Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Generic test-writing discipline: test quality, real assertions, anti-patterns, and resistance to rationalization. Use when writing tests, adding test coverage, or fixing failing tests for any language or framework. Complements language-specific skills.
Use when auditing a manuscript item by item against a reporting guideline or risk-of-bias tool. Covers 49 reporting guidelines and risk-of-bias tools (STROBE, CONSORT, STARD, TRIPOD+AI, PRISMA, QUADAS and more), marking each item PRESENT, PARTIAL or MISSING. Not a reviewer critique (/self-review).
Use when validating an App Builder app before submitting to Adobe Exchange, or when the user mentions Adobe Commerce app compliance, extension review, marketplace submission, or Adobe Exchange listing. Checks security requirements, project structure, documentation completeness, and dependency health; reports MUST-have blockers and NICE-to-have recommendations and walks through each finding interactively.
De-risk product decisions with UX research: method choice, study design, findings synthesis and research operations (interviews, usability tests, surveys, research repository and consent practice), backed by a library of reference guides and templates.
Spec-driven feature work that freezes obligations instead of the plan: one human-reviewed plan with EARS criteria, path, entities, interface and one-way doors, then proof-backed checks, then build, then an independent Verifier. Use when the user says "tlc-spec-lean", "plan feature", "specify feature", "write the checks", "build this plan", or "verify work". Do NOT use for standalone design documents unattached to a feature, architecture decomposition analysis, or work that already has a task list or checklist to execute.
Expert knowledge for Azure DevTest Labs development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when managing lab VM images, ARM/CI-CD automation, RBAC/Key Vault security, hub-spoke networking, or quotas, and other Azure DevTest Labs related development tasks. Not for Azure Lab Services (use azure-lab-services), Azure Dev Box (use azure-dev-box), Azure Virtual Machines (use azure-virtual-machines), Azure Virtual Desktop (use azure-virtual-desktop).
Organizes, redacts, and reports GitHub bugs for chengfeng-videocut. Use when the user asks to report a bug, report an issue with 剪口播, submit a GitHub Issue, tell the developers about a problem, or continue submitting a bug draft they have previewed. Do not use for feature requests, general troubleshooting, code commits, or automatic reporting without user confirmation.
Diagnose PostHog Surveys configuration and responses across all five SDKs (web/posthog-js, iOS, Android, Flutter, React Native). Use whenever a Surveys support ticket is pasted ("survey not showing", "fewer responses than expected", "responses disappeared", "responses are incomplete", "only the first question was answered", "the user says they didn't mean to submit", "survey shows on wrong platform"), or when diagnosing why a survey does or doesn't display. Covers the eligibility pipeline, how a response actually gets stored (partial responses, branching, optional questions, auto-submit), cross-SDK feature parity, the known-cause catalog, read-only diagnostic queries, staff access, and the customer-reply style guide.
Review Django and Python changes for clarity, consistency, maintainability, ORM or DRF anti-patterns, and project conventions while preserving behavior. Use after Django code changes or when the user explicitly requests review. Report findings by default; apply refinements only when the user expresses explicit edit intent or the host has already authorized edits.
Scans React codebases for security, performance, correctness, accessibility and architecture issues and reports a 0-100 health score, with severity-ranked findings and a regression check to run after changes. Can also run a focused UI design audit and a runtime performance trace.
Drive iOS Simulator, Android emulator/device, and physical iPhone/iPad screens for AI agents. Use when asked to automate a simulator or emulator, drive a real iOS device, tap/swipe/type on a device, describe UI, take a screenshot, or interact with a mobile app.
Use whenever reviewing code for quality and correctness — a diff, PR, module, or subsystem — producing verified, severity-ranked findings on the RV ledger. Not for comprehension tours (walkthrough) or doctrine-conformance hunts (inquisition, user-invoked only).
Three-stage code review protocol covering spec compliance, code quality, and domain integrity. Use this skill whenever the user asks to review code, prepare or check a PR, assess implementation quality, verify code against a spec or acceptance criteria, or audit for security and domain modeling issues. Triggers on: "review this code", "review my PR", "check implementation against spec", "code quality audit", "does this match the requirements", "review for security issues", "check for primitive obsession", "monetary precision review", "review test coverage gaps". Also activates when the user wants structured PASS/FAIL verdicts per requirement, severity-rated findings, or a gated review that blocks on critical issues. NOT for: style/formatting linting, debugging runtime errors, writing new code, or automated CI checks.
Automated code review workflow using OpenAI Codex CLI. Implements iterative fix-and-review cycles until code passes validation or reaches the iteration limit. Use when building features requiring automated code validation, security checks, or quality assurance through Codex CLI.
Structured UI design review — existing code (React/JSX, CSS, Tailwind) and, when behaviour matters, the running app in a real browser — reported as a prioritised Before / After / Why table. Covers visual hierarchy, spacing, typography, colour & contrast, component states, motion, responsiveness, accessibility, multi-page flow & navigation, and interaction continuity — grounded in Refactoring UI and Emil Kowalski's principles. For animation/jank/FPS, focus order, and cross-page UX it can drive Chrome via chrome-devtools-mcp to capture what a screenshot can't. Trigger when the user asks to "review this UI", "design review", "critique this component/screen/page or multi-page flow", asks why something "looks off", "looks AI-generated", or "looks like a wireframe", or wants to raise visual polish. For building UI from scratch use web-taste; for the full animation set see emilkowal-animations.
