Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Use when reviewing Playwright or Cypress E2E specs, Page Objects (POM), PRs, pull requests, patches, diffs, or changed test files; when asked to review tests, audit test quality, or find weak, flaky, or silently passing tests; when tests pass CI but prove nothing or miss bugs; when auditing missing awaits, vacuous or always-passing assertions, anti-patterns, or finding-linked coverage suggestions; or when validating passing tests with assertion mutation or app-fault probes. Not for debugging a test that is currently failing at runtime (use playwright-debugger / cypress-debugger).
Guides end-to-end Meta VR and Horizon OS app submission to the Meta Horizon Store — build validation, store-readiness checks, asset preparation, upload, and submission tracking. Use when preparing a Meta VR app for store publishing. Build paths: all Meta VR app stacks; use hz-quest-verify-first if the build path is unclear.
Write and run unit tests for custom Omni Gateway policies built with the Policy Development Kit (PDK) — wire up `src/tests/`, build a first `UnitTestBuilder` test, mock HTTP/gRPC upstreams with closures or `TraceBackend`, factor reusable `TestConfig` helpers, assert on responses / headers / violations, run with `make test` or `cargo test`, troubleshoot init-sleep races, authority mismatches, and feature-gate skew. Use whenever the user mentions "PDK unit test", "pdk-unit", "UnitTestBuilder", "test my policy", "cargo test PDK", "mock backend PDK", "Omni Gateway policy unit testing", `with_http_upstream_from_authority`, `with_entrypoint`, `TraceBackend`, or asks "how do I test an Omni Gateway policy", "how do I mock an upstream in pdk-unit", "why is my policy timer not firing in tests". For full `pdk-unit` API reference see `pdk-templates/templates/unit_testing.md`. For scaffolding / build / publish see `develop-pdk-policy`.
Implement the fix for a GitHub issue from its RCA artifact (created by piv-investigate-issue) — drift-check the plan, branch, implement, add regression tests, and validate. Use after the investigation artifact exists and you're ready to fix the issue.
ALIAS — merged into the unified `obsidian` skill (v2.0). Use the `obsidian` skill instead. Build, validate, and publish Obsidian plugins. Redirects to obsidian skill for plugin development, ESLint rules, boilerplate generation, accessibility, and submission validation.
Write and run integration tests for custom Omni Gateway policies using the `pdk-test` framework — Docker-based, real Omni Gateway routing, `#[pdk_test]` macro, `TestComposite` orchestration, `HttpMock` / `GrpcBin` backends, `reqwest` assertions. Use whenever the user mentions "PDK integration test", "pdk-test", "functional test PDK", "#[pdk_test]", "TestComposite", "FlexConfig", "tests/requests.rs", "make test", or asks "how do I test my policy against real Omni", "how do I set up Docker-based tests for PDK", "why does my pdk-test timeout", "how do I mock a backend in integration tests".
Migrates and converts test automation scripts between Selenium, Playwright, Puppeteer, and Cypress. Use when the user asks to migrate, convert, or port tests from one framework to another; rewrite tests in a different framework; or switch from Selenium to Playwright, Playwright to Selenium, Puppeteer to Playwright, Cypress to Playwright, or vice versa. Triggers on: "migrate", "convert", "port", "selenium to playwright", "playwright to selenium", "puppeteer to playwright", "cypress to playwright", "rewrite tests in", "switch from [framework] to [framework]".
Run deterministic accessibility audits and regression gates on web projects, especially large sites with many routes and shared templates. Combines axe-core and optional Lighthouse with template-aware sampling, stable finding fingerprints, accepted baselines, standards evidence mapping (WCAG 2.1 AA default, WCAG 2.2 AA, EN 301 549), manual check guidance, and structured reporting. Output is configurable: markdown report only, markdown plus machine-readable JSON, or markdown plus issue tracker integration. Use this skill whenever the user mentions “accessibility audit”, “a11y audit”, “WCAG audit”, “accessibility check”, “compliance scan”, “accessibility baseline”, “new accessibility regressions”, or asks to check a web project for accessibility issues. Also trigger when the user wants evidence for WCAG conformance review or mapping to a specific standard (WCAG 2.2, EN 301 549 / European Accessibility Act, CAN-ASC-6.2, ADA/AODA)
Monitor a shipped release after merge, publication or deployment. Verify published packages, production behavior, installed plugins, and late CI results or user reports until the observation window is clear; use babysit for PR readiness before release.
