Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Gates whether a new test should exist and forces it to be efficient, protecting CI from low-value test bloat. Use before any change to what a pytest, Jest, or Playwright test asserts or sets up, down to one fixture or one assertion added to an existing block. Front-loads the value bar (every test must catch a realistic regression no existing test already catches; extend the nearest existing test before writing a new standalone one; test behavior through the public interface, not implementation details; collapse near-duplicates into parameterized cases) and the efficiency bar (deterministic, isolated, fast; pick the cheapest test level; Django TestCase over TransactionTestCase; no sleeps, no real network; no time bombs from absolute dates left to age against the real clock; no database a test never uses). Includes a "don't write it" decision tree. For fixing an existing flaky test use `/fixing-flaky-tests`; after this gate says a Playwright test is warranted, use `/playwright-test` for mechanics.
Browser automation via Chrome extension and DevTools MCP. Use when controlling a logged-in Chrome browser, automating workflows, filling forms, extracting data, debugging web apps, reading console logs, or running scheduled browser tasks. Use for browser testing, form automation, data extraction, web scraping, authenticated browsing.
Load this skill when configuring or reviewing CI/CD pipelines, GitHub Actions workflows, or automated testing setups. Ensures accessibility regressions are caught before code reaches production by enforcing quality gates, structured reporting, and layered automated + manual testing across all pages and user preferences.
Verify customer support work against the selected customer-case flow, full-thread evidence, account and canonical-thread matching, authority, financial approval, customer communication, eligible optional Trustpilot review-request rules, post-action read-back, send confirmation, thread-wide archive, and closure requirements. Use after every SaaS support triage, account/access or unsupported-platform response, duplicate or resolved acknowledgement, positive-confirmation closure reply, cancellation, failed-payment cancellation, refund, accidental-renewal case, support handoff, draft, send, or archive task before reporting completion
Systematic 4-phase debugging: (1) understand the failure by reading the complete error and reproducing it, (2) find working examples to compare against, (3) test one hypothesis at a time with a single change, (4) fix the root cause and verify with tests. Includes the Three Strikes Rule (escalate after 3 failed fix attempts) and the Iron Law (no fixes without investigation). Activate when tests fail unexpectedly, errors occur, behavior is wrong, something that worked before is now broken, or a user reports a bug. Triggers on: "debug", "why is this failing", "test failure", "unexpected error", "bug", "broken", "investigate this error", "fix this bug", "tests are failing", "weird behavior", "something broke", "track down this issue". Also activates when multiple bugs need systematic investigation (one at a time, not batch-fixed). NOT for: writing new tests from scratch (use tdd), or general code review (use code-review).
Compatibility router for LangWatch evaluation requests. Use only when the user asks for evaluations without making it clear whether they mean pre-deployment experiments or production online evaluations. Routes the request to the focused companion skill and does not implement either workflow itself.
Compare a Figma node's actual specs against a code spec (the values your component renders) and get a 0–100 parity score, a list of discrepancies, and fix suggestions. Use to detect design-to-code DRIFT: triggers 'check design parity', 'does my code match the Figma', 'compare this component to the design', 'is my implementation faithful', 'find differences between design and code', 'verify the build matches Figma', 'design QA against code', 'parity score'. Reads the node's visual / typography / spacing / token / accessibility specs via use_figma (any plan) and diffs them against a codeSpec you provide. Complements the native get_design_context: instead of GENERATING code, it VALIDATES that existing code stayed in sync with the design.
