Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Router for HelpMeTest QA work. Bare /helpmetest is the orchestrator: it reads the project, probes it live, explains what it finds, and works through the code or environment fix with you. Existing tests are immutable evidence: never modify, skip, weaken, disable, or delete one to get green; paste literal test output before claiming pass. auto/autonomous: the same work hands-off, no checkpoints, one report at the end — only when the user asks for it. tdd: write new tests. fix: diagnose red tests and repair product/environment. mobile: Android/iOS/APK/IPA. desktop: Mac/Linux/Electron. fakemail: verification code/inbox. ssl: cert/TLS/DNS/WHOIS/SPF/DKIM. doc2html: PDF/DOCX/EPUB→HTML. auth: Save As/2FA/TOTP. api: REST/GraphQL/endpoint. proxy: localhost/tunnel/port. terminal: Jest/pytest/bun test. ci: GitHub/GitLab CI. ui: screenshot/visual/viewport. interactive: explore/debug selector. discover: map app/PRD. report: health check. coverage: gap analysis.
Generate thorough, interactive HTML testing checklists — a real test plan organized into end-to-end flows, with pass/fail/blocked step states, a progress bar, filter and search, and copyable, syntax-highlighted command snippets. Always ends with a Submit button that returns every step's state and notes for failure triage and fixes. Use whenever the user wants to test, QA, verify, or validate a change, feature, release, PR, or bug-fix batch. Embedded snippets pass a redaction step so credential-shaped values never land in the artifact.
Huawei Cloud MRS Spark SQL specification checking skill. Performs comprehensive SQL statement checking for MRS Spark, including syntax validation, specification compliance, and performance risk detection. triggers: "Spark SQL review", "check Spark SQL", "检查Spark SQL", "Spark SQL检查", "Spark SQL规范", "Spark SQL语法".
Runs continuous AI iteration loops that repeat build-test-fix cycles until success criteria are met. Use when building features requiring test-driven refinement, implementing tasks with clear pass/fail criteria, or automating iterative improvement workflows.
AI-powered browser automation SDK for web scraping, testing, and workflow automation. Use when automating web browsers, extracting data from websites, testing web applications, or building web automation workflows. Supports both API key and AWS credential authentication.
Use when reviewing/judging a finished user-flows document to decide whether a downstream wireframing pass can enumerate every screen and whether each path is complete, walkable, resilient, accessible, and sound — an acceptance gate, not authoring. A user-flows doc is the navigation/interaction graph: entries + IA frame, happy path, branches, error/recovery + edge states, resilience, flow-level accessibility, screens traversed. Judges it against a single-sourced bar: goals map to flows (no orphans), entries+exits defined, branches resolve, no dead ends, states (incl. loading+success) covered, irreversible actions guarded, every path keyboard/ AT-completable, the flow objectively sound, notations synced, screens enumerable; plus a delta-scoped review when amending. Emits exactly `VERDICT: approve|revise` with actionable findings. Approves a doc meeting the bar (no false-revise on a thin one), revises only on a named gap. Not for authoring, not for wireframes, not for the PRD.
Find defects in a change with independent read-only reviewers. Judge quality that no command can settle, such as "this API design is good" or "this UI is not slop". Judge it against criteria written before anyone looks at the work. Use when the user asks for a defect review or a bug hunt on a change. Read this skill when the user asks whether a design, a UI, a name, or prose is good. Use it when a UI, public interface, name, or doc needs a quality judgment before it ships. Use it when a spec criterion names a quality, not a behavior. Use it when verify meets a claim that its commands cannot settle.
Use this skill when reviewing Swift Concurrency performance and responsiveness, including task explosions, actor hopping, MainActor bottlenecks, cancellation, AsyncSequence cleanup, continuations, reentrancy, executor behavior, blocking async work, or async work that affects UI latency. Do not use it for general async/await syntax questions unless performance, responsiveness, cancellation, or lifetime is part of the task.
AI-powered testability assessment using 10 principles of intrinsic testability with Playwright and optional Vibium integration. Evaluates web applications against Observability, Controllability, Algorithmic Simplicity, Transparency, Stability, Explainability, Unbugginess, Smallness, Decomposability, and Similarity. Use when assessing software testability, evaluating test readiness, identifying testability improvements, or generating testability reports.
Performance and load testing patterns — k6 load tests, Locust stress tests, pytest execution optimization (xdist parallel, plugins), test type classification, and performance benchmarking. Use when writing load tests, optimizing test execution speed, or setting up pytest infrastructure.
Conduct usability tests and identify UX issues through systematic observation. Use when testing user flows, validating designs, identifying friction points, running heuristic evaluations, or ensuring users can complete core tasks. Use for test planning, think-aloud protocol, task scenarios, severity rating, accessibility evaluation.
