Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Use this skill to stand up a JUnit4-based JVM unit-test suite on an Android module. Covers the canonical Gradle dependency matrix (`junit:junit:4.13.2`, `androidx.test:core:1.7.0`, `androidx.test.ext:junit:1.3.0`, `androidx.test.ext:truth:1.7.0`), the `@RunWith(AndroidJUnit4::class)` runner, `InstrumentationRegistry.getInstrumentation()`, `ApplicationProvider.getApplicationContext()`, the `@SmallTest` / `@MediumTest` / `@LargeTest` size annotations wired into `am instrument -e size`, the androidx-test Truth subjects, and the canonical `MainDispatcherRule` setup pattern. Use when the user mentions `AndroidJUnit4 unresolved`, `which AndroidJUnit4`, `InstrumentationRegistry deprecated`, `getApplicationContext in unit test`, `Truth IntentSubject`, `@SmallTest`, `MainDispatcherRule`, or asks how to wire JUnit4 into an Android module's `src/test/`.
Stress-test an existing implementation plan and selectively strengthen weak sections with targeted research. Use when a plan needs more confidence around decisions, sequencing, system-wide impact, risks, or verification. Best for Standard or Deep plans, or high-risk topics such as auth, payments, migrations, external APIs, and security. For structural or clarity improvements, prefer document-review instead.
Performs comprehensive code review by analyzing git diff, verifying conformance with project rules, validating test suites, and checking adherence to Tech Spec and Tasks. Generates a structured code review report with severity-classified findings. Use when the user asks for a code review, wants to validate code quality, or needs pre-merge verification. Do not use for QA testing, bug fixing, or task implementation.
Check whether newly written or updated documentation contradicts existing content elsewhere in the docs — procedures, concepts, prerequisites, values, names, recommendations, or cross-references — both in the local repo and across all published Elastic docs. Use when the user asks for a contradiction or consistency check on a docs change, or when a docs review runs. Do not trigger on ordinary drafting or editing.
Identify and design for edge cases that disproportionately affect users with disabilities. Use when reviewing designs for completeness, planning test cases, or when someone says 'that's an edge case.' Triggers on: edge case, corner case, that's unlikely, only a few users, exception, unusual scenario, we'll handle that later, happy path, unhappy path, error state, empty state.
Invoke to set up CI/CD pipelines for game builds -- automated testing, build pipelines, and deployment to Steam, itch.io, or Epic. Triggers on: "CI", "CD", "pipeline", "automated build", "deploy", "Steam deploy", "itch.io butler", "GitHub Actions game", "build automation". Do NOT invoke for general code review (use game-code-review) or manual testing guidance (use game-qa-lead). Part of the AlterLab GameForge collection.
Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications. Use when setting up CI/CD with GitHub Actions, automating development workflows, or creating reusable workflow templates.
Evaluates GraphRAG systems across knowledge graph completeness, retrieval relevance, answer correctness, reasoning depth, and hallucination prevention. Provides structured evaluation frameworks, metric selection guidance, and testing protocols. Use when evaluating GraphRAG quality, benchmarking multi-step reasoning, measuring hallucination reduction, or when user mentions evaluate GraphRAG, quality metrics, answer correctness, test my GraphRAG, or measure RAG performance.
Reviews submitted PRs using only committed changes: product fit, docs drift, engineering quality, test coverage, and pre-merge gate. Use when approving a PR, doing reviewer QA, or self-checking before requesting review. Not for replying to review comments (use heyeddi-pr-respond).
Product leadership: user stories, acceptance criteria, backlog, holistic reviews. Verifies the product works and is useful; delegates UX flow, design critique, visual contrast, and engineering audits; synthesizes plans and change recommendations. Use after @heyeddi-intake, before ship, or when the user asks for PM review, user stories, acceptance criteria, or "is this feature good enough?"
Launch an automatic issue review with expert personas selected automatically, analyze feasibility, completeness, risks and architecture, then publish a structured report directly on the issue — all without user intervention. Use when the user wants an issue reviewed/analyzed before starting it, wants to assess its feasibility, completeness, risks or architecture, or mentions "issue review" / "revue d'issue".
Comprehensive code reviewer for Java and Python implementations focusing on correctness, efficiency, code quality, and algorithmic optimization. Reviews LeetCode solutions, data structures, and algorithm implementations. Use when reviewing code, checking solutions, or providing feedback on implementations.
Implement comprehensive testing strategies using Jest, Vitest, and Testing Library for unit tests, integration tests, and end-to-end testing with mocking, fixtures, and test-driven development. Use when writing JavaScript/TypeScript tests, setting up test infrastructure, or implementing TDD/BDD workflows
Local app and bot testing. Uses agent-browser CLI for Electron/web app UI testing, and osascript (AppleScript) for controlling native macOS apps (WeChat, Discord, Telegram, Slack, Lark/飞书, QQ) to test bots. Triggers on 'local test', 'test in electron', 'test desktop', 'test bot', 'bot test', 'test in discord', 'test in telegram', 'test in slack', 'test in weixin', 'test in wechat', 'test in lark', 'test in feishu', 'test in qq', 'manual test', 'osascript', or UI/bot verification tasks.
