Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Audits built React and Next.js frontends for user-facing defects in code and rendered UI: state gaps, data loss, double submits, focus and keyboard failures, rollback gaps, stale async, accessibility markup, layout resilience, performance setup, typography, motion hazards, and microcopy. Returns file:line findings and a ship verdict. Use when asked to "review this PR for UX bugs", "audit this component", "check my UI", "is this accessible", "design QA this page", or "is this ready to ship". For product decisions use product-design; for agentic apps use ax-audit; for deep type or motion use typography-audit or ui-animation; for the wording of a string rather than whether it is missing or leaky, use copywriting.
Generate and run tests for Adobe App Builder actions and UI components. Scaffolds Jest unit tests, integration tests against deployed actions, contract tests for Adobe API interactions, and React component tests using Testing Library. Provides mock helpers for State, Files, Events SDKs, @adobe/aio-lib-* clients, ExC Shell context (@adobe/exc-app), and UIX Guest SDK (@adobe/uix-guest). Use this skill whenever the user mentions testing App Builder actions, writing unit tests for Runtime actions, creating integration tests, mocking Adobe SDKs, setting up test fixtures, running aio app test, or wants to verify action behavior before deployment. Also trigger when users mention Jest configuration for App Builder, test coverage, CI test setup, React component test, Testing Library, UI test, Provider wrapper, test my page, test my form, test my table, test my component, mock shell context, mock extension context, debug test failures, or fix Jest errors.
Use when setting up or running hooks with prek in any repository. prek is a Rust drop-in alternative to pre-commit for running Git hooks that check, format, lint, and validate code and repository files. Prefer it when speed, workspace mode, built-in hooks, shared toolchains, or native TOML configuration matter.
Use when establishing branching strategies, implementing Conventional Commits, creating or reviewing PRs, resolving PR review comments, merging PRs (including CI verification, auto-merge queues, and post-merge cleanup), managing PR review threads, merging PRs with signed commits, handling merge conflicts, verifying a merge didn't silently drop changes, syncing a long-diverged branch (e.g. master into integration), rebasing a long-lived branch onto a moved base or splitting one into several PRs, integrating Git with CI/CD, setting up git hooks (lefthook, captainhook, husky, pre-commit), debugging hook-install failures in git worktrees, or working in a bare-repo plus per-branch-worktree layout, including consolidating a directory that holds both a plain clone and a .bare. The pull-request tooling is GitHub-only; references/pull-request-workflow.md carries the GitLab equivalents. Not for creating releases (use github-release) or diagnosing BLOCKED/won't-merge PRs (use github-project).
Reviews UI/frontend code and tells you exactly why it "looks AI-generated" — then how to fix it. Use it when a React/Tailwind/HTML interface looks off, generic, or unfinished, when you want a design score before shipping, or when asked to make UI look more professional, polished, or "designed, not generated." Self-contained; based on the open-source StyleSeed design engine.
Systematic performance profiling for Node.js, Python, and Go applications. Identifies CPU, memory, and I/O bottlenecks, generates flamegraphs, analyzes bundle sizes, optimizes database queries, runs load tests with k6 and Artillery. Always measures before and after. Use when investigating a slow endpoint, planning a performance budget, or hunting a memory leak in production.
Platform specs and publish validation — per-platform requirements and the validate-before-publish step for multi-platform fan-out. Use when fanning a post out to multiple platforms, when a post is getting rejected, when mapping per-platform postType/required fields, or to run the validate-before-publish step. Encodes the per-platform postType enums, required-field matrices, and media rules from the OpenAPI spec, and runs POST /posts/validate so a post lands correctly on every target. Uses the CHECK framework. The keystone the per-platform format skills point to. WoopSocial validates + publishes atomically and has no update endpoint; the agent maps fields and fixes spec violations, but human-judgment calls (disclosure truthfulness, privacy intent) stay with the person; metrics never fabricated. Distinct from the per-platform format skills (one platform's content) and scheduling-and-queue (timing).
Embedded CAN / CAN-FD debugging tool for scanning interfaces, monitoring messages, sending test frames, logging, decoding database files and bus statistics. Automatically triggers when the user mentions CAN, CAN-FD, DBC decoding, bus packet capture, USB-CAN debugging, message sending, bus statistics, PCAN, Vector, slcan, CAN interface scanning, CAN ID filtering, ASC logs or BLF files; also supports explicit /can invocation. Even if the user only says "look at the CAN messages", "send a test frame" or "decode the DBC", this skill should trigger as long as the context clearly refers to CAN bus communication operations or issues.
