Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Audit an LLM eval pipeline and surface problems: missing error analysis, unvalidated judges, vanity metrics, etc. Use when inheriting an eval system, when unsure whether evals are trustworthy, or as a starting point when no eval infrastructure exists. Do NOT use when the goal is to build a new evaluator from scratch (use error-analysis, write-judge-prompt, or validate-evaluator instead).
Review a web app or page for visual design quality — layout, typography, spacing, colour, hierarchy, consistency, interaction patterns, and responsive behaviour. Not a UX audit (that checks usability) — this checks whether it looks professional and polished. Produces a design findings report with screenshots. Triggers: 'design review', 'does this look good', 'review the design', 'check the layout', 'is this polished', 'visual review', 'design audit', 'make it look better', 'it looks off'.
Review existing UI against the project's design context, accessibility expectations, responsive behavior, interaction quality, and high-confidence production rules. Use for UI audits, design QA, frontend review, accessibility review, consistency checks, or requests to find and safely fix visual defects. Trigger for requests such as "review this UI", "audit this page", "find design issues", "check responsiveness", or "fix obvious UX problems". Use 21st-ui-build when the request is primarily to create new UI
Prevent and remove generic AI-generated design defaults, incoherent visual choices, and established UI defects while creating, revising, or reviewing websites, apps, screenshots, mockups, and design code. Use as a passive quality gate during UI work or for an explicit anti-slop cleanup; preserve the chosen art direction instead of forcing a neutral redesign
Turn a vague bug report into a VERIFIED minimal reproduction and then a failing regression test, agent-driven end to end. Covers extracting the implicit repro from a thin report (env, build, steps, data), the reproduce-minimize-isolate-capture loop, git bisect to find the introducing commit, building a deterministic minimal repro (fixed seeds, frozen time, stubbed network), writing the failing regression test BEFORE the fix (red) and confirming the fix flips it green, and writing repro evidence back into the ticket. Distinguishes flaky-not-reproducible from environment-specific. Use when: "reproduce this bug," "minimal reproduction," "repro steps," "find the commit that broke it," "git bisect," "make the repro deterministic," "write a failing test for this bug," "regression test for a defect," "can't reproduce this bug." Not for: Classifying/deduplicating/severity-routing existing failures without reproducing them — that is ai-bug-triage. Generating tests from specs rather than from a defect — that is ai-test-generation. Related: ai-bug-triage, ai-test-generation, test-reliability, systematic-debugging, qa-project-context.
QA-test a website or web app and return a 1-5 quality score (5 = flawless, 1 = broken) with evidence. Use when the user wants to test, QA, evaluate, score, or "check how good" a site, page, flow, or app — including a local dev server (e.g. "qa test localhost:5173", "does the checkout work?", "rate this landing page"). Drives a real Browser Use cloud browser, tunneling localhost automatically.
Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback. Use when evaluating academic or scientific work — papers, proposals, methods sections, or evidence quality — against a repeatable rubric.
Apex test execution, coverage analysis, and test-fix loops with 120-point scoring. TRIGGER when: user runs Apex tests, checks code coverage, fixes failing tests, or touches *Test.cls / *_Test.cls files. DO NOT TRIGGER when: writing Apex production code (use sf-apex), Agentforce agent testing (use sf-ai-agentforce-testing), or Jest/LWC tests (use sf-lwc)
Salesforce data operations with 130-point scoring. Trigger when the user creates test data, performs bulk import/export, uses sf data CLI commands, or needs data factory patterns for Apex tests. Do not trigger for SOQL query writing only (use sf-soql), Apex test execution (use sf-testing), or metadata deployment (use sf-deploy).
Audit work, verify claims with concrete evidence, and explain the result in simple grade-5 language. Use when the user asks to review, audit, check, verify, explain a change or fix, summarize test results, validate whether something works, or translate technical findings into plain language for non-technical readers.
