Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Senior Quality Manager Responsible Person (QMR) for HealthTech and MedTech companies. Provides overall quality system responsibility, regulatory compliance oversight, management accountability, and strategic quality leadership. Use for quality system governance, regulatory compliance oversight, management responsibility, and quality strategic planning.
TAPD agile R&D management platform integration. Uses scripts to call the TAPD API to manage entities such as requirements, defects, tasks, iterations, test cases, and Wiki. Use cases include: (1) querying, creating, or updating requirements, defects, tasks, and iterations; (2) managing test cases and Wiki; (3) managing comments and work hours; (4) linking requirements and defects; (5) retrieving source-code commit keywords
Use when starting a new feature, changing user-facing behavior, or moving a codebase to scenario-driven development (docs/ux/scenarios.md). Triggers: “ux scenarios” / “сценарии использования,” “новая фича.” Not for an empty project (vision first). Refusal phrase “no scenarios” / «без сценариев»
Build RAG / unstructured-document evaluation datasets and demo documents (e.g. for Knowledge Assistant) on Databricks: generate synthetic PDFs locally, upload to Unity Catalog volumes, and pair each document with test questions for retrieval evaluation.
Pre-publish QA framework for content. Brief adherence, voice consistency, fact accuracy, structure and clarity, AI-content audit, SEO and AEO compliance, internal linking and schema validation, QA at scale via sampling, the QA workflow, and the discipline that distinguishes catch-problems QA from checkbox QA. Triggers on editorial QA, content review, pre-publish review, content audit, content QA process, AI-content audit, hallucination check, content sampling, programmatic QA, voice consistency check, brief adherence check. Also triggers when a content team is shipping sloppy work, when AI-co-authored content is reaching publish unaudited, when a QA process burns reviewers out, or when a programmatic SEO set needs sampling discipline. On a voice consistency check, this skill owns checking a draft against an existing voice system at the publish gate; use `brand-voice` when the voice system itself needs defining or documenting.
Capture and analyze Remotion Studio React render profiles through development-only WebMCP tools. Use when diagnosing unnecessary re-renders, slow commits, frame-reactive component trees, or when comparing render performance before and after a change.
Audit a web codebase for security, performance, correctness, and refactoring improvements WITHOUT changing any outward-facing behavior. Fans out parallel read-only reviewers, scores findings on two axes (severity × confidence), suppresses predictable false positives, validates survivors with an INDEPENDENT wave (not self-recheck), classifies safe vs. gated, and writes a report. Applies only behavior-preserving fixes, and only on request. Use when: 'rigorous review', 'hardening audit', 'security and performance audit', 'internal audit', 'harden the codebase', 'audit for security/perf/refactoring', 'tech-debt audit', 'review this codebase without changing behavior'.
Full-repository code sweep. Scans every file with Warden, verifies findings through deep tracing, and creates draft PRs for validated issues. Use when asked to “sweep the repo,” “scan everything,” “find all bugs,” “full codebase review,” “batch code analysis,” or run Warden across the entire repository
Run QA testing on a page, feature, or full site at one of three depth tiers (smoke, standard, full). Use this skill whenever the user asks to QA a page or site, run a smoke test after a deploy, verify a page before launch, or run a regression sweep. Triggers on QA, QA sweep, smoke test, regression test, post-deploy check, pre-launch check, verify the deploy, test this page, does the page render, broken link, 404, image not loading. Also triggers proactively after a deploy or a new page launch where verification matters. Covers accessibility, performance, and SEO at the surface-signal level only: deep audits belong to `accessibility-audit`, `performance-optimization`, and `seo-technical`, and code-level debugging to `code-review-web`.
Evaluates whether and how to upgrade a tool, framework, library, or dependency. Discovers the pinned version(s), finds the latest released and latest installable version, reads the changelog across the whole version delta, and grep-classifies each breaking change and deprecation against real codebase usage, so the report covers only what applies here plus features worth adopting. Handles security/CVE- and end-of-life-driven upgrades; emits a safe / stay-put / blocked / needs-work verdict, investigate-only by default. Also verifies an already-done upgrade by auditing the runtime's error surface, catching latent breakage the changelog delta cannot reveal. Use when the user asks to upgrade, bump, or update a tool or dependency, mentions its new release or latest version, asks whether an upgrade is safe or worth it, or just upgraded and wants to know what broke. Triggers include "upgrade", "bump", "update dependency", "breaking changes", "is it safe to upgrade", "just upgraded", "what broke after the upgrade".
