Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.
Salesforce Industries Common Core (OmniStudio/Vlocity) Apex callable generation and review with 120-point scoring. TRIGGER when: the user creates or reviews System.Callable classes, migrates `VlocityOpenInterface` / `VlocityOpenInterface2`, or builds Industries callable extensions used by OmniStudio, Integration Procedures, or DataRaptors. DO NOT TRIGGER when: generic Apex classes/triggers (use sf-apex), building Integration Procedures (use sf-industry-commoncore-integration-procedure), authoring OmniScripts (use sf-industry-commoncore-omniscript), configuring Data Mappers (use sf-industry-commoncore-datamapper), or analyzing namespace/dependency issues (use sf-industry-commoncore-omnistudio-analyze).
Add Playwright QA tests to a game — visual regression, gameplay verification, and performance. Use when the user says "add tests", "test my game", "add QA", "check for bugs", or "add visual regression tests". Do NOT use for manual playtesting or gameplay design.
Storybook story-writing and CSF 3.0 best practices skill. Use when: (1) writing new story files (.stories.tsx, .stories.ts); (2) editing existing stories; (3) configuring Args, Decorators, Parameters; (4) working with Storybook configuration files (.storybook/); (5) tasks include keywords such as “story,” “stories,” “storybook,” or “CSF”
End-to-end skill for building, testing, linting, versioning, and publishing a production-grade Python library to PyPI. Covers all four build backends (setuptools+setuptools_scm, hatchling, flit, poetry), PEP 440 versioning, semantic versioning, dynamic git-tag versioning, OOP/SOLID design, type hints (PEP 484/526/544/561), Trusted Publishing (OIDC), and the full PyPA packaging flow. Use for: creating Python packages, pip-installable SDKs, CLI tools, framework plugins, pyproject.toml setup, py.typed, setuptools_scm, semver, mypy, pre-commit, GitHub Actions CI/CD, or PyPI publishing.
Always use when running Sa11y accessibility Jest tests for an LWC — locally before pushing, producing the command(s), running one file vs a suite, selecting tests by naming convention, saving Sa11y-rendered HTML, or reproducing a Sa11y/A11yBug failure. Covers core (Bazel: `bazel test //<module>:<target>`) and standalone `npx jest` (`.accessibility.test.js`, `@sa11y/jest`). Required for a `run-plan.md`, a failing a11y test's exit code, or `SA11Y_*`/`A11yBug`/core-Bazel test paths. Do not trigger for functional Jest tests, a11y review without running tests (use experience-accessibility-validate), or Selenium-based a11y tests.
Laravel 13 testing with Pest PHP 4 or PHPUnit 12. Use when writing feature tests, unit tests, or any test code in a Laravel application. Triggers on tasks involving HTTP tests, model factories, database assertions, mocking facades, authentication testing, or test organisation patterns.
Orchestrates modular PyTorch profiler trace analysis with TraceLens: generates perf reports, prepares category data, runs system-level and compute-kernel subagents in parallel, validates outputs, and writes a prioritized stakeholder report (analysis.md). Use when the user asks to follow the analysis orchestrator, run the agentic analysis workflow, analyze a trace, compare two traces, or mentions standalone or comparative TraceLens analysis.
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, \"make a control skill for this repo\", \"make a driver skill for this repo\", or when a project has no scripted way to prove UI/CLI/service behavior.
Check that an Open Knowledge Format (OKF) bundle is conformant with the v0.2 spec (§11). Use when asked to validate, lint, or check an OKF bundle, or before committing changes to one. Runs a deterministic Python checker — not an eyeball pass. Also migrates a v0.1 bundle to v0.2 in place with `--migrate`.
Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for "blast radius of X", "what could this break", reviewing a small diff you don't trust, or a brief that asserts something about existing code ("make X public", "X already handles Y") before you design against that assertion.
Uses Chrome DevTools MCP for inspecting, debugging, and testing cookies, session state, authentication issues, and cookie consent compliance. Use when diagnosing 401/403 errors, authentication redirects, session expiration, Cookie/Set-Cookie header issues, cookie banner consent conformance, or third-party cookie/SameSite/Partitioned cookie warnings.