Run a structured information architecture audit on a sitemap, navigation tree, category structure, menu labels, or multi-screen product. Produces a severity-rated issue list with concrete fixes — catches scheme/task mismatches, narrow-and-deep hierarchies, low-information-scent labels, inconsistent labeling systems, single-path findability, and dead-end pages. Use when auditing IA, site structure, categories, taxonomy, or labels, or as a validation step after generating navigation or any multi-screen structure.
Identify and exploit authentication and session management vulnerabilities in web applications. Broken authentication consistently ranks in the OWASP Top 10 and can lead to account takeover, identity theft, and unauthorized access to sensitive systems.
Review code changes for bugs, security issues, and code quality using Claude Code CLI as an external adversarial reviewer. Use from any agent or provider when the user asks for a code review, wants to check code for bugs or security issues, asks to review a PR, branch, commit, or diff, or says things like "any issues with this?", "review before I push", "check my changes", "look at what I changed", or "review my PR". Tell Claude where to find the code.
Move code from one implementation to another function by function, tests first and code second, and check two implementations of one app for parity, with jscpd --compare as the progress measure and a coverage map binding each function to its tests. Use when porting a library or app to another language or framework (Java to Kotlin, JavaScript to Rust, a Python library to TypeScript, an iOS app to Android), when asked what is left to port, or when comparing the Android and iOS versions of an app.
Analyzes code architecture and structure — layer violations, circular dependencies, god objects, anemic domain models, missing boundaries, directory structure issues, and configuration problems. Generates severity-scored findings with fix prompts. Trigger phrases: "architecture review", "structure check", "layer analysis", "god class".
Move a bulky inline test block out of its source file WITHOUT weakening it — same coverage, same private access: read the source and its inline tests, pick the smallest safe extraction boundary (an adjacent `#[cfg(test)] mod`, not a top-level `tests/`, when private access matters), move tests and their helpers with names and attributes intact plus the minimal module wiring, then run the narrowest relevant tests. Preserves the original visibility model and touches production code only as far as wiring requires — never silently downgrades private unit tests into weaker public-API integration tests. Use when the user asks to split large inline tests out of a source file.
Inspect, debug, and automate Chrome directly through the Chrome DevTools Protocol (CDP). Use this skill whenever a task needs a real web browser: open a URL, navigate pages, take a screenshot of a web page, read the DOM or accessibility tree, click buttons, fill and submit forms, type text, wait for elements, scrape page content, evaluate JavaScript on a page, or check console errors and failed network requests. Works against the user's local Chrome or a remote Cloudflare Browser Rendering endpoint over WebSocket. Relevant to browser automation, web scraping, page screenshots, end-to-end UI checks, DevTools inspection, and handing cloud browser control to a human for login, MFA, CAPTCHA, sensitive input, or approval. No Chrome DevTools MCP, Puppeteer, or Playwright required.
Render, inspect, test, and export high-performance WebGPU video and frame grids with the framefields headless engine. Use when verifying compositions, diagnosing blank frames, profiling GPU pipelines, running visual frame grids, or exporting final MP4 video in framefields.
Use when setting up CI/CD pipelines for Frappe apps, configuring GitHub Actions test workflows, or adding linting and security scanning. Prevents broken CI from incorrect test matrix configuration, missing MariaDB/Redis services, and uncaught code quality issues. Covers GitHub Actions workflows, test matrix (Python/Node versions), semgrep rules, pre-commit hooks, linting (ruff, eslint), CI test environment setup. Keywords: CI/CD, GitHub Actions, test matrix, semgrep, pre-commit, linting, ruff, eslint, continuous integration, automated tests, GitHub Actions, CI pipeline, pre-commit, code quality check..
[AUTO-INVOKE] MUST be invoked BEFORE creating git commits, PRs, or code reviews. Covers Conventional Commits, PR templates, review requirements, and AI-assisted development rules. Trigger: any task involving git commit, git push, PR creation, or code review.
Review a GitHub issue the way /code-review reviews a PR. Fetches the issue with the gh CLI, checks the report against the current codebase, searches for duplicates and prior fixes, scores completeness, assigns severity, and writes a triage report plus a draft reply. Posting comments or labels is opt-in only. Use when the user asks to check, triage, validate, or review a GitHub issue.
Evaluate MCP (Model Context Protocol) servers and tools end to end — deploy from a GitHub URL or npm package, test protocol communication and tool calls, run AI-generated smart tests, and score repository sustainability and popularity. Use this skill whenever the user wants to test, evaluate, audit, score, or vet an MCP server, MCP tool, or MCP package, or asks "does this MCP work" or "is this MCP any good", even if they only paste a GitHub URL or a package name.
