NeVibeCode · 1,844 items
Skills for Testing and QA
Skills for Testing and QA: what each one does, an install command and example prompts.
check-skill skill Builds a labelled request set, runs a real agent against each row and scores whether your skill was engaged. Useful when a skill goes quiet.
CX Codex +1
★ 154repo stars
release-prep skill Runs a full audit, fixes critical bugs, validates deploy readiness and writes the release PR. Useful right before shipping a version to production.
CX Codex +1
★ 149repo stars
new-feature skill Runs a new feature through four ordered steps: failing tests first, then code, then the full suite. Handy when regressions are the thing you keep missing.
CX Codex +1
★ 149repo stars
claude-code-eyes skill 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.
CX Codex +1
★ 52repo stars
quality-gate skill Checks a patent draft for missing sections, weak evidence and broken citations. Useful once the text exists and you need to spot gaps before filing.
CX Codex +1
★ 110repo stars
lsp-test-correlation skill Maps an edited source file to the tests that cover it, then runs just those. Useful when one file changed and the full suite is overkill.
CX Codex +1
★ 165repo stars
skill-check skill Runs your skill definitions through Anthropic guidelines and the agentskills spec. Useful when you have written a SKILL.md and want to know where it breaks.
CX Codex +1
★ 42repo stars
otel-telemetrygen skill Builds version-pinned telemetrygen commands for synthetic OTLP traces, metrics and logs aimed at a collector.
CX Codex +1
★ 116repo stars
vibe-testing skill This skill walks your specification documents through made-up user scenarios and flags gaps, conflicts and unclear spots before implementation starts.
CX Codex +1
★ 24repo stars
manual-tester skill Runs manual testing sessions against your running app: exploratory, verification, smoke, UX and localization review, AI answer probes.
CX Codex +1
★ 88repo stars
bmad-run-inspector skill Reads bmad-loop run artifacts from .bmad-loop/runs/ — logs, journals, task state. Answers live questions about what the agent is doing and explains what went wrong in past runs.
CX Codex +1
★ 88repo stars
enforce-design-ci skill Adds a design-quality gate to pull requests that runs without an LLM: accessibility, tokens, component structure, responsive layout. Catches regressions before review.
CX Codex +1
★ 49repo stars
testing-strategies skill Gives your coding agent ready test patterns for a Micronaut and Kotlin backend: integration tests, repository tests, test data builders.
CX Codex +1
★ 109repo stars
python-testing-strategies skill A skill that tells your coding agent how to test FastAPI apps: pytest-asyncio, httpx AsyncClient, data factories and the checks every endpoint needs.
CX Codex +1
★ 109repo stars
dev:dry-run skill 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.
CX Codex +1
★ 57repo stars
harness:health skill Audits an eval dataset for size, difficulty spread, dead examples, category coverage and splits, then fixes what it finds on its own.
CX Codex +1
★ 57repo stars
harness:certify skill Runs the evolved agent's evaluation three times and reports mean with standard deviation. Useful when you cannot tell whether a score holds up between runs.
CX Codex +1
★ 57repo stars
test-strategy skill 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.
CX Codex +1
★ 107repo stars
ui-ux-design-principles skill A canon for user-experience decisions: a review checklist, hard rules and reference notes. Useful when you build a surface or review someone else's.
CX Codex +1
★ 36repo stars
simulation-validator skill A three-stage check for numerical simulations: config pre-flight, live log monitoring, and result validation. Failed runs get a diagnosis.
CX Codex +1
★ 83repo stars
convergence-study skill Computes observed convergence orders from mesh or timestep refinement, estimates discretization error, and reports the Grid Convergence Index per ASME V&V 20.
CX Codex +1
★ 83repo stars
suede-parity-contract skill 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.
CX Codex +1
★ 126repo stars
suede-ai-eval skill This skill drafts eval plans and coverage audits for LLM, RAG, agent and classifier surfaces. Reach for it before shipping AI behavior you cannot yet test.
CX Codex +1
★ 126repo stars
android-app-factory skill 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.
CX Codex +1
★ 126repo stars
pre-send-qa skill Runs a pre-flight pass over an email: merge tag fallbacks, dead links, spam triggers, CAN-SPAM and GDPR footers, mobile rendering.
CX Codex +1
★ 111repo stars
go-ci skill A skill that helps your AI agent write and set up GitHub Actions for Go projects. Use it when you need a pipeline with linting, tests, security checks, and caching.
CX Codex +1
★ 83repo stars
go-troubleshooting skill A skill that walks the agent through Go runtime diagnosis: panics, deadlocks, goroutine and memory leaks, race reports. Useful when a program crashes or hangs and the cause is unclear.
CX Codex +1
★ 83repo stars
go-grpc skill A skill that steers your coding agent through gRPC work in Go: proto contracts, error codes, deadlines, interceptors and streaming.
CX Codex +1
★ 83repo stars
wendy-iterating skill 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.
CX Codex +1
★ 62repo stars
wendy-cloud-iterate skill 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.
CX Codex +1
★ 62repo stars
interface-auditor skill Reads an interface description and flags UX antipatterns, rating severity and returning fix steps as JSON.
CX Codex +1
★ 26repo stars
ml-experiment-standards skill Makes the agent audit leakage, pick splits and justify metrics before a model gets trained. Useful when a result has to replicate, not just look good.
CX Codex +1
★ 35repo stars
mirrord-prev-env skill Walks you through mirrord preview environments: the changed service runs as its own pod in a shared cluster and takes traffic through a filter.
CX Codex +1
★ 29repo stars
mirrord-ci skill Walks the agent through wiring mirrord into CI so tests hit a live cluster instead of mocks. Useful when a pipeline has to reach staging and clean up afterwards.
CX Codex +1
★ 29repo stars
verification-before-completion skill Stops the agent from calling a task done until it has run the check and watched it pass. Useful right before a commit, a PR or a bugfix report.
CX Codex +1
★ 21repo stars
usability-check skill Runs a screen-level usability review against Nielsen's 10 heuristics and returns a pass/partial/fail table, useful before calling UI work done.
CX Codex +1
★ 47repo stars
reflexion skill 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.
CX Codex +1
★ 47repo stars
prompt-optimizer skill Runs your CLAUDE.md edits against two eval splits and shows whether the gain is real or just fitting the test set.
CX Codex +1
★ 47repo stars
ping skill A smoke test that answers with one marker line when the Mycelium plugin is packaged and wired up correctly. Not meant for everyday use.
CX Codex +1
★ 47repo stars
benchmark skill Runs your RAG pipeline through a query set and shows where the time and tokens go. Useful once answers start feeling slow or expensive.
CX Codex +1
★ 24repo stars
1,801–1,840 of 1,844
