# Skills for Testing and QA Skills for Testing and QA: what each one does, an install command and example prompts. 1844 cards · page 46 of 47 - HTML: https://affpapa.org/en/nevibecode/skills/topic/testing?page=46 - Instructions for agents: https://affpapa.org/en/nevibecode/agents.md - [check-skill](https://affpapa.org/en/nevibecode/skills/check-skill.md) — skill · UiPath · Claude Code, Codex, Cursor +3 · ★ 154 — Builds a labelled request set, runs a real agent against each row and scores whether your skill was engaged. - [release-prep](https://affpapa.org/en/nevibecode/skills/release-prep.md) — skill · undeadlist · Claude Code, Codex, Cursor +3 · ★ 149 — Runs a full audit, fixes critical bugs, validates deploy readiness and writes the release PR. - [new-feature](https://affpapa.org/en/nevibecode/skills/new-feature.md) — skill · undeadlist · Claude Code, Codex, Cursor +3 · ★ 149 — Runs a new feature through four ordered steps: failing tests first, then code, then the full suite. - [claude-code-eyes](https://affpapa.org/en/nevibecode/skills/claude-code-eyes.md) — skill · fcavalcantirj · Claude Code, Codex, Cursor +3 · ★ 52 — The skill pulls a frame from an HTTP camera and hands it to the agent, so it answers from a display, board or wiring instead of a log. - [quality-gate](https://affpapa.org/en/nevibecode/skills/quality-gate.md) — skill · illusionaireal · Claude Code, Codex, Cursor +3 · ★ 110 — Checks a patent draft for missing sections, weak evidence and broken citations. - [lsp-test-correlation](https://affpapa.org/en/nevibecode/skills/lsp-test-correlation.md) — skill · blackwell-systems · Claude Code, Codex, Cursor +3 · ★ 165 — Maps an edited source file to the tests that cover it, then runs just those. - [skill-check](https://affpapa.org/en/nevibecode/skills/skill-check.md) — skill · olgasafonova · Claude Code, Codex, Cursor +3 · ★ 42 — Runs your skill definitions through Anthropic guidelines and the agentskills spec. - [otel-telemetrygen](https://affpapa.org/en/nevibecode/skills/otel-telemetrygen.md) — skill · ollygarden · Claude Code, Codex, Cursor +3 · ★ 116 — Builds version-pinned telemetrygen commands for synthetic OTLP traces, metrics and logs aimed at a collector. - [vibe-testing](https://affpapa.org/en/nevibecode/skills/vibe-testing.md) — skill · knot0-com · Claude Code, Codex, Cursor +3 · ★ 24 — This skill walks your specification documents through made-up user scenarios and flags gaps, conflicts and unclear spots before implementation starts. - [manual-tester](https://affpapa.org/en/nevibecode/skills/manual-tester.md) — skill · tronghieu · Claude Code, Codex, Cursor +3 · ★ 88 — Runs manual testing sessions against your running app: exploratory, verification, smoke, UX and localization review, AI answer probes. - [bmad-run-inspector](https://affpapa.org/en/nevibecode/skills/bmad-run-inspector.md) — skill · tronghieu · Claude Code, Codex, Cursor +3 · ★ 88 — Reads bmad-loop run artifacts from .bmad-loop/runs/ — logs, journals, task state. - [enforce-design-ci](https://affpapa.org/en/nevibecode/skills/enforce-design-ci.md) — skill · memi-design · Claude Code, Codex, Cursor +3 · ★ 49 — Adds a design-quality gate to pull requests that runs without an LLM: accessibility, tokens, component structure, responsive layout. - [testing-strategies](https://affpapa.org/en/nevibecode/skills/testing-strategies.md) — skill · c0x12c · Claude Code, Codex, Cursor +3 · ★ 109 — Gives your coding agent ready test patterns for a Micronaut and Kotlin backend: integration tests, repository tests, test data builders. - [python-testing-strategies](https://affpapa.org/en/nevibecode/skills/python-testing-strategies.md) — skill · c0x12c · Claude Code, Codex, Cursor +3 · ★ 109 — A skill that tells your coding agent how to test FastAPI apps: pytest-asyncio, httpx AsyncClient, data factories and the checks every endpoint needs. - [dev:dry-run](https://affpapa.org/en/nevibecode/skills/devdry-run.md) — skill · raphaelchristi · Claude Code, Codex, Cursor +3 · ★ 57 — Runs the evolve pipeline as a smoke test: checks tool syntax and skill cross-references, and with a LangSmith key exercises the full loop on a mock agent. - [harness:health](https://affpapa.org/en/nevibecode/skills/harnesshealth.md) — skill · raphaelchristi · Claude Code, Codex, Cursor +3 · ★ 57 — Audits an eval dataset for size, difficulty spread, dead examples, category coverage and splits, then fixes what it finds on its own. - [harness:certify](https://affpapa.org/en/nevibecode/skills/harnesscertify.md) — skill · raphaelchristi · Claude Code, Codex, Cursor +3 · ★ 57 — Runs the evolved agent's evaluation three times and reports mean with standard deviation. - [test-strategy](https://affpapa.org/en/nevibecode/skills/avelikiy-test-strategy.md) — skill · avelikiy · Claude Code, Codex, Cursor +3 · ★ 107 — A skill for QA engineers that turns "90% coverage" into a defensible plan: what to test, why that set, and a signal that the tests actually catch bugs. - [ui-ux-design-principles](https://affpapa.org/en/nevibecode/skills/ui-ux-design-principles.md) — skill · databricks-solutions · Claude Code, Codex, Cursor +3 · ★ 36 — A canon for user-experience decisions: a review checklist, hard rules and reference notes. - [simulation-validator](https://affpapa.org/en/nevibecode/skills/simulation-validator.md) — skill · HeshamFS · Claude Code, Codex, Cursor +3 · ★ 83 — A three-stage check for numerical simulations: config pre-flight, live log monitoring, and result validation. - [convergence-study](https://affpapa.org/en/nevibecode/skills/convergence-study.md) — skill · HeshamFS · Claude Code, Codex, Cursor +3 · ★ 83 — Computes observed convergence orders from mesh or timestep refinement, estimates discretization error, and reports the Grid Convergence Index per ASME V&V 20. - [suede-parity-contract](https://affpapa.org/en/nevibecode/skills/suede-parity-contract.md) — skill · JasonColapietro · Claude Code, Codex, Cursor +3 · ★ 126 — Keeps a single value across every surface of a product: the contract is generated from the reference surface and the rest assert against it in tests. - [suede-ai-eval](https://affpapa.org/en/nevibecode/skills/suede-ai-eval.md) — skill · JasonColapietro · Claude Code, Codex, Cursor +3 · ★ 126 — This skill drafts eval plans and coverage audits for LLM, RAG, agent and classifier surfaces. - [android-app-factory](https://affpapa.org/en/nevibecode/skills/android-app-factory.md) — skill · JasonColapietro · Claude Code, Codex, Cursor +3 · ★ 126 — A skill that takes an Android app from product idea to a signed bundle ready for Play Console, covering architecture, policy checks, billing, and store assets. - [pre-send-qa](https://affpapa.org/en/nevibecode/skills/pre-send-qa.md) — skill · Cogny AI · Claude Code, Codex, Cursor +3 · ★ 111 — Runs a pre-flight pass over an email: merge tag fallbacks, dead links, spam triggers, CAN-SPAM and GDPR footers, mobile rendering. - [go-ci](https://affpapa.org/en/nevibecode/skills/go-ci.md) — skill · eduardo-sl · Claude Code, Codex, Cursor +3 · ★ 83 — A skill that helps your AI agent write and set up GitHub Actions for Go projects. - [go-troubleshooting](https://affpapa.org/en/nevibecode/skills/go-troubleshooting.md) — skill · eduardo-sl · Claude Code, Codex, Cursor +3 · ★ 83 — A skill that walks the agent through Go runtime diagnosis: panics, deadlocks, goroutine and memory leaks, race reports. - [go-grpc](https://affpapa.org/en/nevibecode/skills/go-grpc.md) — skill · eduardo-sl · Claude Code, Codex, Cursor +3 · ★ 83 — A skill that steers your coding agent through gRPC work in Go: proto contracts, error codes, deadlines, interceptors and streaming. - [wendy-iterating](https://affpapa.org/en/nevibecode/skills/wendy-iterating.md) — skill · wendylabsinc · Claude Code, Codex, Cursor +3 · ★ 62 — Runs a find-fix-ship loop: each change gets its own