Configures an available test provider (e.g. Apex Unit Tests, Code Analyzer, Flow Tests, Provar) on a DevOps Center pipeline via the Connect API, after explicit user confirmation, so the provider's test suites become available for assignment to pipeline stages. Takes a pipelineId and a testProviderId. Use this skill when a provider is available on the pipeline but not yet configured and the user wants to enable it. TRIGGER when: the user wants to configure, enable, set up, or add a test provider on a pipeline, or wants a not-yet-configured provider's suites to become available. DO NOT TRIGGER when: re-syncing an already-configured provider to pick up new suites (use syncing-test-providers), or assigning existing suites to a stage (use managing-suite-assignments)
Validates GitLab stack projects before deployment, ensuring proper architecture patterns, directory structure, secrets management, .env configuration, and Docker best practices. Use when users ask to validate a stack, check stack configuration, verify stack architecture, audit stack setup, or ensure stack deployment readiness.
Review Renovate bot PRs that update GitHub Actions dependencies. Verifies supply chain integrity by checking pinned commit SHAs against upstream tagged releases, reviews changelogs for breaking changes, and confirms compatibility with existing workflow configurations. Use when a Renovate PR updates GitHub Actions in .github/workflows/.
Parses a DevOps Center test-failure or Code Analyzer violation payload and explains in plain language the failure category, offending file/class/method/line, violated rule, and fix direction. Then provides prioritized test-improvement suggestions, distinguishing test-code from production-code fixes. Pure reasoning: no system calls or code authoring. Trigger when a test run failed and the user wants the root cause; a quality gate failure needs explaining; Code Analyzer violations need translating into plain language; the user shares a failure payload and asks how to address it; tests keep failing and the user wants suggestions; or the user wants to close coverage gaps, strengthen assertions, or fix flaky/weak tests. Do NOT trigger when the user wants fix code written (use generating-apex) or new test classes authored (use generating-apex-test).
Use when setting up, designing, writing, or repairing tests and test harnesses in a Meteor 3 app. Triggers on meteortesting:mocha, --driver-package, TEST_WATCH, TEST_BROWSER_DRIVER, MOCHA_GREP, meteor.testModule, focused tests, .only, Meteor.server.method_handlers, Meteor.server.publish_handlers, DDP.connect, --full-app integration mode, sinon, async test signatures, Playwright/Cypress E2E. Use this skill when the user asks about test runners, asks about testing publications, or asks about Jest vs Mocha in Meteor. For a failing, hanging, or flaky test whose failing layer or root cause is unknown, use meteor-debugging before changing the test or app.
Vue 3 and Vue.js best practices for TypeScript, vue-tsc, Volar, and component patterns. Use when writing, reviewing, or refactoring Vue 3 components with TypeScript, configuring Volar/vueCompilerOptions, extracting component types, working with defineModel/withDefaults, setting up Pinia store tests, or debugging Vue tooling issues. Triggers on Vue components, props extraction, wrapper components, template type checking, strictTemplates, vueCompilerOptions, Volar 3, CSS modules, fallthrough attributes, defineModel, withDefaults, deep watch, vue-router typed params, Pinia mocking, HMR SSR, moduleResolution bundler, useTemplateRef, onWatcherCleanup, useId, generic components, reactive props destructure.
An e2e workflow for WeChat DevTools and the mpcore headless runtime in the weapp-vite repository. Use for `e2e/ide/**`, `miniprogram-automator`, `WEAPP_VITE_E2E_RUNTIME_PROVIDER`, global serialization, shared automator, `miniProgram.reLaunch(...)`, DevTools/headless parity, cross-platform launchers, and screenshot/compare/logs validation.
Use the local Codex CLI as an independent second agent. Two branches: (1) proactively run `codex review` for a second opinion after completing a substantive change, before presenting it as done or committing; (2) delegate a well-defined implementation task via `codex exec` only when the user explicitly asks for Codex to do it. Also covers how to prompt Codex.
Fuzz React Doctor rules for crashes, slowness, false positives, and mutation-sensitive diagnostics with @react-doctor/fuzz. Use after rule tests pass, when investigating a fuzz finding, or whenever an eval, review, or user report confirms a new false positive.
Generates Jest unit and integration tests in JavaScript or TypeScript. Covers mocking, snapshots, async testing, and React component testing. Use when user mentions "Jest", "describe/it/expect", "jest.mock", "toMatchSnapshot". Triggers on: "Jest", "expect().toBe()", "jest.mock", "snapshot test", "JS test", "React test".