End-to-end remediation workflow for PR review feedback by PR number. Use when Codex must export CodeRabbit issues for a PR, fix every issue completely, commit all fixes in a single commit, and resolve GitHub review threads afterward. Don't use for general PR reviews unrelated to CodeRabbit, draft PRs without review threads, or merge-strategy decisions.
SUPERSEDED by /claudex-loop (formerly /crucible; adds a Phase 0 research/recon pass + rebuilt interview) — prefer that skill unless you explicitly want this one. Two-act plan hardening. ACT 1 (you ↔ Claude) — Claude interviews you relentlessly about a plan or design, one question at a time, recommending an answer for each and exploring the codebase when it can answer itself, until every branch of the decision tree is resolved. ACT 2 (Claude ↔ Codex) — Claude writes the locked plan to PLAN.md and OpenAI Codex adversarially reviews it in a read-only sandbox (VERDICT:APPROVED/REVISE); Claude revises and re-submits to the SAME Codex session until APPROVED or a MAX_ROUNDS cap, then you sign off before any code. Use when the user says "/grill-me-codex", "grill me then have codex review", "grill me and stress-test the plan", "interview me about this plan then get a second model on it", or is about to build something high-stakes (auth, schema, concurrency, migrations, payments) and wants both alignment AND a cross-model sanity check before implementation. Builds on Matt Pocock's grill-me (MIT). For the docs-aware variant use /grill-with-docs-codex; if you already have a plan and want only the Codex review use /codex-review. NOT for reviewing already-written code (use /codex:review) and NOT for trivial changes
Generates Karma test runner configurations for browser-based JavaScript testing. Works with Jasmine, Mocha, or QUnit. Use when user mentions “Karma”, “karma.conf.js”, “browser test runner”. Triggers on: “Karma”, “karma.conf”, “karma test runner”, “browser-based JS test”
Run a standardized benchmark to evaluate AI trading agent capabilities on the Manic Trade platform. Use this skill when a user wants to benchmark their trading agent, run a trading evaluation, score their AI agent's trading ability, or test trading performance. Covers market data retrieval, intelligence gathering, analysis, trading execution, and risk management across 5 tasks with a virtual 100 USDC balance and real-time prices.
Complete browser automation and web testing with Playwright. Automatically detects development servers, manages server lifecycles, and writes clean test scripts in /tmp. Test pages, fill out forms, capture screenshots, check responsive design, validate UX, test login flows, check links, debug dynamic web apps, and automate any browser task. Use when the user wants to test websites, automate browser interactions, validate web features, or perform any browser-based testing.
Reference for adhere, the linter for coding conventions a normal linter cannot check, judged by TypeSafe AI's Jev. Covers its commands, the Markdown rule format and how to word a rule, the config, presets, shared rules, comments and suppressions, the cache, reading a report, and tuning a noisy rule. Use when writing or editing adhere rules, configuring adhere, reading its findings, or answering questions about it. To set adhere up in a repo, use adhere-setup; to fix findings, adhere-fix.
Use when writing, reviewing, or refactoring TypeScript or React code with a focus on craftsmanship—naming, function and component shape, error handling, data modeling, tests, and abstraction. Translates Robert C. Martin's Clean Code principles into modern TS+React idioms (TS 5.x, React 19), with first-class “When NOT to apply” guidance and a Meta category for principle conflicts (DRY vs. SRP, small functions vs. deep modules, type safety vs. ergonomics). Triggers on code review, refactoring for clarity, naming, function/component design, “is this clean?”, “make this more readable,” “right abstraction?”—even when the user doesn't say “clean code.” Does NOT cover React-specific APIs (RSC, hooks API surface)—use the `react` skill. Does NOT cover TS compiler performance or tsconfig—use the `typescript` skill.