Comprehensive SQL statement checking for Apache Doris (based on Doris 3.1.4 Nereids ANTLR4 grammar), supporting two check modes: 1. Syntax Check - Keyword validation, statement structure verification, clause completeness, Doris-specific syntax compatibility (DISTRIBUTED BY, PARTITION BY, ENGINE, DUPLICATE/AGGREGATE/UNIQUE KEY, INSERT OVERWRITE, LOAD, EXPORT, MTMV, BACKUP/RESTORE etc.) 2. Specification Check - Object design standards, data operation standards, naming conventions based on Apache Doris development best practices. Built-in custom Doris SQL tokenizer (504 keywords from DorisLexer.g4) and recursive descent parser supporting 100+ Doris statement types. Applicable when users need SQL quality review, syntax validation, or specification compliance checking for Apache Doris SQL (versions 2.1.x / 3.0.x / 3.1.x / 4.x). 触发词："Doris SQL检查"、"Doris SQL规范"、"Doris SQL审计"、"Doris SQL语法"、"检查Doris SQL"、"Doris SQL review"
Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the animations", "audit the motion", "make this app feel better", or wants a roadmap of animation fixes rather than a review of a single diff.
Writes Kani bounded model checker proofs for Rust programs. Proves conservation, isolation, arithmetic safety, and access control properties. Use when the user asks for Kani proofs, bounded model checking, or exhaustive formal verification -- or when code contains kani::, #[kani::proof], or #[kani::unwind]. Do NOT use for fuzzing (proptest, quickcheck, cargo-fuzz), property testing, or Miri.
Profiles application performance under load using k6, Artillery, or JMeter to measure latency, throughput, and error rates. Use when planning load tests, stress tests, soak tests, benchmarking APIs, or identifying performance bottlenecks.
Use when reviewing PL/SQL - a changed procedure or package, a proposed file, or an object suspected of causing trouble. Combines the database's own correctness signals with the antipattern checklist, and reports findings anchored to line numbers.
Record a web journey as evidence on the browser host - a WebM video, a screenshot after every click and page load with a red marker at the click point, and a steps.md log. Works two ways - an agent drives the browser itself through agent-browser over CDP, or a human clicks through a Playwright-launched window while the script records. Use when asked to "record a web journey", "record the flow", "capture a user flow", "show me what you clicked", or when a walkthrough needs screenshots and video as proof.
Design, create, run, monitor, and maintain Vapi Simulations for assistants and squads. Use for turning plain-language requirements into a coverage plan, simulation personalities, scenarios, structured-output success criteria, simulations, suites, extending an existing suite, chat or voice runs, tool mocks, target variables, lifecycle webhooks, regression coverage, launch readiness, CI quality gates, run-result analysis, and simulation API validation errors. Do not use for fixed-turn mock-conversation Evals unless the user is deciding between Evals and Simulations.
Diagnose unexpected Three.js WebGPU/TSL runtime, rendering, API, asset, or version behavior. Use for a concrete failure, a suspected upstream regression or known issue, or a choice among an application fix, released upgrade, bounded workaround, upstream report, and blocker.
WCAG 2.2 compliance testing, screen reader validation, and inclusive design verification. Use when ensuring legal compliance (ADA, Section 508), testing for disabilities, or building accessible applications for 1 billion disabled users globally
API testing patterns with supertest, MSW, and Vitest. Covers integration testing for REST APIs, HTTP request mocking with Mock Service Worker v2, response assertions, schema validation, test organization, and framework-specific patterns for Express, Fastify, and Hono. Use when writing integration tests for REST APIs, mocking HTTP requests, or testing API endpoints. Use for api-test, supertest, msw, mock-service-worker, integration-test, http-mock, endpoint-test, request-test.
Guides an agent through reproducing, root-causing, fixing, and validating flaky tests in the PostHog monorepo. Use when a test fails intermittently in CI but passes on rerun or locally, when `hogli ci:insights` or the debugging-ci-failures skill classifies a failure as a flaky test, when given a GitHub Actions URL for a flaky job, when asked to check Trunk Flaky Tests for a test, PR, or master, or when asked to deflake, stabilize, or fix a flaky Jest, pytest, or Playwright test. Core discipline: reproduce locally before changing anything, fix the root cause (never mask it with sleeps, retries, or bigger timeouts), and prove the fix with an N-run validation loop sized to the observed failure rate. Stabilizing is not the only valid outcome — the skill also gates whether the test should exist, so deleting a test that catches nothing real, or re-leveling one that flakes because of the level it runs at, are first-class endings.