Comprehensive toolkit for detecting and eliminating "AI slop" - generic, low-quality AI-generated patterns in natural language, code, and design. Use when reviewing or improving content quality, preventing generic AI patterns, cleaning up existing content, or enforcing quality standards in writing, code, or design work.
Parallel read-only multi-agent root-cause investigation for bugs, regressions, crashes, flaky behavior, or unexplained failures. Use when the user asks to investigate a bug, find the root cause, trace a regression, understand why something broke, or wants a ranked diagnosis with the fastest proof path without making code edits.
Calibrate an LLM judge against human labels using data splits, TPR/TNR, and bias correction. Use after writing a judge prompt (write-judge-prompt) when you need to verify alignment before trusting its outputs. Do NOT use for code-based evaluators (those are deterministic; test with standard unit tests).
Tests applications using the Pest 4 PHP framework. Activates when writing tests, creating unit or feature tests, adding assertions, testing Livewire components, browser testing, debugging test failures, working with datasets or mocking; or when the user mentions test, spec, TDD, expects, assertion, coverage, or needs to verify functionality works.
Invoke when dev-testing a Cyrus change that spans CYPACK (edgeworker + CLI) and CYHOST (the Vercel-hosted GUI) and the hosted GUI needs to point at an unreleased `cyrus-core` from this repo. Publishes `cyrus-core` (and `claude-runner` if needed) as a `-test.N` prerelease under the npm `test` dist-tag so CYHOST can install it via `cyrus-core@test` without affecting the `latest` dist-tag or shipping a real release.
Diagnoses and designs safe Terraform releases, provisioners (remote-exec/local-exec/file, cloud-init, Compose, Caddy), multi-environment isolation, and fresh-host bootstrap. Use when writing or reviewing plan/apply wrappers or provisioners; when staging/production config may differ; when a rollout can mutate a shared gateway; or when debugging drift, TLS, container restarts, DNS duplication, or snapshot contamination.
Use when the user is investigating QML / Qt Quick performance — both vague complaints ("the UI feels laggy", "this is slow", "frames are dropping", "the app stutters") and explicit asks to profile, find hotspots, or optimize bindings, signals, or rendering. Runs qmlprofiler on a 2D QML application, parses the .qtd trace, and analyzes hotspots against the source with frame-time, memory, and pixmap-cache summaries. Does NOT cover Qt Quick 3D.
Technical debt inventory, prioritization, and audit for PHP/Laravel (MySQL) and Node/TypeScript/React projects. Use when assessing code health, identifying refactoring candidates, planning debt paydown, or auditing a codebase for accumulated debt. Triggers on "audit technical debt", "find tech debt", "debt inventory", "what should we refactor first", or tasks involving code health, security debt, performance debt, data debt, observability debt, debt prioritization, or remediation planning.
WordPress performance optimization guidelines for plugin, theme, and custom code development. This skill should be used when writing, reviewing, or refactoring WordPress PHP code to ensure optimal performance patterns. Triggers on tasks involving WP_Query, database queries, caching, hooks, REST API, or WordPress theme/plugin development.
You MUST use this when an implementation plan or a finished implementation needs an independent review by other agent CLIs - by default the opposite CLI (Codex for work done in Claude Code, Claude Code for work done in Codex) together with Antigravity (Gemini) - whether the user asks for a cross-review or a second opinion from the other agent, or plan-crafting, inline-plan-dev, or subagent-plan-dev reach their cross-review step. Same-host implementation review belongs to review-request and deciding on findings to review-resolution; spec review and per-task review are outside this skill.
Use this skill when working with the UI5 Linter (@ui5/linter) for static code analysis of SAPUI5/OpenUI5 applications and libraries. Covers setup, configuring linting rules, running the linter to detect deprecated APIs, global variable usage, CSP violations, and manifest issues. Supports autofix for deprecated API usage, global references, event handlers, and manifest properties. Includes CI/CD integration, pre-commit hooks, and UI5 2.x migration preparation.
Create diverse synthetic test inputs for LLM pipeline evaluation using dimension-based tuple generation. Use when bootstrapping an eval dataset, when real user data is sparse, or when stress-testing specific failure hypotheses. Do not use when you already have 100+ representative real traces (use stratified sampling instead), or when the task is collecting production logs.