worktree, a subagent carries it to green CI, and the loop stops itself when nothing is left. - [wendy-cloud-iterate](https://affpapa.org/en/nevibecode/skills/wendy-cloud-iterate.md) — skill · wendylabsinc · Claude Code, Codex, Cursor +3 · ★ 62 — Runs the Wendy Cloud dev stack end to end: brings up Docker and the Swift broker, runs integration tests, reads the failures and edits code. - [interface-auditor](https://affpapa.org/en/nevibecode/skills/interface-auditor.md) — skill · uxuiprinciples · Claude Code, Codex, Cursor +3 · ★ 26 — Reads an interface description and flags UX antipatterns, rating severity and returning fix steps as JSON. - [ml-experiment-standards](https://affpapa.org/en/nevibecode/skills/ml-experiment-standards.md) — skill · Muhammed Enes Duran · Claude Code, Codex, Cursor +3 · ★ 35 — Makes the agent audit leakage, pick splits and justify metrics before a model gets trained. - [mirrord-prev-env](https://affpapa.org/en/nevibecode/skills/mirrord-prev-env.md) — skill · MetalBear · Claude Code, Codex, Cursor +3 · ★ 29 — Walks you through mirrord preview environments: the changed service runs as its own pod in a shared cluster and takes traffic through a filter. - [mirrord-ci](https://affpapa.org/en/nevibecode/skills/mirrord-ci.md) — skill · MetalBear · Claude Code, Codex, Cursor +3 · ★ 29 — Walks the agent through wiring mirrord into CI so tests hit a live cluster instead of mocks. - [verification-before-completion](https://affpapa.org/en/nevibecode/skills/dshakes-verification-before-completion.md) — skill · dshakes · Claude Code, Codex, Cursor +3 · ★ 21 — Stops the agent from calling a task done until it has run the check and watched it pass. - [usability-check](https://affpapa.org/en/nevibecode/skills/usability-check.md) — skill · haabe · Claude Code, Codex, Cursor +3 · ★ 47 — Runs a screen-level usability review against Nielsen's 10 heuristics and returns a pass/partial/fail table, useful before calling UI work done. - [reflexion](https://affpapa.org/en/nevibecode/skills/reflexion.md) — skill · haabe · Claude Code, Codex, Cursor +3 · ★ 47 — A skill that runs implement, validate, self-critique and retry up to three times, then escalates with a written list of what is still broken. - [prompt-optimizer](https://affpapa.org/en/nevibecode/skills/haabe-prompt-optimizer.md) — skill · haabe · Claude Code, Codex, Cursor +3 · ★ 47 — Runs your CLAUDE.md edits against two eval splits and shows whether the gain is real or just fitting the test set. - [ping](https://affpapa.org/en/nevibecode/skills/ping.md) — skill · haabe · Claude Code, Codex, Cursor +3 · ★ 47 — A smoke test that answers with one marker line when the Mycelium plugin is packaged and wired up correctly. - [benchmark](https://affpapa.org/en/nevibecode/skills/takagoto-benchmark.md) — skill · TakaGoto · Claude Code, Codex, Cursor +3 · ★ 24 — Runs your RAG pipeline through a query set and shows where the time and tokens go. Next: https://affpapa.org/en/nevibecode/skills/topic/testing.md?page=47 ## Refine [qa](https://affpapa.org/en/nevibecode/tag/qa.md) · [debugging](https://affpapa.org/en/nevibecode/tag/debugging.md) · [python](https://affpapa.org/en/nevibecode/tag/python.md) · [typescript](https://affpapa.org/en/nevibecode/tag/typescript.md) · [ci-cd](https://affpapa.org/en/nevibecode/tag/ci-cd.md) · [accessibility](https://affpapa.org/en/nevibecode/tag/accessibility.md) · [e2e](https://affpapa.org/en/nevibecode/tag/e2e.md) · [tdd](https://affpapa.org/en/nevibecode/tag/tdd.md) · [ios](https://affpapa.org/en/nevibecode/tag/ios.md) · [dotnet](https://affpapa.org/en/nevibecode/tag/dotnet.md) · [java](https://affpapa.org/en/nevibecode/tag/java.md) · [cli](https://affpapa.org/en/nevibecode/tag/cli.md) ## Narrow this list Parameters: `?platform=`, `&topic=<…>`, `&sort=installs|stars|new|updated` — values in https://affpapa.org/en/nevibecode/agents.md --- NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md