Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Structured visual and usability audit of existing interfaces — landing pages, SaaS apps, portfolios. Screenshot-first review against taste rules, Nielsen heuristics, and accessibility floor; severity-ranked findings with specific fixes; before/after verification. Use when asked to critique, review, or improve an existing UI.
Use when completing implementation, fixing bugs, refactoring code, or any time you need to verify the test suite passes. Also use when tests fail and you hear "pre-existing" or "not my changes" — enforces strict code ownership. Ensures MECE coverage (no overlap, no gaps) and that ALL test categories including E2E are executed.
Set up the local dev environment, seed data, and API keys to test the staff-only managed migrations MCP tools (managed-migrations-support-list, managed-migrations-support-get) end to end. Use when testing batch import support tooling, debugging MCP tool responses or discovery (tools not appearing), or verifying the support API before deploying. Covers the discovery gate: hidden scope, is_staff, user:read, and why wildcard keys and OAuth never work.
Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs. Use when issues or external PRs need categorising, verifying, and turning into agent-ready briefs. Triggers on: triage, triage the backlog, review these issues.
Static performance audit for Unity projects. Triggers: /perf, /perf-audit, 'audit performance', 'optimiser performance', 'anti-pattern performance', 'frame rate', 'profiler', 'budget fps'. Analyses the project's C# code to detect performance anti-patterns (CPU, GPU, memory). Produces a report with severity, file:line locations, and concrete before/after fixes.
Adjudicate whether users can operate an interface, and run heuristic evaluation. Use when the question is operability rather than looks — is it usable, hard to use, confusing, where do users get stuck; heuristic evaluation, Nielsen heuristics, usability audit, severity rating; the UX laws (Fitts, Hick, Miller/Cowan, Jakob, Tesler, Doherty, peak-end, Zeigarnik, aesthetic-usability); Gestalt grouping, affordances, signifiers, mapping, feedback, cognitive load, recognition over recall; picking among navigation, form, search/filter, table/data, feedback, action, disclosure, or onboarding patterns; or usability-side accessibility (WCAG POUR, inclusive design). Not for: the visual look or aesthetic audit (use core design/audit); the words/microcopy themselves (use content-design); the route through time, IA, or funnel (use journey); persuasion or conversion mechanics (use behavioral); truthful chart/data encoding (use data-viz).
Use this skill to gate CI on Jetpack Compose stability — catch when a composable becomes unskippable/unrestartable or a parameter goes stable → unstable, before it ships and tanks recomposition. Covers the Compose Stability Analyzer Gradle plugin's `stabilityDump` (write a `.stability` baseline) and `stabilityCheck` (compare current compilation against it, fail on regression) tasks, the `composeStabilityAnalyzer { stabilityValidation { … } }` DSL (`failOnStabilityChange`, `ignoreNonRegressiveChanges`, `ignored*` lists, `allowMissingBaseline`, `stabilityConfigurationFiles`), the `@IgnoreStabilityReport` annotation, committing `app/stability/app.stability` as a team baseline, the deliberate baseline-update workflow, and GitHub Actions wiring (`needs: build`, since the analysis reads compiled output). Use when the user mentions "stabilityCheck", "stabilityDump", "compose stability analyzer", "stability baseline", "@IgnoreStabilityReport", "composeStabilityAnalyzer", or "fail the build on stability changes".
Implement and deliver an authorized change end to end — verify, open the PR, merge, and confirm post-merge state — using live-state gates, durable interruption handoffs, and live-state-first resumption. Use when a user grants end-to-end delivery authority for a specific change and the work may cross tool-call limits, context exhaustion, worker loss, or session interruptions before the delivery boundary is reached. Do not use for plain fixes with no delivery directive, for granting merge or post-merge authority the user did not grant, or for designing release pipelines (use release-engineering for that).