Ensures zero-mismatch integrity between server-rendered HTML and client-side React trees. Use when debugging hydration errors, fixing text content mismatches, handling browser extension DOM pollution, implementing selective hydration with Suspense, using the React 19 use() hook for deterministic server-to-client data bridges, or applying Next.js use cache for data drift prevention. Use for hydration mismatch, SSR, hydrateRoot, suppressHydrationWarning, onRecoverableError, two-pass rendering.
Generates Python code that evaluates SageMaker models. Supports two evaluation types: LLM-as-Judge and Custom Scorer. Use when the user says "evaluate my model", "run a benchmark", "test model performance", "how did my model perform", "compare models", or similar requests.
Reads MetaTrader 5 log files to validate indicator execution, unit tests, and compilation errors. Use when user mentions Experts pane, MT5 logs, errors, or asks "did it work". Triggers - check logs, did it work, Experts pane, Print output, runtime errors, debug output. (project)
Adaptation review expert for porting GPU code to Ascend NPU. This skill must be used for a comprehensive review when users need to port code from GPU (especially deep learning and model inference code) to Huawei Ascend NPU. It identifies migration bottlenecks, writes adaptation scripts, generates verification plans, and produces a complete Markdown review report. Triggers include keywords such as “NPU adaptation,” “Ascend migration,” “GPU to NPU,” “Ascend,” “CANN,” “model migration,” and “operator adaptation,” or requests to review a GPU code repository and migrate it to the NPU platform.
Design and validate product UI behavior as visual state prototypes before coding. Use when tasks ask how screens should change after user actions (click, tap, submit), when non-developers need to review web/iOS/Android UX flows, or when teams need interaction-state assets and acceptance checks for implementation.
React component and hook testing patterns with Testing Library and Vitest. Use when writing tests for React components, custom hooks, or data fetching logic. Covers component rendering tests, user interaction simulation, async state testing, MSW for API mocking, hook testing with renderHook, accessibility assertions, and snapshot testing guidelines. Does NOT cover E2E tests (use e2e-testing) or TDD workflow enforcement (use tdd-workflow).
Use when writing a Storybook story for a component gated on a feature flag — boolean flags or multivariate/experiment-arm variants. Covers the `featureFlags` story parameter and why imperatively setting flags renders the flag-off branch in visual-regression snapshots while passing in jest.
Owns one experiment's smoke test: a small pytest that fits on part of real `data/` and predicts on a disjoint slice with no pre-history buffer. Prediction count must equal predict-grid rows. TRIGGER when an approved experiment needs its smoke test, `pytest tests/smoke/` fails on row count, the user asks why the smoke test is failing, a pipeline edit needs proof, or the experiment script changes pipeline shape. STOP when `status.setup.pending` is non-empty (load `setup-ml-project`), or when there is no approved design or no matching experiment script: explain and send the user to setup or stay in `build-ml-pipeline`. A declined git is not asked again. "Why is smoke failing?" stays here. This action does not cover regression tests or CV interpretation. Do not write `skore.evaluate`. HOW TO USE: `status`, read the journal and experiment, write `tests/smoke/test_NN_*.py`, then `python -m skore_skills smoke run --stem <stem>`. Red JSON means fix the pipeline in `build-ml-pipeline`. Do not loosen the assertion.
Use whenever creating, configuring, or extending Storybook for a TS/React component library — covers main.ts/preview.ts setup, CSF3 story authoring, args/argTypes/controls, decorators and providers, MSW and module mocking, play-function interaction tests via the Vitest addon, the @storybook/addon-a11y workflow (axe-core), autodocs vs MDX docs, design tokens, Figma linking, Chromatic deployment, and on-demand build performance. Triggers on tasks like "write a story", "set up Storybook", "configure addon-a11y", "fix this play function", "deploy Storybook", "test Storybook in CI" — even when the user doesn't say "storybook" but is editing `*.stories.tsx`, `.storybook/main.ts`, or `.storybook/preview.ts`. Targets Storybook 9+/10 (modern `storybook/test` import, Vitest addon, CSF3 + `satisfies Meta`). Does NOT cover generic React patterns (use the `react` skill), generic Testing Library queries (use `react-testing-library`), or WCAG primer (points at addon-a11y + axe rule config).
