Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
Apply a prompt-agnostic execution and verification loop to any substantial task while preserving the original request. Use when the user asks to fan out work, use subagents or independent reviewers, loop until done, benchmark against references, apply a harsh critic, compare candidates blind, improve an existing prompt with verification, or continue until explicit quality gates pass.
Use when setting up linting for a Go project, configuring golangci-lint, or adding Go checks to a CI/CD pipeline. Also use when starting a new Go project and deciding which linters to enable, even if the user only asks about "code quality" or "static analysis" without mentioning specific linter names. Does not cover code review process (see go-code-review).
React 19 performance patterns and composition architecture for Vite + Cloudflare projects. 50+ rules ranked by impact — eliminating waterfalls, bundle optimisation, re-render prevention, composition over boolean props, server/client boundaries, and React 19 APIs. Use when writing, reviewing, or refactoring React components. Triggers: 'react patterns', 'react review', 'react performance', 'optimise components', 'react best practices', 'composition patterns', 'why is it slow', 'reduce re-renders', 'fix waterfall'.
Applies Arbor Hypothesis Tree Refinement to research artifacts with repeatable evaluators, including model training, agent harnesses, data synthesis and benchmark optimization. Uses persistent hypotheses, isolated experiments, evidence propagation and held-out candidate comparison for multi-experiment research runs. Includes a standard-library state manager and guidance for the RUC-NLPIR Arbor CLI.
Agentforce agent testing with dual-track workflow and 100-point scoring. TRIGGER when: user tests Agentforce agents, runs sf agent test commands, creates test specs, validates topic routing, or analyzes agent test coverage. DO NOT TRIGGER when: Apex unit tests (use sf-testing), building agents (use sf-ai-agentforce), or Agent Script DSL (use sf-ai-agentscript).
Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates
Use this skill when the user asks to “analyze session,” “세션 분석,” “evaluate skill execution,” “스킬 실행 검증,” “check session logs,” “로그 분석,” provides a session ID with a skill path, or wants to verify that a skill executed correctly in a past session. Post-hoc analysis of Claude Code sessions to validate skill/agent/hook behavior against SKILL.md specifications.
Use when capturing or analyzing an iOS .memgraph, especially when the task mentions a memory leak, heap growth, persistent memory increase, ownership path, or matched-capture comparison with Apple CLI tools. Covers unambiguous Simulator capture, leaks/heap/vmmap/malloc_history evidence, raw artifact preservation, and same-flow verification. Use debugging-instruments for interactive Xcode Memory Graph, Instruments, generic retain-cycle inspection, or LLDB work
Debug a MAX model that loads, compiles, serves, and generates tokens but whose output disagrees with a reference implementation. Use when parity debugging stalls on scalar taps, the model returns gibberish or wrong greedy tokens, logit cosine is high but argmax differs, or generation is coherent then diverges. Applies during an architecture port, a quantization bring-up, a multi-GPU conversion, or after a MAX upgrade. Triggers on “parity failure,” “silent corruption,” “logits match but tokens diverge,” “top-1 mismatch,” “greedy divergence,” and “model serves but generates garbage.” Not for crashes on load or pre-serve scaffolding (use import-model). Mandates reference-vs-MAX tensor-dump comparators first, numerical verification of fixes before recompiling, and a serve-vs-pipeline bisect when dumps match but text diverges.
Write Playwright tests for Hyvä themes with Alpine.js components. This skill should be used when writing e2e tests, creating page objects, or debugging selector issues in Playwright tests for Hyvä Magento storefronts. Trigger phrases include "write playwright test", "playwright alpine", "test hyva page", "e2e test", "playwright selector".
Audit and review application UI for IDS compliance, accessibility, usability, and cognitive load. Covers component usage validation, WCAG accessibility checks, cognitive load assessment, and UX quality evaluation. Use when asked to review UI, check accessibility, assess usability, audit IDS compliance, or when the user says "review this page", "check a11y", or "is this accessible?"
Use AI to write NEW test code from specs, PRDs, user stories, code diffs, bug reports, or OpenAPI specs. Staged pipeline: requirements extraction → risk analysis → coverage matrix → scenario generation → oracle design → test code → human review, with guardrails against hallucinated APIs and weak assertions. Use when: "generate tests from spec," "tests from PRD," "tests from user story," "auto-generate test cases," "AI write tests for me." Not for: testing AI/LLM features in your product — use ai-system-testing. Not for: auditing a pre-existing test suite you did not just generate — use ai-qa-review (Step 7 here only reviews tests THIS pipeline produced). Related: playwright-automation, unit-testing, api-testing, qa-project-context
Use when optimizing Go code, investigating slow performance, or writing performance-critical sections. Also use when a user mentions slow Go code, string concatenation in loops, or asks about benchmarking, even if the user doesn't explicitly mention performance patterns. Does not cover concurrent performance patterns (see go-concurrency).
Build truthful Vesperfall asset-library review pairs from transparent PNG references and live Three.js, FBX, or img2threejs models. Use when adding a character, enemy, prop, or equipment asset to the Vesperfall catalog; creating a card-PNG plus inspector-model treatment; exposing an isolated model or moveset route; or standardizing provenance, grounding, tests, and Codex-browser validation for game art review.
Use when capturing or analyzing ETTrace profiles for a focused iOS launch or runtime flow, including exact-build dSYM UUID matching, Simulator or device capture, processed per-thread flamegraph JSON, sampled inclusive/exclusive time, unresolved symbols, and comparable verification. Use debugging-instruments or swiftui-performance for generic profiling instead.