Web automation, debugging, and E2E testing with Playwright. Handles interactive (login, forms, reproduce bugs) and passive modes (network/console capture). Triggers on "e2e test", "browser test", "playwright", "screenshot", "debug UI", "debug frontend", "reproduce bug", "network trace", "console output", "verify fix", "test that", "verify change", "test the flow", "http://localhost", "open browser", "click button", "fill form", "submit form", "check page", "web scraping", "automation script", "headless browser", "browser automation", "selenium alternative", "puppeteer alternative", "page object", "web testing", "UI testing", "frontend testing", "visual regression", "capture network", "intercept requests", "mock API responses". PROACTIVE: Invoke for security verification, UI fix verification, testing forms/dropdowns, or multi-step UI flows. ON SESSION RESUME - check for pending UI verifications.
L2 AI-driven web UI testing for a React/Vite dashboard app. Originally authored against the Onsager Dashboard (the body's route table + file paths are Onsager-shaped); other React dashboards fork the procedure and substitute their own routes / test paths. Use when testing UI on PRs, triaging L1 test failures, or verifying UI behavior at desktop + mobile viewports. Triggers include "test the UI", "check the dashboard", "triage L1 failure", "run L2 tests", "validate this PR", "exploratory test the web app".
WordPress plugin architecture review and WordPress.org submission standards. Use when reviewing WordPress plugin code, auditing plugin architecture, preparing WordPress.org plugin submission, checking plugin best practices, analyzing custom post types, taxonomies, Settings API, hooks system, internationalization, or when user mentions "plugin review", "plugin development", "plugin best practices", "WordPress.org submission", "Plugin Check", "plugin headers", "activation hook", "deactivation hook", "uninstall", "custom post type", "taxonomy", "Settings API", "hooks", "actions", "filters", "i18n", "text domain", "prefixing", "namespacing". Detects issues in plugin architecture, lifecycle hooks, WordPress.org compliance, and API integration.
Use when you have a spec or requirements for a multi-step task, before touching code. Produces an engineering plan complete with TDD tasks, DRY/SOLID/YAGNI principles, a required Test Plan & Verification section, and a coverage target — then auto-runs /plan-eng-review as an independent double-check before execution.
Load PROACTIVELY when task involves accessibility compliance or inclusive design. Use when user says "check accessibility", "audit for WCAG", "fix screen reader issues", "add keyboard navigation", or "check color contrast". Covers WCAG 2.1 AA compliance across semantic HTML, ARIA patterns, keyboard navigation, screen reader support, color contrast ratios, form accessibility, media alternatives, and focus management. Produces structured audit reports with severity ratings.
Evaluate, test, and track an AG2 Agent offline. Build a Suite of tasks, run the agent with run_agent, and grade answers with prebuilt scorers (final_answer_matches, tool_called, no_tool_errors, token_budget) or a custom @scorer — including the agent_judge LLM judge. Read the RunResult scorecard (pass_rate, score_stats, value_counts), gate it in CI with deterministic TestConfig cassettes, persist to store_dir and diff runs to catch regressions, and grade existing traces with evaluate_traces. Use when the user wants to evaluate, test, grade, or benchmark an agent, build a CI or regression gate, or score correctness, tool use, cost, or quality. To compare builds head-to-head or on a leaderboard, see ag2-eval-comparison.
Use when writing, recording, updating, validating, or troubleshooting Agent Host end-to-end and real-provider integration tests under src/vs/platform/agentHost/test/node/e2e and providerIntegration. Covers adding a cross-provider test, re-recording fixtures after an SDK bump, required cross-platform Azure validation, gating non-deterministic or platform-specific tests, and diagnosing replay cache misses.
Agent design advisor and review tool. Based on 12-Factor AgentOps best practices, for: (1) discussing Agent architecture designs; (2) reviewing the design of existing Agents/Skills/workflows, finding issues and giving improvement suggestions. Trigger words: review my agent, help me analyze this skill, agent design, agent optimization, help me review this workflow, what's wrong with this agent, how to design an agent, agent architecture consulting.