Wire Strix security scanning into CI/CD — GitHub Actions, GitLab CI, or any pipeline — so every pull request gets a diff-scoped AI pentest that blocks vulnerable code. Covers both the self-hosted open-source CLI (runs in your runner) and the managed app.strix.ai platform (GitHub/GitLab app or API, no runner infra). Use when the user asks to add security scanning, pentesting, or Strix to their CI pipeline or PR workflow.
Use test-driven development for behavior-changing feature or fix work, and whenever the user mentions TDD, test-first, red-green-refactor, tracer bullets, integration tests, or public-interface behavior tests. Skip for docs-only, path-only rename, formatting-only, or purely mechanical chores unless explicitly requested.
Select and run TypeScript SDK verification for packages, examples, type checks, linting, builds, Vitest suites, Effect v4 CLI tests, and runtime E2E tests. Use when adding tests, diagnosing TypeScript CI, choosing a focused test command, validating TypeScript package changes, or writing/porting CLI tests against [email protected] and @effect/vitest. Do not use for Python-only checks.
When writing or reviewing code to prevent over-engineering and speculative features. Use when the user says "is this over-engineered," "do we need this," "should I add," "future-proof," or "just in case." For simplicity concerns, see kiss. For abstraction design, see solid.
Convert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.
Main Agents: Do NOT use this skill directly. If you need to test the TUI, invoke the `tui_tester` subagent. Drive terminal UI (TUI) applications programmatically for testing, automation, and inspection. Use when: automating CLI/TUI interactions, regression testing terminal apps, or verifying interactive behavior. Also use when: user asks "what is agent-tui", "what does agent-tui do", "demo agent-tui", "show me agent-tui", "how does agent-tui work", or wants to see it in action.
Comprehensive AI security verification using OWASP AI Security Verification Standard (AISVS) framework. Use when verifying an AI-driven application, ML pipeline, or LLM-integrated system against AISVS, preparing for an AI security audit, or checking security and ethical controls across 13 categories from training data governance to human oversight.
Headless browser automation via agent-browser — Rust CLI daemon with persistent auth profiles for fast, scriptable, parallel browser work. Supports batch commands, network interception, device emulation, per-site profile auth (one-time headed login, headless forever after), and parallel isolated sessions via --session. Workflows: ReviewStories (fan out YAML user stories to parallel UIReviewers), Automate (load/run parameterized recipe templates), Update. Delegates to general-purpose agents with agent-browser instructions for background parallel scraping. Falls back to Interceptor if site has bot detection. USE WHEN headless browser, batch scrape, fast screenshot, dev server test, parallel browser, background automation, extract data, review stories, automate recipe, batch screenshots, scrape multiple pages in parallel. NOT FOR deploy verification or UI confirmation with real Chrome (use Interceptor). NOT FOR simple single-URL fetching (use WebFetch). NOT FOR CAPTCHA or bot-detection bypass (use BrightData or Interceptor).
One-shot efficiency audit of a file, diff, or whole repo across BOTH axes at once: over-engineered code (reinvented stdlib, needless abstractions, speculative config) AND bloated prose (verbose comments, padded docstrings, redundant doc sections). Neither a pure code-minimizer nor a pure prose compressor does both in one pass. That's the point. Ranked report, biggest saving first; changes nothing. Use when the user says "chisle audit", "/chisle-audit", "audit this for bloat", "what can I cut", "review this PR for over-engineering and verbosity".
Review a diff or file through the Chisle lens: flag over-engineering, speculative abstractions, reinvented stdlib, and verbose code that a lazier approach would shrink. One finding per line, no praise. Use when the user says "chisle review", "review this for bloat", or invokes /chisle-review.
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.