eslint-custom
Use when custom ESLint rules and plugins including rule development, AST traversal, and publishing.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-23 00:13
Testing & quality
12,539 results
expo-dev-loop
Verify Expo and React Native changes in a running app with agent-device. Use after editing screens, navigation, interactions, app configuration, config…
adjudicate-regression
Use when deciding whether source and live reproduction evidence establish a new regression or an exclusion.
hunt-regressions
Use when discovering possible regressions from a pinned change and its callers before reproduction.
prepare-regression
Use when pinning before/after sources and collecting PR or commit context for a regression investigation.
report-regressions
Use when assembling or refreshing an evidence-linked regression report from saved campaign decisions.
reproduce-regression
Use when deploying before/after systems and building a live-system PoC for a regression candidate.
wstg-web-pentest
Full WSTG-aligned web application pentest — 12-phase methodology from information gathering through reporting, with concrete commands, expected outputs,…
nextjs-reproduce-issue
Reproduce and validate a reported Next.js issue using real code and runtime evidence. Use when investigating whether a vercel/next.js bug report is…
assumption-testing
Identify, document, and explicitly test assumptions rather than leaving them implicit and untested
test-orchestrator
Orchestrate and coordinate different test types in proper order
prd-auto-test-loop
PRD-driven automated test orchestration skill. Used to standardize and implement the test plan, AI self-testing and self-repair, and test reports for each PRD version; applicable to scenarios of splitting Unit/Integration/E2E by acceptance criteria, delineating the boundary between automation and manual testing, and generating versioned TEST_PLAN/TEST_REPORT.
quality-assurance-auditor
Perform the final submission-level audit of mathematical-modeling workflow integrity, evidence quality, anti-fabrication, paper coherence, figures, references,…
web-tooling-storybook
Storybook patterns - CSF 3.0, args, controls, autodocs, play functions, interaction testing, visual testing, addons configuration
named-persona-adversarial-review
Code review through the lens of real engineers' documented philosophies (Torvalds, Thompson, Carmack, Kent Beck, Jobs, Cagan). Complements abstract-role…
litestar-testing
Test Litestar applications with TestClient, AsyncTestClient, create_test_client, websocket test helpers, dependency overrides, mocked dependencies,…
npu-op-benchmark
Ascend NPU single-operator performance benchmark Skill; the current version only performs existing environment checks, CANN version identification, and executes the benchmark after user confirmation. It is not responsible for repairing or installing the environment.
mole-debug
Systematic debugging through methodical hypothesis-driven investigation. The mole follows vibrations to their source. Use when something is broken and nobody…
jb-browser-testing
Use for JB browser debugging and testing: prefer Vercel's agent-browser, but use jb-chrome-mcp when requested or as its fallback; avoid Playwriter and…
tdd
This skill should be used when a task explicitly asks for TDD, test-first development, or the Red-Green-Refactor cycle. It guides incremental implementation…
pytest-best-practices
Expert guidance for writing high-quality pytest tests. Use when writing tests, setting up fixtures, parametrizing, mocking, or reviewing test code.
smoke-test
Smoke testing patterns for verifying backend implementations end-to-end. Covers build verification, service health checks, authentication flows, test data…
module-registry
Load when working with the module registry in workerd — reading, modifying, debugging, or reviewing module resolution, compilation, evaluation, or registration…
pyqt-testing
Use when testing PyQt/PySide6 applications with pytest-qt - qtbot fixture, signal/wait patterns, mouse/keyboard simulation, dialog testing, model/view testing,…