Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Used to create, modify, or understand an RWX CI/CD config or any other file in a `.rwx` directory. Trigger when: the user asks about RWX; wants to create or modify an RWX config; says things like “CI failed”, “CI is red”, or “tests are failing in CI”; asks “what's failing on my PR / branch / commit?”; wants to run tests or build steps in a sandbox; wants to debug test failures, check a run status, fetch logs/artifacts, or start a run loop.
Documents edge cases, error states, boundary conditions, race conditions, and recovery paths for a feature - the systematic catalog of what can go wrong and the failure modes to design for. Use during specification to map the failure surface and ensure comprehensive coverage, or during QA planning to identify boundary and limit scenarios to test. Distinct from deliver-acceptance-criteria, which writes story-level Given/When/Then checks; this skill produces the whole-feature edge-case catalog.
Reviews LangGraph code for bugs, anti-patterns, and improvements. Use when reviewing code that uses StateGraph, nodes, edges, checkpointing, or other LangGraph features. Catches common mistakes in state management, graph structure, and async patterns.
Apex code quality guardrails for Salesforce development. Enforces bulk-safety rules (no SOQL/DML in loops), sharing model requirements, CRUD/FLS security, SOQL injection prevention, PNB test coverage (Positive / Negative / Bulk), and modern Apex idioms. Use this skill when reviewing or generating Apex classes, trigger handlers, batch jobs, or test classes to catch governor limit risks, security gaps, and quality issues before deployment.
Multi-path parallel product analysis with cross-model test-time compute scaling. Spawns parallel agents (Claude Code agent teams + Codex CLI) to explore product from multiple perspectives, then synthesizes findings into actionable optimization plans. Can invoke competitors-analysis for competitive benchmarking. Use when "product audit", "self-review", "发布前审查", "产品分析", "analyze our product", "UX audit", or "信息架构审计".
Babysits an open GitHub PR until merge-ready, first judging whether an old PR still belongs. Use when asked to watch a PR over time or update an old one — not for one-shot comment resolution or one CI failure. GitHub (incl. Enterprise) only
Use this skill to determine whether a Lightning Web Component (LWC) is accessible and meets WCAG accessibility guidelines. TRIGGER when the user asks \"is my component accessible?\", \"does my LWC meet accessibility guidelines?\", \"is this component WCAG compliant?\", \"find accessibility problems in this LWC\", \"is this LWC keyboard accessible?\", \"does this component work with a screen reader?\", \"does this component have sufficient color contrast?\", \"check ARIA usage in this LWC\", or \"WCAG 2.2 accessibility check\". Also TRIGGER when the user wants to fix or improve accessibility (a11y, WCAG, ARIA) in an LWC's HTML, JS, or CSS — semantic markup, focus, keyboard nav, contrast, screen-reader labels, WCAG 2.2 SC. Produces `a11y-review.md` with WCAG-cited findings. DO NOT TRIGGER for general LWC generation (use `experience-lwc-generate`) or SLDS visual/design review not focused on accessibility (use `design-systems-slds-validate`).
MSW (Mock Service Worker) best practices for API mocking in tests (formerly test-msw). This skill should be used when setting up MSW, writing request handlers, or mocking HTTP APIs. This skill does NOT cover general testing patterns (use test-vitest or test-tdd skills) or test methodology.
Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying server-client inference for ALOHA, or debugging normalization, LoRA merge, and cross-GPU issues.
Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines
Executes real end-to-end verification against a running application after specification implementation. Detects the application type, starts the local runtime (Docker, Node, Spring Boot, etc.), runs real tests (curl for REST APIs, Playwright for web SPAs, computer-use for desktop apps), verifies acceptance criteria from the functional specification, generates a markdown report, and tears down the environment. Use when: user asks to verify a completed spec with real tests, run e2e checks after implementation, validate acceptance criteria in a live environment, or test the feature for real after task completion.
Audit the developer experience of a product, SDK, docs site, or SKILL.md by dropping multiple Claude subagents at it with only a tiny task prompt and real tools (WebFetch, Bash, Write). Agents must discover the docs themselves, install deps, ask for credentials if needed, and attempt real execution. The skill captures each agent's trace — tool calls, retries, wall time, errors — and scores on Setup Friction, Speed, Efficiency, Error Recovery, and Doc Quality, then emits an HTML report with an A–F grade and concrete fixes. Use when the user asks to audit agent experience, test a skill, audit docs for agents, check if an SDK is agent-friendly, validate a SKILL.md, measure agent DX, or benchmark how painful onboarding is for an AI agent. Triggers: 'audit agent experience', 'test this skill', 'audit docs for agents', 'is my SDK agent-friendly', 'run a DX audit', 'agent experience test', 'test my docs', 'how do agents do with my product'.
Pre-ship gate — runs detector, verifies brief and tokens, applies the 10-pass finish bar, ranks findings by feedback hierarchy. Use when the user wants to ship, merge, or finalize a surface and needs a verdict (READY / NOT READY / BLOCKED) before committing. Invoke when the user asks for finalize on their UI, or mentions 'finalize' alongside design / UI / frontend work.