Verifies that implemented neural network models correctly respect their intended symmetries through systematic equivariance testing, layer-wise isolation, and gradient analysis. Use when testing model equivariance, debugging symmetry bugs, verifying implementation correctness, checking if a model is actually equivariant, or diagnosing why an equivariant model isn't working.
Performs a security-focused code review by launching multiple specialized agents and a verification agent to ensure comprehensive coverage and accurate findings. Use this skill when the user asks for a "perform-security-review", "bitwarden-security-review", "execute a security review", "run a comprehensive security audit", "perform an end-to-end security assessment", or needs to coordinate multiple security checks across code, dependencies, secrets, and configurations. The skill manages the workflow, delegates tasks to specialized agents, and presents final findings to the user.
Prepare and seed test data for a feature into a target environment. Analyzes the feature's implementation, proposes data categories covering regular and edge cases, and populates the environment via existing seed mechanisms code access, REST, MCP. Use when the user asks to seed test data, populate a test or staging environment, prepare data for manual/QA testing of a feature, generate a dataset for a feature, or create fixtures in an environment.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Use when reviewing/judging a finished data-model document (the persistence/ domain model — entities, keys, relationships, indexes, normalization, lifecycle) to decide if an engineer can build the schema + query it correctly — an acceptance gate, not authoring. Judges it against a single-sourced 9-condition integrity + queryability bar: entities typed + keyed (stored shape, not the api-spec DTO); relationships carry cardinality + a referential rule (on-delete / embed-vs-reference); every index traces to an access pattern; normalization + paradigm choice + tradeoffs; lifecycle + migration; diagram ⇄ tables in sync; privacy/scale; one-directional vs the api-spec + consistent with the shipped schema; amend delta-scoped. Paradigm-aware (relational/document/graph/wide-column/key-value — never a relational reflex). Emits exactly `VERDICT: approve|revise` — approves a model meeting the bar, revises on a named gap. Not for authoring, the api-spec/feature-spec, or generic design docs (use design-review).
Validate skills against agentskills.io specification. Use when adding new skills to the marketplace, reviewing skill PRs, checking skill compliance, or running quality gates on skills. Validates frontmatter fields (name, description, compatibility, metadata, allowed-tools), directory naming, line limits, and structure.
Patterns for detecting and managing code smells and technical debt in .NET applications. Run Slopwatch CLI to detect LLM reward hacking, disabled tests, suppressed warnings, empty catches, and other shortcuts. Use when identifying code smells, running quality gates in CI/CD, or validating LLM-generated code changes.
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions
Test Temporal workflows with pytest, time-skipping, and mocking strategies. Covers unit testing, integration testing, replay testing, and local development setup. Use when implementing Temporal workflow tests or debugging test failures
This skill should be used when writing or reviewing tests for Android code in Bitwarden. Triggered by "BaseViewModelTest", "BitwardenComposeTest", "BaseServiceTest", "stateEventFlow", "bufferedMutableSharedFlow", "FakeDispatcherManager", "expectNoEvents", "assertCoroutineThrows", "createMockCipher", "createMockSend", "asSuccess", "Why is my Bitwarden test failing?", or testing questions about ViewModels, repositories, Compose screens, or data sources in Bitwarden.
WordPress site and codebase onboarding review. Use when inheriting a WordPress repo, auditing an unfamiliar site or project, scoping technical risk before deeper review, identifying whether a codebase is plugin/theme/headless/WooCommerce/multisite/Bedrock/builder-heavy, or when user asks for "site audit", "onboarding review", "what am I looking at", "inherit this WordPress project", "stack discovery", or "where should I start". Produces a prioritized review path and routes follow-up work to the right WordPress skill.
WooCommerce extension code review for HPOS compatibility, payment gateway security, cart optimization, and template overrides. Use when reviewing WooCommerce extension code, payment gateway development, shipping methods, custom product types, cart operations, checkout customization, or when user mentions "WooCommerce review", "WooCommerce extension", "WooCommerce plugin", "payment gateway", "shipping method", "HPOS", "High-Performance Order Storage", "wc_get_orders", "WC_Payment_Gateway", "WC_Shipping_Method", "cart fragments", "WooCommerce hooks", "WooCommerce template", "shop_order", "WooCommerce performance", "Action Scheduler", "WooCommerce REST API", "WooCommerce Blocks", "checkout block", "woocommerce_checkout". Detects HPOS issues, CRUD violations, payment security anti-patterns, performance problems, and template override mistakes in WooCommerce 8.2+ through 10.x code.
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.