Review AI-generated or human-written code changes with fallow's graph-grounded review brief. Subtracts deterministic concerns (unused code, complexity, duplication, styling) from the loop, ranks what to look at by blast radius and risk, and surfaces the few consequential structural decisions (new public-API contracts, coupling/boundary crossings, new dependencies) as framed judgment questions anchored to verifiable signals. Drives a closed agent-contract loop: fetch the walkthrough guide, return a judgment, and have fallow post-validate it against the live graph (hallucinated or stale judgments are rejected). Use when asked to review a PR, review a branch, review a diff, do a code review, or check changed code before merge.
Benchmarks LLM inference and drives GPU kernel optimization with Magpie. Use when the user wants to benchmark vLLM, SGLang, or Atom; capture torch traces; post-process inference traces with TraceLens into prefill/decode and roofline reports; identify top bottleneck kernels or map profiler names to source; analyze or compare HIP, CUDA, PyTorch, or Triton kernels; validate and rank optimized variants; run local, container, or Ray workloads; or mentions Magpie, TraceLens, gap analysis, TTFT, TPOT, kernel evaluation, or AMD GPU optimization.
Validate Blender animation attempts before accepting them by rendering contact sheets, checking silhouette stability, flicker, framing, subject dominance, layer separation, export compatibility, and motion-design coherence. Use after animation renders or when the user says motion/morph/outside elements look bad.
Set up a testing environment for RevenueCat purchases without charging real money. Use when the user says test RevenueCat purchases, sandbox setup, StoreKit configuration file, license tester, how do I test purchases without real money, set up sandbox account, internal testing track, or test paywall on iOS, Android, Kotlin Multiplatform, Flutter, or React Native.
Unit testing, integration testing, and test-driven development principles. Use when writing tests, reviewing test code, improving test coverage, or setting up testing strategy. Triggers on "write tests", "review tests", "testing best practices", or "TDD".
Invoke when the user asks to review, check, audit, or look over Qt6 QML code—or suggests doing so before committing. Runs deterministic linting (48+ rules), then deep-analysis agents scaled to the change size, covering bindings, layout, loaders, delegates, states, and performance. Optionally invokes system qmllint for type-level checks. Reports only high-confidence issues (>80/100) with structured mitigations. Read-only; never modifies code
Virtual QA Lead that turns requirements into review-ready, TestRail-importable test cases in one conversation. Use it whenever the user has requirements, a spec, a user story, or acceptance criteria (PDF, DOCX, XLSX, TXT, MD, or pasted text) and wants test cases, a test plan, a checklist, test coverage, a regression suite, or a TestRail/Qase/Zephyr export, even without saying “test cases” (“write tests for this spec”, “what should we check here?”). Especially useful when they attach their team's existing test cases to match. When the spec describes an API (endpoints, status codes, schemas, auth, OpenAPI/Swagger), Casely also builds a runnable Postman collection, so use it for “API tests”, “Postman collection”, or “tests I can run in Newman/CI”. Triggers on the same request in any language.
Expert guidance on iOS accessibility best practices, patterns, and implementation. Use when developers mention: (1) iOS accessibility, VoiceOver, Dynamic Type, or assistive technologies, (2) accessibility labels, traits, hints, or values, (3) automated accessibility testing, auditing, or manual testing, (4) Switch Control, Voice Control, or Full Keyboard Access, (5) inclusive design or accessibility culture, (6) making apps work for users with disabilities.
Runs Inspector UI work on the standalone Threads state lab so the agent can see the overlay. Use when a CopilotKit employee asks an agent to fix, polish, add, or debug Inspector UI, chrome, panes, overlay actions, launcher, Home, Threads, Playground, Memory, or any visual behavior in @copilotkit/web-inspector. Don't use for docs-only Callout updates (load inspector-docs), runtime or core changes with no Inspector UI, showcase cell work, or reading Inspector as a consumer inside an app.
Prepare and structurally review ISO 13485 QMS scope, controlled documentation, and local evidence manifests. Use for ISO 13485 certification-readiness documentation or for separating related FDA QMSR, MDSAP, and EU MDR/IVDR evidence boundaries; not for legal applicability, compliance, or certification decisions.