Detect and reconcile drift between a feature flag’s in-code SDK fallback default and its LaunchDarkly default rule (fallthrough). Use when a flag’s default rule changed, the user asks to detect flag drift, check whether a hardcoded default still matches LaunchDarkly, sync an in-code default, or open a PR reconciling a fallback value, without removing the flag or its evaluation.
Cổng sức khoẻ tổng / tuyến phòng thủ cuối của framework overstack — gõ /medic (hoặc `medic` ở CLI) để CHỨNG MINH hệ còn khoẻ trong MỘT lệnh: luật còn cắn (harness-doctor fire-drill), validator không lệch bản (drift), docs khớp đĩa, code compile, eval không regress, backstop git sống. Hub 1-tên — mô tả PHẠM VI thay vì nhớ subcommand (`medic` = all · `medic rules` · `medic docs eval`). Dùng trước commit/PR, sau khi pull/đổi máy, khi nghi một rule không chặn nữa, hoặc vừa thêm skill/rule/generator (medic tự báo nếu quên hàng rào). Trigger: /medic, "medic", "chạy medic", "hệ còn khoẻ không", "rà luật có cắn không", "cổng phòng thủ cuối", "health gate", "last line of defense".
RED-GREEN-REFACTOR for production behavior changes, followed by mutation testing or alternate evidence once at the end-of-phase PR-readiness gate. Use before implementing new features, bug fixes, or any changed observable behavior, and as the governing workflow for mixed implementation work. Load it for any request to add, implement, or fix production code, including a bug report that calls the fix a one-liner or a quick change in a named file — a small fix still starts from a failing behavior test, not from an edit. This is the workflow, not the whole toolkit — load it alongside, not instead of, functional for logic or data-shaping changes (pricing, tiering, filtering, merging, sorting, totals), refactoring when a change also tidies already-tested code, front-end-testing (react-testing for React components) when the behaviour under test lives in a browser — a form, a button, a spinner, a page — and any architecture skill the repository declares (hexagonal-architecture, domain-driven-design). Do not use for pure behavior-preserving refactoring or mechanism reduction; those start from passing proportionate evidence via refactoring or reduce-system-complexity, never fabricated RED or structural mutants. Not for plan-only requests; use planning first for significant multi-slice work.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
Senior CAPA Officer specialist for managing Corrective and Preventive Actions within Quality Management Systems. Provides CAPA process management, root cause analysis, effectiveness verification, and continuous improvement coordination. Use for CAPA investigations, corrective action planning, preventive action implementation, and CAPA system optimization.
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
Use when reviewing GDScript or C# Godot code — a checklist of best practices, common anti-patterns, and Godot-specific pitfalls. Triggers on “review this script”, “check my code”, “any issues with this”, “what's wrong with this code”, including a short pasted snippet.
Generates Selenide tests in Java. Concise UI testing framework built on Selenium with automatic waits and fluent API. Use when user mentions "Selenide", "$(selector)", "shouldBe(visible)", "Selenide Java". Triggers on: "Selenide", "$() selector", "shouldBe", "shouldHave", "Selenide test".
Wix Design System component reference. Use when building UI with @wix/design-system, choosing components, checking props and examples, or writing tests with component testkits. Triggers on "what component", "how do I make", "WDS", "show me props", "testkit", "driver", or component names like Button, Card, Modal, Box, Text.
Bug investigation and fix workflow. Triggers: 'debug', 'fix bug', 'investigate issue', 'something is broken', or /debug. Hotfix track for quick fixes, thorough track for root cause analysis. Do NOT use for feature development or refactoring. Do NOT escalate to /ideate unless the fix requires architectural redesign.
Review AI-generated code changes before committing using GitHuman. Use when reviewing code changes, creating code reviews, checking what the AI agent wrote, preparing to commit, or when the user mentions “review,” “GitHuman,” or “before commit.”
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.