Guide performance profiling for Apple platform apps with Instruments, Xcode diagnostics, and MetricKit. Use when investigating app hangs, stutters, high CPU, memory leaks, memory growth, OOM crashes, slow launch, battery drain, thermal issues, App Store performance readiness, or when adding os_signpost and measurement hooks
Hybrid fingerprint + LLM pipeline for bug classification, deduplication, and ticket generation. Normalizes CI logs, creates stable fingerprints, clusters near-duplicates, then uses LLM for severity classification and ticket writing. Includes bug reporting templates and severity/priority matrix. Use when: "bug triage," "classify bugs," "failure analysis," "auto-classify," "CI failures," "bug report," "defect template." Not for: runtime self-healing of one flaky locator — use test-reliability. Not for: designing new tests from production telemetry — use observability-driven-testing. Related: qa-metrics, qa-dashboard, ci-cd-integration, qa-project-context.
Automated auditor designed to verify Android applications against Google Play Policy domains. It cross-references static code analysis with Play Store declarations to generate deterministic compliance reports, identifying undeclared data collection, architectural risks, and missing disclosures across Permissions and APIs Hygiene, User Account and Identity, and Data Safety and Privacy domains
Goal-driven E2E testing where a browser agent (Playwright MCP / computer-use) reads a natural-language goal and explores the app via the accessibility tree to assert outcomes — no pre-written script. Covers when intent-driven beats scripted, making agent runs repeatable and bounded (pinned model, temperature 0, seeded data, bounded steps, explicit success assertion, snapshot-not-pixel), cost/latency control, the accessibility-tree-first interaction model, CI gating, and graduating a stable run into a scripted Playwright test. Use when: "agentic browser test," "goal-driven browser test," "let an agent explore the app," "natural-language E2E," "browser agent smoke test," "Playwright MCP test." Not for: Writing/maintaining deterministic scripted Playwright tests — that is playwright-automation. Testing your product's OWN LLM features — that is ai-system-testing. Related: playwright-automation, ai-system-testing, exploratory-testing, test-reliability, qa-project-context.
Test REST and GraphQL APIs with Playwright APIRequestContext, Supertest, or standalone HTTP clients. Covers schema validation with Zod 4/AJV, auth flow testing, CRUD lifecycle tests, error and header validation, pagination, and performance assertions. Use for “API test,” “endpoint test,” “REST test,” “GraphQL test,” “schema validation,” or “Postman replacement.” Not for consumer-driven contract verification (Pact, broker) — use contract-testing; browser UI flows — use playwright-automation. Related: contract-testing, test-data-management, ci-cd-integration, playwright-automation.
Audit a website or digital experience against its supplied source references for originality and plagiarism risk. Use when Codex must compare current or historical site output with reference pages, capture packs, screenshots, copy, brands, numbers, images, assets, videos, layouts, motion, or code; raise evidence-backed red flags; distinguish common visual grammar from distinctive copying; and propose concrete fixes without making unsupported legal claims.
Triages a repository's open GitHub issues and pull requests via the gh CLI. Optionally reviews and merges ready PRs — incrementally merging passing automated/bot PRs and maintainer-approved ones, and spawning review subagents for never-reviewed ones — then closes already-resolved issues with comments citing the resolving PR or commit, cross-links issues with their pending fix PRs, and assigns local-only priority and change-size estimates for everything outstanding. Use when triaging, grooming, or reviewing a repository's open issues and PRs.
Create and manage test data with factory patterns, fixture strategies, data anonymization, and synthetic data generation. Covers Fishery (TypeScript), FactoryBot (Ruby), Factory Boy (Python), database seeding, cleanup strategies, and GDPR-compliant data handling. Use when: "test data," "fixtures," "factories," "seed data," "synthetic data," "test database," "data anonymization." Not for: migration/integrity testing of the DB itself — use database-testing; environment provisioning and database branching strategy — use test-environments. Related: test-environments, database-testing, api-testing, unit-testing.