Check whether newly merged CLI features in te-cli are sound. Scans six dimensions — command registration, business domain ↔ skill pairing, skill documentation coverage, internal consistency of skills, user documentation sync, and engineering robustness — to find problems such as commands failing to load, AI agents reading empty docs and guessing parameters, or outdated user documentation. Use when a new command domain/command is merged, a skill is added or modified, a pre-release self-check is needed, or CLI feature completeness must be assessed.
When the user wants a comprehensive technical analysis of a codebase or project. Also use when the user mentions 'analyze this codebase,' 'technical overview,' 'document this architecture,' 'what does this codebase do,' 'summarize this repo,' 'code audit,' 'architecture review,' 'codebase walkthrough,' or 'analyze this project.' Performs a multi-phase analysis covering architecture, code quality, testing, and infrastructure, producing a detailed markdown report targeting engineers. For quick code searches or single-file reviews, see standard editor tools.
Closed-loop compare-adjust-repeat workflow for fitting Blender models to supplied front/side/back/top templates and originals. Use when the user asks to compare the product to templates/originals and adjust until it fits across all dimensions, or when all views must pass measurable bbox/centroid/silhouette/edge validation before export.
Watch an open PR — fix failing CI, handle straightforward review comments, and drive it to a mergeable state. Claude Code analog of Cursor's built-in /babysit. Use after opening a PR when the user wants the agent to shepherd it without re-prompting.
Run an extremely strict maintainability review focused on abstraction quality, oversized files, and growth of spaghetti conditions. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
Writes failing tests first for test-driven development and hands off a strict implementation contract that requires agents to make those tests pass without weakening the tests. Use when users ask for test-first workflows, RED/GREEN cycles, or behavior-gating tasks with automated tests.
Provides the complete, verified grep scan command library for auditing React codebases before a React 18.3.1 or React 19 upgrade. Use this skill whenever running a migration audit—for both the react18-auditor and react19-auditor agents. Contains every grep pattern needed to find deprecated APIs, removed APIs, unsafe lifecycle methods, batching vulnerabilities, test file issues, dependency conflicts, and React 19 specific removals. Always use this skill when writing audit scan commands—do not rely on memory for grep syntax, especially for the multi-line async setState patterns which require context flags.
Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.
Python software engineering guidelines from real PR review patterns. This skill should be used when writing, reviewing, or refactoring Python code — especially dataclasses, service interfaces, error handling, and type annotations. Triggers on tasks involving Python modules, API design, data modeling, type safety, exception handling, or refactoring for maintainability. For asyncio and concurrency guidance, see the python-async-best-practices skill.
Run a self-refinement loop when a Blender result is subpar, user expectations are not met, validation fails, or repeated issues reveal missing skill depth. The loop diagnoses the gap, decides whether to repair the artifact or acquire/refine a generic skill, sanitizes lessons for reusable publication, updates docs/versioning, validates, and prepares stage/commit/push when explicitly requested.
Validates security patches with reproducible baseline-versus-patched evidence, including original exploits, root-cause variants, behavior preservation, regressions, and newly introduced security failures. Use after a patch exists and before accepting, merging, or reporting it as fixed; also use when an AI-generated patch, remediation commit, pull request, or proposed upstream fix needs adversarial post-patch validation across any language.
Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and skills against benchmarks, or implementing automated agent evaluation loops.
Hands-off, diff-scoped browser QA of the active branch: maps user flows, drives a real browser, autonomously fixes small breakages with regression tests and commits, judges experience against product personas, and writes a durable dogfood report. Manual invocation only.
Use when writing, reviewing, or refactoring code for maintainability and readability. Triggers on code reviews, naming discussions, function design, error handling, and test writing. Based on Robert C. Martin's Clean Code handbook with modern corrections.
Use when the user asks to perform security audits, penetration testing, vulnerability scanning, OWASP Top 10 checks, or offensive security assessments. Covers static analysis, dependency scanning, secret detection, API security testing, and pen test report generation.
Compiler sanitizer skill for runtime bug detection in C/C++. Use when enabling and interpreting AddressSanitizer (ASan), UndefinedBehaviorSanitizer (UBSan), ThreadSanitizer (TSan), MemorySanitizer (MSan), or LeakSanitizer (LSan) with GCC or Clang. Activates on queries about sanitizer flags, sanitizer reports, ASAN_OPTIONS, memory errors, data races, undefined behaviour, uninitialised reads, or choosing which sanitizer to use for a given bug class.
Principle-engineering posture for production-grade code: reads the repo first, plans before code, matches conventions, pulls latest docs over training recall, and ships the simplest correct change that holds the bar — proper algorithms and data structures, idempotent writes, schema+queries+indexes as one artefact, typed errors, tests in the same diff. Substrate-agnostic; defers to peer skills on their lanes. Use for non-trivial planning, design, implementation, review, or refactoring; RCA and debugging; performance and optimization work; changes touching a database schema, security, infrastructure, or a public API; hardening inherited, vibe-coded, or LLM-generated code (dependency/CVE and migration audits); and over-engineering cleanup ("simplest solution," "YAGNI," "what can we delete").
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.