conversion-rate-optimization
Audit a landing page or funnel step and produce a prioritised CRO test plan. Use when asked to improve conversion rate, audit a landing/signup/checkout page,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-26 00:15
Testing & quality
12,697 results
quiz-generator
Generate a quiz or test on any topic with a balanced mix of question types and difficulty, plus a complete answer key with explanations. Use when asked to…
playwright
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging)…
ideate
Generates, stress-tests, and iteratively evolves ideas for a stated problem — product concepts, features, solution options, strategies — using…
github-code-review
Comprehensive GitHub code review with AI-powered swarm coordination
browser-workflow-to-playwright
Translates browser workflow markdown files into Playwright E2E tests for CI. Use this when the user says "convert workflows to playwright", "translate…
ios-workflow-to-playwright
Translates iOS workflow markdown files into Playwright E2E tests for CI using WebKit with mobile viewport. Use this when the user says "convert ios workflows…
thermo-nuclear-code-quality-review
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use when the user explicitly asks for a…
ai-dev-team
The AI Dev Team contract — how work is run in any project using this framework: proportional process, TDD, behaviour-only tickets, which process skills exist…
ollygarden-otel-collector-config-validation
Behaviorally validate an OpenTelemetry Collector processor or connector against realistic telemetry. Use for "does my filter drop the right spans?", "prove…
cmd-chain-halt-code-reviewer
Review protocol code for chain halt risks, non-determinism, and onchain behavior bugs
physicalai-train-benchmarking-a-policy
Benchmarks a trained Physical AI Studio policy in a simulation gym and reports success metrics. Use when running physicalai benchmark, editing configs under…
create-verification-skill
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for…
maintain-verification-skill
Keep a project's verification skill and product/agent access maps aligned with current source and real evidence. Use for /maintain-verification-skill, auditing…
review-storybook
Review Paperclip stories for a feature or change using the Storybook catalog, production source, and existing browser tests. Report component, mock,…
test-audit
Garden the test suite by finding and removing redundant, vacuous, or implementation-coupled tests while preserving useful regression coverage. Use for test…
assistant-ui
Guide for assistant-ui library - AI chat UI components. Use when asking about architecture, debugging, or understanding the codebase.
swift-testing
Test Swift applications - XCTest, Swift Testing, UI tests, mocking, TDD, CI/CD
linkedin-post-creator
LinkedIn professional content creation tool, generates high-quality LinkedIn posts based on topic and audience, optimizes professional expression and engagement rate
quality-posters
Generate quality posters across 31 distinct visual styles using GPT Image 2 (via Fal). Auto-picks the right style from the user's brief, builds a templated…
test-and-break
Autonomous testing skill that opens a deployed app, goes through user flows, tries to break things, and writes detailed bug reports. Use after deploying to…
quality
Construct, assess, and improve a repository's quality project graph and four-score quality index. Use only when the user explicitly invokes /quality or asks…
integration-test-grill
Use when planning integration coverage for a product flow and choosing whether each scenario belongs in a browser or component test.
ab-test-setup
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this…