Drive Chrome via the DevTools Protocol from JavaScript. Run JS snippets through the `browser-harness-js` CLI — it auto-spawns a long-lived bun HTTP server holding a fully-typed CDP `Session`, and every call (`browser-harness-js 'await session.Page.navigate(...)'`) executes against the same persistent connection. Session, active target, and globals survive across calls. Use when the user wants to automate, script, or inspect a Chrome browser via CDP — single tab or multi-tab, attach to existing Chrome or to a new one launched with --remote-debugging-port.
Test C# MCP servers at multiple levels: unit tests for individual tools and integration tests using the MCP client SDK. USE FOR: unit testing MCP tool methods, integration testing with in-memory MCP client/server, end-to-end testing via MCP protocol, testing HTTP MCP servers with WebApplicationFactory, mocking dependencies in tool tests, creating evaluations for MCP servers, writing eval questions, measuring tool quality. DO NOT USE FOR: testing MCP clients (this is server testing only), load or performance testing, testing non-.NET MCP servers.
Valgrind profiler skill for memory error detection and cache profiling. Use when running Memcheck to find heap corruption, use-after-free, memory leaks, or uninitialised reads; or Cachegrind/Callgrind for cache simulation and function-level profiling. Activates on queries about valgrind, memcheck, heap leaks, use-after-free without sanitizers, cachegrind, callgrind, KCachegrind, or massif memory profiling
Debug applications with motel, a local OpenTelemetry ingest and query server. Use when the user wants runtime-evidence debugging with traces or logs, wants temporary debug instrumentation that can be removed later, or needs a repo wired to send OTLP/HTTP telemetry to a local motel server. If the target repo uses Effect or @effect/*, also read references/effect.md.
Audits an existing pm-skills skill against structural conventions and quality criteria. Produces a structured validation report with pass/fail checks, severity-graded findings, and actionable recommendations. Use when checking whether a skill meets repo standards before shipping or after making changes.
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or have explicit authorization to test.
Install Fandhe-AI organization-standard CI guards in the target repository (introduce ai-review / AGENTS.md review criteria / required-check aggregation job / branch protection ruleset and additional guards). Use for requests such as “add repository guards,” “introduce CI guards,” “set up branch protection,” “introduce ai-review,” or “maintain AGENTS.md.” Supports bulk application to multiple repositories. For initial setup of the .claude/ system, see init-claude; to expand an existing system, see update-claude.
Create and edit React Native Storybook stories using Component Story Format (CSF). Use when writing .stories.tsx files, adding stories to React Native components, configuring Storybook addons (controls, actions, backgrounds, notes), setting up argTypes, decorators, parameters, or working with portable stories for testing. Applies to any task involving @storybook/react-native story authoring.
Critiques an implementation plan—or a wayfinder map/ticket—from multiple angles (security, simplicity, edge cases, scope creep, codebase conflicts, tech-specific best practices) via parallel critic subagents. Trigger: user says “kritisiere den plan,” “plan check,” “plan-kritik,” “blinde flecken,” or “/plan-critics”—also invoke when a planning agent wants to validate its own plan before presenting it, or a wayfinder session wants a resolution checked before closing a ticket. Must be called at top level (not inside a subagent)—it uses the Task tool.
Interactive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, file issues conversationally, or mentions "QA session".
Provides comprehensive code review guidance for React 19, Vue 3, Angular 17+, Svelte 5, Rust, TypeScript, Java, PHP, Python, Django, Go, C#/.NET, Kotlin, NestJS, C/C++, and more. Helps catch bugs, improve code quality, and give constructive feedback. Use when: reviewing pull requests, conducting PR reviews, code review, reviewing code changes, establishing review standards, mentoring developers, architecture reviews, security audits, checking code quality, finding bugs, giving feedback on code.
Generates Postman collection JSON files from Express, Next.js, Fastify, Hono, or other API routes. Scans route definitions, extracts endpoints, methods, params, and creates importable collections. Use when users request "generate postman collection", "export to postman", "create postman file", or "postman import".
Production-grade Playwright testing toolkit. Use when the user mentions Playwright tests, end-to-end testing, browser automation, fixing flaky tests, test migration, CI/CD testing, or test suites. Generate tests, fix flaky failures, migrate from Cypress/Selenium, sync with TestRail, run on BrowserStack. 55 templates, 3 agents, smart reporting.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.