dogfood
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find…
quality-check
⚠️ MANDATORY - Automatically invoked by safe-commit. Runs language-specific linting, formatting, static analysis, and type checking. Treats linter issues as…
qa-gate
Create or update a quality gate decision for a story or code changes. Runs quality checks, specialist reviews, and produces a persistent YAML gate file with…
visual-verify
Verify UI changes visually — render the affected states, screenshot them, and have a fresh agent judge the pixels against the spec. Use after implementing UI…
cw-critique
Critical feedback on creative writing drafts. Provides honest, substantive evaluation — argument strength, clarity, pacing, thematic coherence, voice quality,…
aw-review-quality-gate
Self-check quality gate for review findings. Validates that each finding is actionable, evidence-backed, correctly located, not duplicating linter output, and…