NeVibeCode · 1,762 items
Skills for Testing and QA
Skills for Testing and QA: what each one does, an install command and example prompts.
find-bugs skill Walks the diff on your current branch and reports bugs, security holes and code quality problems. Handy before a merge or a push.
944installs
accessibility-auditor skill Audits web interfaces for accessibility issues and suggests fixes for WCAG, ARIA, keyboard access, and screen-reader use.
846installs
metric-pack-designer
official skill A skill that helps you describe a local metric pack for plugin-eval: rubric categories, checks and metrics in a schema-compatible shape.
CX Codex GP ChatGPT
1installs
evaluate-skill
official skill Audits a local skill, explains the score, and points to the first fixes. Use it before benchmarking or measuring token usage.
CX Codex GP ChatGPT
1installs
jackin-release-check skill Runs the jackin❯ release-readiness gates and reports a verdict for each one. Use it before cutting a release.
CX Codex +1
469installs
grade-iterate skill Phase 3 of building a Claude Managed Agent. Sets a rubric, reads each grader verdict and iterates until a version passes.
1installs
playwright-in-sandbox skill A skill that verifies UI changes in a sandbox browser and writes durable Playwright E2E coverage. Useful when you want screenshot proof, not just DOM state.
CX Codex +1
508installs
v8-xsd-fetch skill Downloads 1C XML export XSD schemas by format version into the project directory. Use it to inspect available versions or validate an export against its schema.
CX Codex
17installs
security-audit skill A workflow skill that walks a web app or API through recon, vulnerability scanning, pentesting, hardening and reporting.
673installs
playwright-interactive-sandbox skill This skill runs iterative web UI checks through a persistent Node.js Playwright workflow. Use it for functional checks, visual QA, and screenshot evidence.
CX Codex +1
400installs
tool-abuse-detection skill Runs dialogue probes against an agent to catch command execution, out-of-scope file reads and SSRF. Useful when the agent holds file, code or network tools.
CX Codex +1
★ 7,083repo stars
memory-rag-poisoning-detection skill This skill tests whether an agent stores hostile instructions in memory or a knowledge base and follows them in later conversations.
CX Codex +1
★ 7,083repo stars
data-leakage-detection skill A skill that runs escalating dialogue probes against an agent to surface leaked system prompts, credentials, PII and internal config.
CX Codex +1
★ 7,083repo stars
dtcg-tokens skill Turn multimodal source material into DTCG tokens, evidence data, and an HTML proof artifact. Use it when token choices need to trace back to inspectable source material and pass visual review.
CX Codex +1
303installs
python-pro skill A Claude skill that steers Python 3.12+ development: async patterns, typing, profiling, plus uv, ruff, pydantic and FastAPI.
399installs
testing-patterns skill A Claude skill that hands the agent Jest testing patterns: data factories, module mocks and the red-green-refactor loop.
365installs
code-review-checklist skill A skill that walks a reviewer through context, functionality, quality, security, performance and tests. Useful on pull requests and audits.
365installs
pentest-checklist skill A skill that walks you through pentest planning: objectives, scope, environment prep, tester selection and monitoring. Useful before a security assessment.
336installs
azure-microsoft-playwright-testing-ts skill A skill that wires Playwright tests to Azure Playwright Workspaces, so browser runs happen on cloud browsers and land in the Azure portal.
3installs
vibe-verify skill This skill exercises a running product against acceptance criteria and reports evidence. A passing build on its own proves nothing about behavior.
CX Codex +1
★ 3,183repo stars
vibe-debug skill A skill that walks an agent through a reproducible failure in an existing project: crashes, broken behavior, failing checks. Not for greenfield planning.
CX Codex +1
★ 3,183repo stars
playwright-e2e-builder skill A skill that plans and builds Playwright E2E suites. It interviews you about flows and auth first, then writes the tests.
271installs
tui-validate skill This skill screenshots a terminal UI with freeze and judges it against criteria using an LLM. Useful after TUI changes, when you need to catch broken layout.
CX Codex +1
★ 3,186repo stars
test-driven-development skill This skill walks the agent through RED → GREEN → REFACTOR and makes it write tests before code. Useful when a spec or task needs to become checkable tests.
CX Codex +1
★ 3,186repo stars
code-assist skill A skill that walks the agent through Explore, Plan, Code, Commit: research and a plan first, then failing tests, then code. Useful when a task should go through TDD instead of straight to implementation.
CX Codex +1
★ 3,186repo stars
improvement skill Walks the agent through a TDD loop when you are enhancing something that already works. Useful for UX, performance and code-quality tweaks.
CX Codex +1
★ 1,556repo stars
fix-bug skill The skill walks an agent through a defect: reproduce it, write a failing test, apply a minimal fix, verify. Built for the ClaudeBar project.
CX Codex +1
★ 1,556repo stars
loki-mode skill Runs a spec-driven loop where the agent picks its own tasks and backs up every finished job with a signed receipt you can re-check.
CX Codex +1
★ 1,108repo stars
extension-development skill A skill for Nimbalyst extension work: build, install and hot-reload extensions from inside the running app through MCP tools.
CX Codex +1
★ 1,971repo stars
api-security-testing skill A skill that walks the agent through seven phases of API security work, from endpoint discovery to error handling. Useful when you need to probe an API for holes.
121installs
smtp-penetration-testing skill A Claude skill that walks the agent through SMTP checks: banner grabbing, user enumeration, open relay tests, credential brute force.
113installs
bdg skill A skill that hands your agent a CLI for a real Chrome: navigation, clicks, forms, network and console reads. Handy when you need to confirm a UI change in a running app.
CX Codex +1
★ 181repo stars
verify-counts skill This skill compares numeric claims in documentation against the real values and flags the outdated ones. Handy when a README still promises 14,000+ tests.
CX Codex +1
★ 242repo stars
check-coverage skill This skill inspects a CLI handler and its test file, spots the gaps and writes the missing cases. Handy when you add a command or audit old coverage.
CX Codex +1
★ 242repo stars
pict-test-designer skill Turns requirements or code into a PICT model, then hands back a table of test cases with expected results for each one.
CX Codex +1
★ 102repo stars
regression-proof skill This skill walks the agent through a bug fix: write a test that fails on the old behavior, apply the fix, then watch the same test pass.
CX Codex +1
★ 353repo stars
composition-design-review skill A design review layer for OrkasVideoStudio COMPOSE previews and drafts. It reads the whole frame index, then opens the cover and risky frames at full size before any preview is shown.
CX Codex +1
★ 327repo stars
tendril-review skill A skill that walks through all files touched by a big change, looking for dead code, duplication, leftover compatibility shims and test gaps.
CX Codex +1
★ 203repo stars
live-check skill Loads the working copy of a plugin into a live Claude session and shows how replies actually draw. Useful after any visual change.
CX Codex +1
★ 184repo stars
lint-tasks skill Reviews existing coder-eval task YAML and reports criteria that cannot fail, prompts that leak the answer, and near-duplicate tasks. Read-only.
CX Codex +1
★ 154repo stars
1,681–1,720 of 1,762