Fullstack development toolkit with project scaffolding for Next.js, FastAPI, MERN, and Django stacks, code quality analysis with security and complexity scoring, and stack selection guidance. Use when the user asks to "scaffold a new project", "create a Next.js app", "set up FastAPI with React", "analyze code quality", "audit my codebase", "what stack should I use", "generate project boilerplate", or mentions fullstack development, project setup, or tech stack comparison.
Guided journey from a working codebase grown slow and tangled to one measurably fast, cleanly bounded, and readable. Orchestrates eight skills phase by phase - working-with-legacy-code, clean-architecture, software-design-philosophy, refactoring-patterns, system-design, ddia-systems, release-it, pragmatic-programmer - every phase carries its method inline so it runs standalone, asking the user questions at every decision point and recording results in the project docs/ folder (PERFORMANCE.md, ARCHITECTURE.md, ARCHITECTURE-OPTIMIZATION-PLAN.md) so the journey resumes across sessions. Use when the user wants to make an app faster, untangle drifted boundaries, fix slow endpoints and queries, or says ''it works but it is slow and getting worse''. For an untested prototype, improve-code-quality; for an aged codebase you fear to touch, remove-technical-debt; for greenfield structure, design-code-architecture; for marketing-site page speed, improve-website. For one framework in isolation, invoke that skill directly.
React Testing Library: user-centric component testing with queries, user-event simulation, async utilities, and accessibility-first API. Use when writing React component tests, selecting elements by role/label/text, simulating user events, or testing async UI behavior. Keywords: React Testing Library, @testing-library/react, user-event, queries, render.
Use when writing, reviewing, or improving Go test code — including table-driven tests, subtests, parallel tests, test helpers, test doubles, and assertions with cmp.Diff. Also use when a user asks to write a test for a Go function, even if they don't mention specific patterns like table-driven tests or subtests. Does not cover benchmark performance testing (see go-performance).
Optimizes AI skills for activation, clarity, and cross-model reliability. Use when creating or editing skill packs, diagnosing weak skill uptake, reducing regressions, tuning instruction salience, improving examples, shrinking context cost, or setting benchmark/release gates for skills. Trigger terms: skill optimization, activation gap, benchmark skill, with/without skill delta, regression, context budget, prompt salience.
Test a playable browser game end to end with deterministic fixtures and real browser evidence. Use for gameplay QA, regression testing, controls, accessibility, responsive/mobile testing, save flows, console checks, performance smoke tests, and release verification.
Runs a Trailmark structural review gate over a branch, pull request, fix commit, release diff, or git ref range to detect new entrypoints, new tainted paths, removed validation or authorization calls, privilege-boundary drift, blast-radius growth, complexity growth, and newly reachable sensitive sinks. Use when reviewing a PR, branch, remediation commit, or release diff where graph-level security regressions should be checked before merge
Remove AI-generated patterns from QA reports, bug reports, test summaries, status updates, and quality communications. Detects and rewrites robotic test-result language, template-sounding status updates, inflated severity descriptions, and generic stakeholder reports — without inventing facts. Makes QA writing sound like a real engineer wrote it. Use when: "humanize report," "rewrite QA summary," "fix test report," "make this sound human," "clean up status update." Not for: general prose, blog, or marketing-copy cleanup — use the global humanizer skill. Not for: classifying or routing CI failures — use ai-bug-triage. Related: ai-bug-triage, qa-metrics, qa-dashboard, quality-postmortem.
Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Repeat this each time the operator corrects you. Use for /correct.
Cold-read the artifact you're focused on from a fresh, zero-context sub-session to confirm it stands on its own — a shower-thought reset for accumulated session bias. Use when a long session has worn away your fresh eyes and you can no longer tell whether the artifact in focus is clear to someone with no prior context; before a handoff, publish, or merge; or when you want a clean-room comprehension smoke test. Spawns a separate context-free reviewer; it diagnoses, it does not fix.
Apply Traceknot's ISTQB-aligned, evidence-bound QA process to repository changes across OMP, Codex, GajaeCode, Claude Code, and OpenCode, including session-scoped QA Board publication. Use for implementation verification, bug fixes, release checks, repository audits, defect confirmation, and residual-risk decisions without treating an agent's own completion claim as proof.
