testing-patterns
Jest testing patterns, factory functions, mocking strategies, and TDD workflow. Use when writing unit tests, creating test factories, or following TDD…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-28 00:17
Testing & quality
12,793 results
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing…
eval-suite-designer
Design a task-specific evaluation suite with clear failure modes, metrics, and decision criteria. Use when generic benchmarks are not enough.
failure-taxonomist
Cluster model failures into actionable categories such as retrieval miss, reasoning slip, calibration failure, or formatting brittleness. Use after running…
prompt-policy-ablator
Design controlled comparisons for prompts, routing, tools, and system policies. Use when a system changed and you need to know why performance moved.
train-test-split
Applies the "Training/Test Set Separation — AI's 'Scientific Method'" methodology distilled from AI for Everyone. Use when the user needs practical guidance, diagnosis, workflow design, decision support, or an action plan…
dash-discover
Diagnoses latent architectural modernization opportunities across Dart and Flutter packages (language idioms, testing hygiene, CLI patterns, doc rot) and…
record-verification
Record a reviewable end-to-end walkthrough of an agent's changed UI flow for human product and visual verification. Use only when the user explicitly asks for…
no-mistakes
Validate your code changes through the no-mistakes pipeline - automated code review, tests, lint, docs, push, PR, and CI - before they reach upstream. Use when…
duplicate-detection
Find copy-pasted code blocks and similar patterns using jscpd. Use when asked to find duplicate code, identify refactoring targets, or check if a utility…
ha-testing
Write tests for Home Assistant integrations using pytest and the hass fixture. Use when mentioning test, pytest, testing, test coverage, mock, fixture, or…
langsmith datasets
INVOKE THIS SKILL when creating evaluation datasets from trace OR uploading datasets to LangSmith OR querying datasets. Covers dataset types (final_response,…
playwright-cli
Playwright CLI browser automation — navigate, screenshot, fill forms, click. Use when automating browser tasks from the shell; 4-10x more token-efficient than…
dspy-evaluate
Run dspy.Evaluate to score DSPy programs against labeled examples using custom or built-in metrics. Use when you need to measure how well your DSPy program…
dspy-multi-chain-comparison
Use when you want higher accuracy by generating multiple reasoning chains and selecting the best answer — trading speed for quality on critical outputs. Common…
weekly-npm-dependency-audit
Run a weekly npm dependency audit for JavaScript or TypeScript projects. Use this when the user asks for an npm dependency audit, npm outdated package review,…
challenge
Stress-test the user's plan, decision, or idea by interrogating it hard — surfacing hidden assumptions, unexamined trade-offs, failure modes, and…
ljg-rank
Perform a "rank reduction" operation on any domain—start from phenomena, extract dimensions, discover constraints, find the irreducible independent generators (the rank), and confirm it with generative tests and runnable validation. Use when user says "降秩", "找秩", "这个领域的秩是什么", or wants to find the irreducible principles of any…
lov-fix-by-add-log
Add minimal diagnostic logging for hard-to-reproduce issues and use actual output to locate the root cause. Support explicit input and result readback. Use to debug a problem with targeted logging.
dotnet-stryker
Use the open-source free `Stryker.NET` mutation testing tool for .NET. Use when a repo needs to measure whether tests actually catch faults, especially in…
typescript-testing
TypeScript testing patterns with Vitest and MSW. Use when writing unit tests, mocking APIs, creating typed mocks for dependency injection, or using snapshot…
hses-packet-analysis
Analyze HSES protocol packet captures and generate a markdown report. USE WHEN: debugging moto-hses communication, interpreting HSES packet data, identifying…
playwright-reviewing
Review Playwright E2E tests for best practices violations. Detects mocked app data, explicit timeouts, CSS selectors, skipped tests, and assertion…
playwright-writing
Write reliable Playwright E2E tests following official best practices. Prioritizes user-facing locators, web-first assertions, and test isolation. NEVER mock…