Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
For writing, filling in, or reviewing test cases and test plans from requirement acceptance criteria; product goals and UAT status definitions belong to prd. Covers normal, boundary, permission, and concurrency scenarios, generates standard mapping and SPMS TC drafts, and checks for duplicates before writing.
Implement accessibility (a11y) best practices to make applications usable by everyone. Use when building UIs, conducting accessibility audits, or ensuring WCAG compliance. Covers screen readers, keyboard navigation, ARIA attributes, and inclusive design patterns
Audits codebases and product copy for deceptive dark patterns inferable from local source code and text—no runtime inspection or screenshots needed. Produces a structured narrative report with confidence grading, source locations, concise reasoning, and official pattern reference links for each detected pattern. Covers pricing, subscriptions, consent, modals, preselected controls, misleading CTAs, and more.
Debug the signals pipeline locally end-to-end. Covers emitting test signals from fixtures, monitoring Temporal workflows via the REST API, reading sandbox agent logs from object storage, inspecting Docker sandbox containers, and diagnosing common failures (stale ClickHouse embeddings, agentsh network denials, inactivity timeouts). Use when a signal isn't reaching the inbox, a signal-report-summary workflow fails, or a sandbox task run times out.
Diagnoses CI and pull-request pipeline health for a GitHub repo using the engineering analytics MCP tools—pull-requests (PR list with CI status), workflow-health (per-workflow CI trends), and pr-lifecycle (a single PR's timeline). Use when asked whether CI is getting faster or slower, which GitHub Actions workflow is the slow or flaky long pole, how long PRs take from open to merge, how an author's merge time compares to the cohort, which open PRs have failing or pending CI, or where a specific pull request is stuck. Triggers on “engineering analytics,” “is CI getting slower,” “slow workflow,” “flaky CI,” “time to merge,” “cycle time,” “PR throughput,” “failing checks,” “where is PR <n> stuck,” “CI long pole,” “what's holding up this PR.” For a verdict on one specific CI failure (whose fault, which commit) use investigating-ci-failures; to save these numbers as insights use turning-engineering-analytics-into-insights.
UAT THẬT cho một bản framework sắp phát hành - dựng một dự án TRỐNG hoàn toàn mới, cài overstack đúng đường NGƯỜI MỚI (curl bootstrap từ GitHub raw, không phải file:// working-tree), rồi kiểm chứng năng lực MỚI của chính bản đó có tới tay người dùng không (skill reachable, rule CẮN thật, docs khớp). HAI PHA - (1) nhánh CANARY trước merge: đẩy lên nhánh tạm uat/<ts>, curl từ raw của chính nhánh đó (kèm HARNESS_BASE + REPO_RAW + SKILLS_REF trỏ canary), UAT đầy đủ; FAIL thì xoá canary và nhánh chính chưa hề bị bẩn. (2) main-URL smoke NGAY SAU merge: chạy đúng lệnh người mới gõ, KHÔNG override biến nào - chỉ pha này kiểm được các giá trị MẶC ĐỊNH (chỗ hardcode tên nhánh); FAIL thì gỡ commit khỏi remote (revert hoặc reset --force-with-lease). Gọi khi user nói "uat", "test thật", "test downstream", "kiểm tra người mới cài có chạy không", "acceptance", "/fdk-uat", hoặc trước khi công bố một bản có năng lực mới. KHÁC medic --ci và fresh-install-smoke (cả hai cài từ working-tree qua file:// nên KHÔNG chứng minh được đường remote).
Comprehensive SQL statement checking for DWS, supporting two check modes: 1. Syntax Check - Keyword validation, statement structure verification, clause completeness, DWS syntax compatibility based on gram.y grammar definitions 2. Specification Check - Object design standards, data operation standards, naming conventions based on DWS development design specification Built-in custom DWS SQL tokenizer (594 keywords) and recursive descent parser supporting 160+ statement types. Applicable when users need SQL quality review, syntax validation, or specification compliance checking. Trigger phrases: “SQL检查”, “SQL规范”, “SQL审计”, “SQL语法”, “SQL优化”, “检查SQL”, “SQL review”
Use when reviewing ML system design docs, ML/AI project repos, design-doc PRs, RAG/LLM/foundation-model architectures, agentic AI workflows, or production ML readiness. Applies the ML System Design framework by Kravchenko and Babushkin to grade designs, compare docs with code, find critical gaps and low-hanging fruit, and give specific non-cringy praise.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Fix a confirmed bug at its root cause with the smallest correct change only—reproduce it before touching code: write a failing reproducer, diagnose the first broken assumption in the data flow, load the matching framework reference and category playbook, apply the minimal fix, then verify the reproducer passes and run the regression scope. Never write fix code without a reproducer (or a documented reason one is impossible), patch the symptom while the root cause remains, or weaken a test to pass. Use when the user says “fix this bug”, “fix the findings”, “/bugfix”, or asks to repair a confirmed defect
Perform evidence-driven, multi-subsystem audits of real codebases to find correctness bugs, race conditions, security gaps, stale documentation, dead code, and production-readiness risks. Use when asked to audit a system end-to-end, verify agent-written code before shipping, analyze a subsystem for correctness across multiple modules, or produce a structured risk report for a real implementation. Prefer other skills for a single isolated bug, a proposal or document review, or a dedicated dead-code cleanup
Explore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by deepening shallow modules. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly coupled modules, or make a codebase more AI-navigable.