Use when testing, debugging, or making targeted improvements to rendered frontend apps through the Build Web Apps or web dev plugin: local dev servers, UI regressions, interaction bugs, console errors, responsive layout, and visual QA. Check whether the Browser plugin is available and use it first when it is; otherwise use regular Playwright with the recorded reason
Port TON smart contracts from FunC (.fc/.func) to modern Tolk (.tolk) with Acton: use acton func2tolk when helpful, then refactor storage/messages/opcodes into typed structs and serialization, implement Acton-style entrypoints, generate wrappers, migrate JS/TS tests to native Tolk tests, and use acton build/test/script/verify/disasm to preserve TL-B compatibility and behavior. Use when asked to convert, port, or modernize FunC contracts into idiomatic Tolk.
A WorkBuddy/OpenClaw adaptation of gstack. Derived from gstack (Y Combinator Garry Tan), it is optimized for AI assistant platforms such as WorkBuddy/OpenClaw. Includes 15 specialized tools covering the complete development workflow from product ideation to code release.
Analyzes and improves Marp Markdown presentations using SlideGauge quality scoring — checks accessibility (alt text, contrast), code, color, content density and layout on the Markdown source. Use as a companion to marp-slides, run after slide creation.
Design or review testing strategy, test portfolios, and test quality. Use for unit/integration/contract/E2E choices, flaky or brittle tests, mocks and test doubles, BDD review, legacy-code testing, production QA, and testing LLM or AI-generated systems. Also covers TCRDD / TCR (test && commit || revert, red-green-refactor, baby steps, commit on green, revert on failure, approval-gated TDD) and HTTP API smoke tests (smoke test, critical path test, CI gate, Hurl, .hurl files, curl smoke test).
Find where an AI/LLM application is failing in production and surface the failure patterns, working from real traces. Use when someone wants to understand what's going wrong with an AI feature, find and categorize failure modes, triage errors, or investigate quality issues (wrong answers, ignored instructions, hallucinations, tool misuse) — "what's failing in my agent", "surface error patterns", "why are the responses bad", "find the common failure modes", "what should I fix next". Covers scoping to one use case, finding failing traces by whichever signal fits the context (code errors, metric outliers, trace-type slices, manual review, existing-eval spikes, clustering), and reading them into a ranked failure taxonomy.
Audits interface source code (Swift, UIKit, AppKit, React, Vue, Svelte, Angular, Compose, Android XML, Flutter, CSS, HTML) for Apple HIG-aligned interface and accessibility problems by running the HIG Doctor CLI, then reports findings by severity and helps remediate them. Review evidence, not certification.
Comprehensive LLM security assessment against OWASP Top 10 for LLM Applications 2025. Use when reviewing LLM-integrated applications, RAG pipelines, chatbots, AI agents, or GenAI features. Covers prompt injection, data poisoning, supply chain, excessive agency, and more with real-world attack scenarios and testing methodologies.
Screenshot localhost/local dev-server pages across viewports and compare them for visual regression. Use when asked to "screenshot my local site", "capture localhost pages", "visual diff", "compare screenshots", "responsive screenshots", "check breakpoints", "visual regression", or capture a Portless app at a named .localhost URL. Not for public URLs or writing e2e tests.
Analyze MCP server connection issues and validate implementations against the latest specification. Use when troubleshooting tools/list or tools/call errors, stdio, SSE, or HTTP transport issues, resources or prompts routing problems, or when inspector-based reproduction tests are needed.
Use when the user asks to "write a QUnit test", "fix a failing QUnit test", "add a QUnit module", "modernize QUnit tests", "migrate from QUnit 1", or mentions QUnit-specific constructs such as assert.async, nextUIUpdate, Core.applyChanges, sinon sandbox, asyncTest, or QUnit.module. Covers coding standards for OpenUI5/SAPUI5 unit test files: const/let over var, arrow functions over .bind(this), async/await over assert.async(), assert.expect() in every async test, sinon.createSandbox(), descriptive test names, beforeEach/afterEach module isolation, nextUIUpdate vs Core.applyChanges rules, try/finally teardown in helpers, QUnit 1 to QUnit 2 globals migration, and non-ASCII character avoidance.
Execute comprehensive client-side injection vulnerability assessments on web applications to identify XSS and HTML injection flaws, demonstrate exploitation techniques for session hijacking and credential theft, and validate input sanitization and output encoding mechanisms.
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.
Plan verification and validation campaigns for simulation codes using manufactured solutions, canonical benchmark problems, grid/time refinement, uncertainty propagation, and pass/fail acceptance criteria. Use when an agent needs to prove a solver, model, or result is trustworthy rather than only plausible.
Проводит независимое ревью изменений кода без их исправления. Используй, когда пользователь явно просит проверить код, коммит, ветку, pull request или diff на соответствие задаче, корректность, безопасность, производительность и качество тестов. Не используй, когда пользователь просит изменить код, реализовать задачу или сначала найти причину проблемы.
Author continuously-running online evaluations in PostHog AI observability, grounded in real failure modes you've identified. Use when the user wants evaluations that automatically score new generations or whole traces going forward — "create an eval to catch X", "continuously check that responses do Y", "turn these failures into evals". Covers letting the explored data decide how many evals to create, proposing that set for the user to pick, choosing the target and eval type (hog / llm_judge / sentiment), configuring a provider and model for an llm_judge eval (a provider key gates enabling, not creation), scoping which generations trigger it via conditions, creating disabled, verifying scope, enabling, and backfilling past data. Proposes a sentiment eval when no failure mode is worth catching. Finding and ranking the failure modes worth evaluating is its own job — use exploring-ai-failures first. To debug or manage evaluations that already exist, use exploring-llm-evaluations.
This skill should be used when the user asks to "optimize my Next.js app", "why is this page slow", "reduce my bundle size", "improve Core Web Vitals", or "run a Lighthouse audit". Diagnoses and fixes Next.js frontend performance issues using Lighthouse, bundle analysis, and animation best practices — covering LCP, TBT, and CLS.
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.