Interview-driven assistant for customers with Kubernetes-based production setups who are getting started with Antithesis. Helps the customer (and the Antithesis engagement team) figure out what their k8s setup contains, what to keep, drop, or stub for testing, and produces structured questions for ops plus an escalation packet when stuck.
Use to fix UI gaps according to a UI acceptance review report; not for an initial UI review, code review follow-up, or UI development without a report. Verify each item against screenshots and targets before fixing and self-checking; rethink the approach when a stagnation warning appears, then record the submission and hand it back for review
Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X', 'what could this break', or reviewing a small diff you don't trust.
Build or improve a Coval dashboard with metric visualizations backed by real data. Creates new dashboards from scratch or rebuilds existing ones by analyzing usage patterns, metric frequency, and data density. Use when user says "create a dashboard", "build a dashboard", "improve my dashboard", "add widgets", "visualize my metrics", "make a performance dashboard", or "dashboard for my runs".
Guidance for converting COBOL programs to modern languages (Python, Java, etc.) while preserving exact behavior and data format compatibility. This skill should be used when modernizing legacy COBOL applications, converting COBOL business logic to modern languages, or ensuring byte-for-byte output compatibility between COBOL and its replacement.
Use when implementing any substantial feature, multi-file modification, or architectural change - produces a plain-language walkthrough of every alteration so the developer can verify genuine understanding before committing, preventing the accumulation of cognitive debt where code ships faster than comprehension
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.
Analyze the completeness of a plan, report, or change proposal and its impact assessment on the project. Use when: the user provides a document (plan, technical debt assessment, change proposal, RFC, ADR, security report, etc.) and asks to analyze its quality, completeness, or potential risks. Trigger: /custom-skills-plan-analyze @file path — applies whether the request is made in Chinese or English.
Design and create a simulation persona for testing an AI agent. Guides through use case selection, voice and language configuration, behavior prompt crafting, and interruption calibration. Use when user says "create a persona", "design a persona", "set up a test persona", "configure simulation persona", or "build a caller profile".
Optimize Django and pytest-django test execution in CI with cache configuration, slow-test splitting, database reuse strategy, parallel workers, pytest-xdist, CircleCI/GitHub Actions/Jenkins/Travis patterns, and full-coverage safeguards. Use when CI test jobs are slow, flaky under parallelism, missing slow-test coverage, or need a local-vs-CI test command design.
Mock Django test boundaries safely with override_settings, pytest settings, autospecced unittest.mock objects, output/input capture, requests-mock, VCR.py, outbound HTTP blocking, and time-freezing tools. Use when tests need to replace settings, HTTP calls, time, command output, stdin, or external services without broad fragile MagicMock patches.
Safely parallelize Django and pytest-django test suites with Django --parallel, pytest-xdist, test isolation checks, randomized order detection, shared-resource sharding, locks, and load balancing. Use when enabling parallel tests, diagnosing failures under parallel execution, handling flaky Django tests, or making caches, files, queues, and external resources safe across workers.
Profile and measure slow Django test suites with Django's runner, pytest-django, shell timing, py-spy, cProfile, pytest durations, and profiler visualizations. Use when a Django project has slow tests, unclear test-runtime bottlenecks, CI timing problems, startup overhead, database setup overhead, or a request to find the slowest tests before optimizing.
Backlog triage protocol for Engram: audit open issues and PRs, classify each item, infer maintainer ideology from comments, and produce an actionable disposition report. Trigger: Auditing open issues or PRs, triaging the backlog, reviewing contributor submissions as a maintainer, or applying triage to any GitHub repo.
Plan, implement, review, and validate general ets_runtime changes with a planner/worker/reviewer workflow. Use when working under arkcompiler/ets_runtime, or when handling ets_runtime feature work, bug fixes, refactors, test additions, and compile-validation tasks.
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.