Test your AI agent with simulation-based scenarios. Covers writing scenario test code (Scenario SDK), creating platform scenarios via the `langwatch` CLI against a connected agent, reading the run parameters that agent declares so the scenarios and comparison runs turn its real levers, and red teaming for security vulnerabilities. Auto-detects whether to use code or platform approach based on context.
Deep dive into table-driven tests in Go: when to use or avoid them, struct design, subtest naming, advanced patterns such as test matrices and shared setup, and refactoring bloated tables into clean ones. Use when writing or refactoring table-driven tests, reviewing test table structure, or deciding whether table-driven tests are appropriate. Examples: “table-driven test,” “table test,” “test cases struct,” “test matrix,” “parametrize tests,” “data-driven test,” “refactor test table.” Not for general test strategy, mocks, golden files, fuzzing (go-test-quality), or benchmarks (go-performance-review).
Improves Python library code quality through ruff linting, mypy type checking, Pythonic idioms, and refactoring. Use when reviewing code for quality issues, adding type hints, configuring static analysis tools, or refactoring Python library code.
MSW (Mock Service Worker) v2 and v3 best practices, patterns, and API guidance for API mocking in JavaScript/TypeScript tests and development. Covers handler design, server setup, response construction, testing patterns, GraphQL, and v1-to-v2 and v2-to-v3 migration. Baseline: msw ^3.0.0. Triggers on: msw imports, http.get, http.post, HttpResponse, setupServer, setupWorker, graphql.query, sse, ws.link, or mentions of “msw”, “mock service worker”, “api mocking”, or “msw v3”.
UX agency skill for user journey mapping with emotional tracking. Includes Playwright testing (happy path, cognitive walkthrough, accessibility, synthetic user), a library of proven UX patterns, synthetic personas, Nielsen heuristics scoring, and anti-generic-AI guardrails.
Before showing the user any substantive GTM deliverable (positioning, value prop, homepage, launch post, pricing, sales script, the brief, the market research, or the roadmap), stress-test it against the standard as an independent critic, because the agent that wrote it is the worst judge of whether it is good. Use as a gate right before presenting work, or when the user asks whether something is actually strong.
WCAG 2.2 AA enforcement as a package of Agent Skills: router skills for web UI, full-site audits, Office/PDF/ePub documents, markdown, desktop and Python tooling, and GitHub workflows dispatch specialist, helper and reference skills by name.
Guides contributors through the z-schema codebase, PR workflow, and common development tasks. Use when the user wants to contribute to z-schema, add a new feature or keyword, add an error code, add a format validator, modify options, write tests, run the test suite, fix a failing test, understand the validation pipeline, navigate the source code architecture, or submit a pull request. Also use when someone mentions contributing, PRs, the z-schema source code, or the JSON Schema Test Suite integration.
A comprehensive designer toolkit by Marie Claire Dean, organised into nine plugins: design-research, design-systems, ux-strategy, ui-design, interaction-design, prototyping-testing, design-ops, designer-toolkit, and visual-critique. Covers the design practice from research to systems, UI, interaction, testing, and handoff.
Use this skill to run a visual-craft audit of a rendered UI and produce an evidence-grounded Craft Report across Useful, Usable, Reliable, Coherent, and Well-Crafted. Invoke it for craft audits, visual critiques, design comparisons, felt-quality reviews, or visual-craft readiness checks on screenshots (.png, .jpg, .jpeg, .webp, .gif), Figma frames, rendered prototypes, and live URLs. Do not use it for source-code review, SLDS compliance (use design-systems-slds-validate), or accessibility compliance (use experience-accessibility-validate).
Score and compare images using vision LLMs as judges. YAML-defined criteria presets for 11 use cases (text-to-image, photorealism, document OCR, charts, UI, portrait, product, scientific, invoice, alt-text, artistic style). Supports OpenAI, Anthropic, Gemini, Mistral, and OpenRouter as judge providers. Keys auto-decrypted via SOPS + age.
This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration, evaluator bias mitigation, confidence scoring, and automated quality assessment.
Configure project guidance for AI/coding agents to use Allure agent mode during test work by detecting local test commands, Allure capabilities, result paths, and evidence conventions, then creating short root agent routers plus docs/allure-agent-mode.md. Use when the goal is agent workflow guidance, evidence review workflow, expectations, and project-specific test-work instructions; not when the primary goal is installing Allure adapters, making tests emit results, adding report scripts, or configuring CI publishing.
AscendC operator precision evaluation. Generate a comprehensive set of precision test cases (≥30) for compiled and installed operators, run the tests, and produce a precision validation report. Keywords: precision testing, precision evaluation, precision report, accuracy, error analysis. After completion, MUST present an overview, failure summary, and key findings in the current conversation; do not provide only the report path.
Validate Bun workspace configuration and detect common monorepo issues. Ensures proper workspace setup, dependency catalogs, isolated installs, and Bun 1.3+ best practices. Use when setting up a Bun monorepo, before adding workspace dependencies, auditing an existing Bun workspace, or validating package.json in CI.
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.