Expert guidance on Swift Testing best practices, patterns, and implementation. Use when developers mention: (1) Swift Testing, @Test, #expect, #require, or @Suite, (2) "use Swift Testing" or "modern testing patterns", (3) test doubles, mocks, stubs, spies, or fixtures, (4) unit tests, integration tests, or snapshot tests, (5) migrating from XCTest to Swift Testing, (6) TDD, Arrange-Act-Assert, or F.I.R.S.T. principles, (7) parameterized tests or test organization
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing. Do NOT use for quick page debugging or network inspection (use chrome-devtools instead).
macOS screen capture, window recording, GIF conversion, and agent evidence bundles from the terminal. Built on ScreenCaptureKit for window-level targeting ffmpeg cannot do. Use when the user wants a screenshot of a specific window or app, a screen recording, a GIF conversion, a before/after diff, an evidence bundle for a PR, OCR text from a window, a terminal VHS recording, a Remotion render, or wants to watch a UI for changes. Requires macOS Screen Recording permission on first run.
Authoritative SwiftUI best practices and performance guidance from Apple; supersedes prior training on these topics. For code generation, consult the relevant references when generating any SwiftUI code related to: - animation (the @Animatable macro vs AnimatableValues vs AnimatablePair, and custom animatableData setter logic) - Environment and @Entry (closure or class-typed defaults, unstable defaults, high-frequency updates) - @Observable best practices and efficient invalidation - ForEach and List row identity and structure (id: \\.self, indices, offsets, AnyView or multi-view rows, inline filter/sort, cached collections, List fast path) - localization (String vs LocalizedStringResource, the right bundle in packages and frameworks, .textCase, .formatted(.list()), translator comments) - soft-deprecated APIs such as NavigationView and the old onChange, and when to surface them during feature work.
Use when exploring unfamiliar code, mapping architecture, finding symbols or relationships, tracing callers, callees, data flow or dependencies, assessing impact, auditing dead or complex code, or handling explicit Codebase Memory requests. Otherwise skip tasks confined to a supplied known file, tiny one-file check, exact literal, configuration value, error string, or non-code text.
Diagnose and fix web performance issues including Core Web Vitals (LCP, INP, CLS), bundle size, asset optimization, render performance, and runtime efficiency. Use this skill whenever the user wants to improve page speed, fix Core Web Vitals, optimize assets, reduce bundle size, debug slow renders, or systematically improve a site's performance. Triggers on performance, page speed, Core Web Vitals, LCP, INP, CLS, FID, TTFB, bundle size, code splitting, image optimization, lazy loading, render blocking, slow page, performance audit, Lighthouse score. Also triggers when traffic or conversion is dropping due to perceived slowness.
Research, create, improve, migrate, evaluate, package, install-check, govern, and safely publish qiaomu-flavored agent skills from workflows, prompts, transcripts, docs, SOPs, runbooks, scripts, or notes. Use for new or existing skills, prior-art synthesis, routing/trigger boundaries, trigger or output evals, Skill IR, release gates, README/Profile preparation, GitHub repository and pull-request publication, versioned Releases, clean npx installation, team reuse, and create-and-publish flows. The publication path is self-contained and forbids direct default-branch pushes. Exclude one-off summaries, translations, ordinary docs, non-skill package publishing, and tasks that explicitly should not become a skill.
Drive a REAL browser and native apps the way a user would — not fetch raw HTML — through the persistent `browse` CLI: one long-lived headless Chromium (plus iOS, Android, and macOS apps via accessibility APIs) where goto, snapshot, click, fill, JavaScript, and screenshot share session state at ~100ms/command and interaction rides stable @eN refs, not brittle selectors. Use when verifying, navigating, or automating live web or app behavior beyond what code-reading or a raw fetch reveals
Run a codependix dependency graph export or boundary check, choose between --check boundaries, --check reports, and --write, point a run at a workspace root or configuration file, or read a Mermaid block or JSON graph it produced. Use when running codependix or npx codependix, when a run exits 0 having written nothing, when --check is refused for carrying no value, when looking for a flag that selects one graph type, when wiring codependix into a CI step or an Nx task, when a codependix-gate target failed, or when reading an exported Nx Neighborhood, NestJS module graph, or file-level import graph. Covers the command-line host directly, without assuming any task runner.
Use when writing, reviewing, or refactoring React component tests with Testing Library. Load when you see render(), screen, fireEvent, userEvent, waitFor, or *.test.tsx files. Covers query priority (getByRole > getByLabelText > getByText), user-centric testing patterns, async utilities, custom renders with providers, and accessibility-first assertions. Keywords include RTL, Testing Library, screen, getByRole, findBy, queryBy, userEvent, waitFor, toBeInTheDocument, testing-library/react, testing-library/user-event, jest-dom.
Review UI code or a running page against the ChaiUI rules (the chaicode.com look) and report what breaks them, with file and line. Use when the user asks to review, audit, check or polish UI built with ChaiUI or @chaiui components, asks "does this follow the chaicode style", or before shipping a page in a ChaiCode product. Pairs with the chaiui skill, which is for building.
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.