Audit websites, apps, screenshots, mockups, and design code for harmful AI-design clichés, generic generated defaults, and established UI defects. Use when the user wants evidence-backed design feedback, an anti-slop review, or a removal-first cleanup plan without a speculative redesign.
Add missing test coverage for your local code changes by generating new test files. Covers uncommitted and untracked changes, or the latest commit if everything is committed. Use when you want to write tests for new logic or increase test coverage.
Review existing test code for quality, smells, and testability issues. Detects test smells across six dimensions—readability, reliability, diagnostic value, design, AI-generated, and coverage—analyzes the testability of application code, and backs qualitative smells with mutation testing. Use when: “review my tests,” “test quality audit,” “test smells,” “testability analysis,” or “are these tests any good.” Not for generating new tests—use `ai-test-generation`. Not for testing AI features in your product—use `ai-system-testing`. Related: unit-testing, shift-left-testing, coverage-analysis, ai-test-generation
Capture and review Agent Skill observations, and create, run, diagnose, or iteratively improve Skill evaluations (evals) with the skill-up CLI. Use when the user asks to record explicitly attributed Skill usage or feedback; review observations or user-supplied traces/transcripts; turn an approved observation into a regression case; evaluate, test, regress, verify, fix, improve, iterate, or evolve a Skill; add or strengthen eval cases; write eval.yaml/case.yaml; run skill-up run/validate/list-cases/report/import/init; or migrate from Anthropic evals.json. Plugin observation capture/review require either the Codex skill-up plugin or an observer-enabled DSH skill-up plugin. User-supplied external evidence can be reviewed without a plugin; evaluation remains multi-engine.
Implement visual regression testing with Playwright screenshots, Chromatic, Percy, and Argos CI. Covers baseline management, diff threshold tuning, dynamic content masking, responsive viewport testing, and review/approval workflows. Use when: "visual test," "screenshot," "visual regression," "pixel diff," "snapshot diff," "update baselines," "Chromatic," "percy snapshot," "argos screenshot." Not for: bulk baseline regeneration after a redesign broke many tests — use selector-drift-recovery; cross-browser rendering matrices — use cross-browser-testing; general Playwright test structure — use playwright-automation. Related: playwright-automation, ci-cd-integration, cross-browser-testing.
Draw how any system moves between states, such as a product flow, a protocol, or a service, as a Mermaid statechart from a TLA+ model. Each bug is a numbered path with blue borders to a state that breaks a rule. Use for /statechart, to show a bug as a path through states, or to turn an agreed chart into a TLA+ skeleton.
Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.
Comprehensive QA and testing skill for quality assurance, test automation, and testing strategies for ReactJS, NextJS, NodeJS applications. Includes test suite generation, coverage analysis, E2E testing setup, and quality metrics. Use when designing test strategies, writing test cases, implementing test automation, performing manual testing, or analyzing test coverage.
Checks a GitHub, GitLab, or Perforce (p4) pull request (or merge request, or shelved changelist) for unresolved review comments, failing status checks, and incomplete PR descriptions. Waits for pending checks to complete, categorizes issues as actionable or informational, and optionally fixes and resolves them. Use when the user wants to check a PR/MR/CL, address review feedback, or prepare a change for submission.
This skill should be used when generating comprehensive test cases from PRD documents or user requirements. Triggers when users request test case generation, QA planning, test scenario creation, or need structured test documentation. Produces detailed test cases covering functional, edge case, error handling, and state transition scenarios.
Comprehensive DAG failure diagnosis and root-cause analysis with structured investigation and prevention recommendations. Use when deep failure investigation is needed, a DAG fails to import/parse or 'airflow dags list' errors on a file; a task or run is failing and must be diagnosed and fixed; requests like 'why did X fail', 'my dag keeps failing — find and fix it', or fixing a broken DAG so it loads cleanly. For simple 'why did it fail / show logs', the airflow skill handles it directly.
Makes Capacitor apps work with VoiceOver, TalkBack, Dynamic Type / Android font scale, Switch Control, hardware keyboards, Reduce Motion and Increase Contrast. Covers Capacitor-specific gaps - WKWebView not following iOS Dynamic Type, Android WebView text zoom breaking layouts, zoomEnabled/user-scalable, SPA route changes not announced, native views under the WebView (maps, camera preview) being unreachable, @capacitor/screen-reader (isEnabled, speak, stateChange) and @capacitor/text-zoom (getPreferred, set) - plus testing with Accessibility Inspector, simctl content_size, adb font_scale, TalkBack and axe-core, mapped to WCAG 2.2. Do not use for Ionic component styling (use ionic-design), notch/home-indicator layout (use safe-area-handling), keyboard overlap bugs (use capacitor-keyboard), automated test framework setup (use capacitor-testing), or App Store metadata (use capacitor-app-store).
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization. Applies the RED-GREEN-REFACTOR cycle to process documentation by running a baseline without the skill, writing to address failures, and iterating to close loopholes.
Add tree-sitter language support to codegraph end-to-end — wire the grammar + extractor, write tests, then benchmark extraction quality and retrieval value on 3 popular real-world repos. Use when the user runs /add-lang <language> or asks to add/support a new language (e.g. Lua, Elixir, Zig, OCaml) in codegraph.
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.