UX research and design toolkit for Senior UX Designer/Researcher including data-driven persona generation, journey mapping, usability testing frameworks, and research synthesis. Use for user research, persona creation, journey mapping, and design validation.
Audit any eval, metric, experiment, or benchmark for leakage: does external ground truth enter independently, or are the model, scorer, and designer just confirming a result no outside truth ever produced? Use before trusting any 'how we'll know it worked' — an A/B, a holdout, a score, a validation — and whenever a result feels too clean or self-confirming. Walks an 8-pattern leakage taxonomy and returns only the patterns that fire, each with an independence fix. Read-only.
Design environment strategy for testing across dev, CI, preview, staging, and production — Docker Compose test infrastructure, multi-stage Dockerfiles, seed-data lifecycle, per-PR preview environments, production parity, and external-dependency stubbing at the HTTP boundary. Use when: "set up test environment," "docker-compose for tests," "per-PR preview environment," "staging parity," "spin up test infra," "environment tiers." Not for: choosing mock-vs-stub-vs-fake per dependency — use service-virtualization; factory and fixture data patterns — use test-data-management; pipeline/Actions config — use ci-cd-integration. Related: test-data-management, ci-cd-integration, contract-testing, service-virtualization.
Runs a manual QA session for a PR, issue, or branch — publishes an interactive runbook the tester works through in parallel from the moment a plan exists, updated with AI verdicts and bugs at the end. Never touches the tracker itself. Unlike `om-auto-qa-pr`'s automated sign-off, this is human-in-the-loop and grows a local QA knowledge base. Use when the user says “test this for me,” “QA this PR,” “find bugs in this change,” or “walk through this issue for bugs”
After you create or change an artifact or skill, taste-test it with our own skills instead of trusting your in-session judgment — recursive self-improvement, made automatic. Use right after writing or editing anything, before calling it done, committing, or handing it off.
Testing guide for Capacitor apps and plugins. Covers web-layer unit and component tests with Vitest and mocked Capacitor plugins (`vi.mock('@capacitor/core')`, `registerPlugin`), Playwright for the web build, Appium E2E with NATIVE_APP / WEBVIEW context switching, native plugin unit tests with Swift Testing vs XCTest (what can migrate, `CAPPluginCall` patterns, `xcodebuild test` on a simulator) and Android JUnit, plus an agent-driven verification loop on simulators and devices (build, install, launch, screenshot, UI hierarchy, tap, logs) with `xcrun simctl`, `xcrun devicectl`, `adb`, Xcode MCP device tools, and live reload via `npx cap run --url` (Capacitor 9) or `-l --host --port` (Capacitor 8). Use when adding tests, mocking plugins, asking “does it work on device,” verifying a UI change on a simulator, migrating XCTest to Swift Testing, or setting up test CI. Do not use for crash log capture (ios-android-logs), WebView debugging sessions (debugging-capacitor), or build pipelines (capacitor-ci-cd).
Use when writing or running Unreal Engine tests, adding logging, or profiling a build. Also use when the user mentions 'UE_LOG', 'log category', 'DEFINE_LOG_CATEGORY', 'UE_LOGFMT', 'verbosity', 'check', 'ensure', 'ensureMsgf', 'verify', 'IMPLEMENT_SIMPLE_AUTOMATION_TEST', 'automation test', 'TEST_CLASS', 'CQTest', 'AFunctionalTest', 'latent command', 'Unreal Insights', 'TRACE_CPUPROFILER_EVENT_SCOPE', 'TRACE_BOOKMARK', 'stat unit', 'SCOPE_CYCLE_COUNTER', 'memreport', 'DrawDebugLine', 'UE_VLOG', 'gameplay debugger', 'ShowDebug', 'console command', 'CVar', or 'why is my frame time bad'. For module and target wiring, see ue-module-build-system; for editor tooling, see ue-editor-tools.
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.