Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Testing best practices with React Testing Library and Vitest. Use when: (1) working on .test.tsx, .test.ts, .spec.tsx, or .spec.ts files; (2) writing or refactoring component tests; (3) tasks include keywords such as "test", "testing", "vitest", "RTL", "getByRole", "userEvent", "waitFor", or "expect"; (4) writing tests for asynchronous logic or user interactions
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/spec 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".
Create new scientific tools for the ToolUniverse framework with proper structure, validation, and testing. Use when users need to add tools to ToolUniverse, implement new API integrations, create tool wrappers for scientific databases or services, expand ToolUniverse capabilities, or follow ToolUniverse contribution guidelines. Supports creating tool classes, JSON configurations, validation, error handling, and test examples.
Generate a working k6 browser test (k6/browser) from a plain-language description of a user journey — no CSS selectors or technical detail needed. Explores the LIVE target site with a throwaway k6/browser session to discover real, verified selectors (getByRole/getByLabel/getByText, etc.), dismisses cookie/consent banners, then writes a functional or load test using expect() from k6-testing (Web-Vitals thresholds for load). Looks up k6/browser APIs via `k6 x docs`; validates with `k6 run`. Use when the user wants to write, author, or generate a k6 browser/UI or load test with a real browser, or says things like "write a browser test for…", "test this login/checkout/search flow with k6", "click through my site and verify…", or describes navigating a site in prose. For a full multi-test performance suite use k6-perf-test-website; for HTTP/protocol (non-browser) tests use the general k6 skills; for browser or scripted checks in Grafana Cloud Synthetic Monitoring, use synthetic-monitoring-checks
Evidence-first development — surround the implementation with an executable spec and a gauntlet of constraints (tests, types, coverage, mutation) so line-by-line review becomes optional. Use when the user explicitly asks for high-assurance or evidence-first work ("reliable", "TDD", "prove it works", "I won't read the code"), or when the change touches high-stakes domains (money, auth, data loss, concurrency, public API). For routine changes where the user just wants normal tests, write good tests directly instead of invoking this loop.
PostgreSQL database design, migration, and performance optimization best practices. This skill should be used when writing, reviewing, or refactoring database schemas, migrations, or query patterns. Triggers on tasks involving PostgreSQL databases, schema design, migration optimization, or data modeling
Step-by-step debugging workflow: reproduce the bug, isolate the failing component, trace to root cause, apply a targeted fix, and verify the fix resolves the issue without regressions. Use when you encounter a bug, error, exception, crash, or unexpected behavior that needs troubleshooting.
Use a consultative, modular, step-by-step approach to add or configure only the Maven plugins you need in pom.xml. Covers quality tools (enforcer, surefire, failsafe, jacoco, pitest, spotbugs, pmd), security scanning (OWASP), code formatting (Spotless), version management, container image builds (Jib), build information tracking, and benchmarking (JMH). Trigger for requests to add or improve Maven plugins in pom.xml, configure Maven quality plugins, add Maven build lifecycle plugins for Java verification, or review Maven plugin versions and executions. Part of Plinth Toolkit
Implement OpenAI Harness Engineering practices in any repository—AGENTS.md, PLANS.md, deterministic smoke/test/lint harness commands, strict architecture boundaries, observability from day one, and entropy-control audits for reliable autonomous agent runs.
Write Patrol end-to-end (E2E) tests for a Flutter app — order of actions, Patrol API and assertion rules, native dialog handling, and test-key conventions. Use when adding or editing Patrol/integration tests, assigning widget keys for testing, or debugging a failing Patrol test.
Knip dead code detection best practices for JavaScript and TypeScript projects. Use when configuring Knip, analyzing unused code, setting up CI integration, or cleaning up codebases. Triggers on knip.json, dead code, unused exports, unused dependencies, bundle optimization.
Use when an n8n workflow isn't working, errors appear, results don't match what was expected, or the user says "this isn't working." Triggers on errors, unexpected output, "it's not working", "why is this happening", "the workflow stopped", failure investigation, or any debugging context.