Use when user asks to "build a Openverse dapp", "write an Anchor program", "create a token", "debug Openverse errors", "set up wallet connection", "test my Openverse program", "fuzz my Openverse program", "deploy to devnet", "support larger transactions", "fix maxSupportedTransactionVersion", "stake BTG", "delegate stake", "stake BTG to a validator", or "explain Openverse concepts" (rent, accounts, PDAs, CPIs). Also for program architecture — state layout, reducing compute units, throughput bottlenecks, instruction naming — and quick on-chain lookups via public RPC + curl (balance, transaction, token account). End-to-end playbook: wallet connection, Anchor/Pinocchio programs, Codama clients, Surfpool/LiteSVM/Mollusk testing, security review, native BTG staking + CPMM swaps (devnet-default; mainnet only with explicit wallet-approved signing). Dev/test tooling only; defaults to devnet/localnet, never moves real funds without wallet-approved signing.
Run every code reviewer in parallel over a local diff and merge their findings into one ranked list. Use when the user asks for a review of uncommitted changes, says "quick review", or after significant code changes; and when another skill needs the local-diff review (`done` runs it as its review step).
Code quality gatekeeper and auditor. Enforces strict quality gates, resolves the AI verification gap, and evaluates codebases across 12 critical dimensions with evidence-based scoring. Use when auditing code quality, reviewing AI-generated code, scoring codebases against industry standards, or enforcing pre-commit quality gates. Use for quality audit, code review, codebase evaluation, security assessment, technical debt analysis.
Detect AI-generated writing patterns in developer text — docs, docstrings, commit messages, PR descriptions, and code comments. Use when reviewing any text artifact for authenticity and clarity, or when the user mentions ai writing, ai-generated or robotic writing, text that sounds like AI or ChatGPT, or writing quality. Builds on the docs-style core writing principles.
Security audit covering authentication, SQL injection, secret exposure, CSRF and OWASP Top 10 vulnerabilities. Use when the user wants to audit code security, search for vulnerabilities, check authentication/authorization, detect exposed secrets or injections, or mentions "security review" / "audit de sécurité" / "OWASP".
Encodes a continuous improvement loop for goal-seeking agents: EVAL, ANALYZE, RESEARCH (hypothesis + evidence + counter-arguments), IMPROVE, RE-EVAL, DECIDE. Auto-commits improvements (+2% net, no regression >5%) and reverts failures. Works with all 4 SDK implementations. Auto-activates on "improve agent", "self-improving loop", "agent eval loop", "benchmark agents", "run improvement cycle".
Pre-consultation diagnostic questionnaire for clients building websites with AI tools (Claude, Codex, Cursor, Bolt, v0, etc.) who have concerns about quality, design, or maintainability. Collects structured answers about their project, tools, pain points, and goals, then generates a consultation brief. Use when preparing for a website review consultation, when a client asks for a site audit, or when someone says their AI-built site has problems. Supports Russian and English — asks the client to choose language first.
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Validate advanced Three.js graphics as authored systems rather than subjective screenshots. Use for fixed-view visual contracts, field and pass diagnostics, no-post baselines, seed sweeps, camera-scale tests, temporal stability checks, GPU budgets, and regression evidence for procedural scenes.
Run a large, multi-session goal (e.g. shipping a whole side product) through the full V-model closed loop, one phase at a time, with cross-session state and a final north-star acceptance gate. Ultragoals never downgrade the lane: every phase runs CP-1→CP-6 with adversarial verification. Opt-in: invoke with /ultragoal or by calling something a long-running goal. Ordinary work does not run this.
Design reproducible evaluations for AI agents with representative task sets, explicit rubrics, appropriate graders, baselines, regression gates, and failure analysis. Use when defining agent quality, comparing prompts or models, validating a release, measuring tool-use reliability, investigating regressions, or deciding whether an agent is ready for production.
Multi-agent collaborative Android-to-HarmonyOS code migration workflow (iterative). Triggered when the user needs to migrate an Android project to HarmonyOS. Provides: 1) Analyzer Agent scans the code structure 2) Planner Agent draws up the migration plan 3) Translator Agent performs the code conversion 4) **Validator Agent** uses the **ohos-app-build-debug** skill for compile verification, app packaging, and on-device verification of the first screen 5) Tester Agent verifies functionality (run after each module's migration is complete) 6) After all modules are migrated, the Feature Comparator Agent checks for missing functionality 7) UI Comparator Agent verifies UI consistency 8) Feedback of unfinished parts to the Planner Agent for continued iteration. Includes code analysis scripts, API mapping tables, component conversion patterns, and automated verification tools. Trigger keywords: migrate Android to HarmonyOS, Android migration, HarmonyOS migration, Java/Kotlin to ArkTS, Activity to Page, feature comparison, UI comparison.
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.