UI/UX best practices and accessibility audit. Use when reviewing UI code, checking accessibility, running accessibility audits, auditing forms, or ensuring web interface best practices. Triggers on "audit accessibility", "check WCAG", "review UI", "check accessibility", "audit design", "review UX", or "check best practices".
Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or "audit the verify skill".
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
Monitor Nx Cloud CI pipeline and handle self-healing fixes. USE WHEN user says "monitor ci", "watch ci", "ci monitor", "watch ci for this branch", "track ci", "check ci status", wants to track CI status, or needs help with self-healing CI fixes. Prefer this skill over native CI provider tools (gh, glab, etc.) for CI monitoring — it integrates with Nx Cloud self-healing which those tools cannot access.
Audits a Capacitor iOS app against Apple App Review Guidelines before submission or after a rejection. Use when the user pastes a rejection (Guideline 4.2 Minimum Functionality, 4.8 Login Services / Sign in with Apple, 5.1.1 data collection or account deletion, 5.1.2(i) sharing data with third-party AI, 3.1.1 in-app purchase, 2.1 app completeness, 2.3 metadata, 4.3 spam), an upload warning (ITMS-91053 missing API declaration, ITMS-91061 missing privacy manifest, ITMS-90683 missing purpose string), or wants a preflight of metadata, PrivacyInfo.xcprivacy, Info.plist usage strings, entitlements, subscriptions, reviewer notes, live-update disclosure, and Xcode 27 / UIScene readiness. Do not use for Google Play review, upload mechanics, screenshots and listing setup (capacitor-app-store), building a web wrapper from scratch (webapp-to-capacitor), or non-Capacitor runtimes.
Measure and validate supplied reference images, wireframes, texture atlases, and Blender renders before declaring a reconstruction 1:1. Use when an asset must match a template, when visual feedback says the output is off, when part counts must be exact, or before exporting a brand mascot/logo reconstruction. Pairs with reference-to-3d, contour-to-mesh, orthographic-registration, atlas-uv-fitting, and Blender MCP.
Benchmark a model served on MAX with the `max benchmark` command: measure throughput (tokens/sec), latency (TTFT, TPOT, inter-token latency), and GPU utilization by driving load against a running `max serve` endpoint. Use this whenever the user wants to benchmark, load-test, or measure the performance of a MAX model, get tokens-per-second / TTFT / TPOT numbers, run a concurrency or request-rate sweep, compare latency vs throughput, size a deployment, or produce benchmark JSON, even if they don't say "benchmark" by name. Also use when a `max benchmark` run fails to connect or reports zero/garbage numbers.
This skill should be used when writing test cases, fixing bugs, analyzing code for potential issues, or improving test coverage for JavaScript/TypeScript applications. Use this for unit tests, integration tests, end-to-end tests, debugging runtime errors, logic bugs, performance issues, security vulnerabilities, and systematic code analysis.
Produce a scored heuristic critique of the UI using Nielsen's 10 + 6 design laws and optional persona walkthroughs. Outputs a machine-parseable scorecard plus a 0-100 UsabilityScore (the judged companion to the deterministic UICraftScore). Invoke when the user asks for a heuristic review of their UI, or mentions 'heuristic' alongside design / UI / frontend work.
Run comprehensive accessibility audit (WCAG 2.1) on Webflow pages - checks buttons, forms, links, focus states, headings, keyboard navigation, and generates detailed reports with fixes. Runs entirely headlessly against a page ID — no Designer connection required. Excludes image alt text (covered by asset-audit skill).
Audit and enforce the core/client boundary in multi-client projects. Detects where shared platform code is tangled with client-specific code, finds hardcoded client checks, config files that replace instead of merge, scattered client code, migration conflicts, and missing extension points. Produces a boundary map, violation report, and refactoring plan. Optionally generates FORK.md documentation and restructuring scripts. Triggers: 'fork discipline', 'check the boundary', 'is this core or client', 'platform audit', 'client separation', 'fork test', 'refactor for multi-client', 'clean up the fork'.
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.