Execute and implement approved specification proposals in sequence, with testing and validation first. Use to implement changes, apply proposals, execute specification tasks, or build according to an approved plan. Triggers include "openspec开发", "开发", "实施" "实现提案", "应用变更", "执行规范", "按顺序完成任务", "构建功能", "开始实施".
Use when you need to apply testing strategies for Java code — RIGHT-BICEP to guide test creation, A-TRIP for test quality characteristics, or CORRECT for verifying boundary conditions. This should trigger for requests such as Review Java code for testing strategies; Apply RIGHT-BICEP testing strategies in Java code; Apply A-TRIP testing strategies in Java code; Apply CORRECT boundary condition verification in Java code. Part of Plinth Toolkit
Use when you need to set up, review, or improve Java integration tests — including generating a BaseIntegrationTest.java with WireMock for HTTP stubs, detecting HTTP client infrastructure from import signals, injecting service coordinates dynamically via System.setProperty(), creating WireMock JSON mapping files with bodyFileName, isolating stubs per test method, verifying HTTP interactions, or eliminating anti-patterns such as Mockito-mocked HTTP clients or globally registered WireMock stubs. This should trigger for requests such as Review Java code for integration tests; Apply best practices for integration tests in Java code; Write Java integration tests with real infrastructure boundaries; Improve Testcontainers integration tests for Java code; Review integration test setup and teardown in Java projects. Part of Plinth Toolkit
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.
Ship every change the way the user requires, with the guardrails. Take screenshots of the start, the key moment, and the result; give the change its own changelog version with pictures; verify with tests; commit only your own files; merge with the latest main and push as a fast-forward; publish that exact main live; confirm each step; and report measured sizes, asking before any upload over 50 MB. Use at the end of every change (feature, fix, tweak, art, balance, polish) and whenever the user says “ship it”, “commit”, “push”, “merge”, “publish”, “deploy”, “go live”, or “update the changelog”. Project specifics (hosting, the changelog pipeline, merge conflicts) go in an optional local references/<project>.md next to this skill
Fix failing ToolUniverse tools by diagnosing test failures, identifying root causes, implementing fixes, and validating solutions. Use when ToolUniverse tools fail tests, return errors, have schema validation issues, or when asked to debug or fix tools in the ToolUniverse framework.
Tests/benchmarks a third-party LLM endpoint (OpenAI- or Anthropic-compatible): availability, fidelity, speed, concurrency, protocol compliance, quality regression. Use before hand-rolling a curl loop, when onboarding a provider, or debugging "system prompt 不生效" / a tok/s claim — 测评/压测一个模型或渠道. Not for TTS/voice-clone supplier eval (use the audio skill)
Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video
Design comprehensive test cases using PICT (Pairwise Independent Combinatorial Testing) for any piece of requirements or code. Analyzes inputs, generates PICT models with parameters, values, and constraints for valid scenarios using pairwise testing. Outputs the PICT model, markdown table of test cases, and expected results.
Routing-first visual approval gate for AI agent plans, markdown specs, and diffs. Use when a human needs to review a concrete plan before execution, inspect a targeted diff in a browser, mark up a spec/PRD/architecture note, or set up the review loop on Claude Code, Gemini CLI, Codex CLI, or OpenCode. Route planning/spec creation to `task-planning` or `ralph`, broad PR-policy review to `code-review`, rendered-UI critique to `agentation`, and fresh-session browser verification to `browser-harness`.
Address the review findings posted on an Entire trail: fetch the trail's open findings, fix the code, and resolve them on the trail. Use when the user gives a trail URL or number and asks to address, fix, or resolve its findings or review comments. Not for local diff review — that is the `review` skill.
Finds the most informative session recording linked to an error tracking issue. Use when a user has an error tracking issue ID and wants to watch a replay showing what the user was doing when the error occurred. Ranks linked sessions by recency, activity score, and journey completeness, then summarizes the pre-error context. Replaces blind session picking from potentially hundreds of linked recordings
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.