Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Scan generated/authored HTML for accessibility violations with axe-core (Deque) running over JSDOM — structural and semantic rules: ARIA attributes and roles, accessible names, alt text, form labels, heading order, landmarks, semantic HTML, tabindex, duplicate IDs, lang attribute, and ~50 more. Use on the CODE side of a Figma-to-code workflow: triggers 'scan this HTML for accessibility', 'run axe on my component', 'check the generated code for a11y', 'axe-core scan', 'accessibility lint my markup', 'WCAG check on code', 'is this HTML accessible'. This is a standalone Node script — NO Figma connection required. Visual rules (color-contrast, focus-visible, link-in-text-block, target-size) are DISABLED because JSDOM has no layout — use lint-design-figma for visual a11y on the design side. The two together give full design+code coverage.
Generate FK-aware, deterministic sample/seed data from a database schema, ORM model, or migrations — INSERT statements emitted in dependency order (parents first), values derived from row index so output is stable and reviewable. Read-only; never writes to a database. For dev/test fixtures only. Use when the user asks to seed, generate sample/test/fixture/dummy/fake data, populate tables, or create starter rows for Postgres, MySQL, SQLite, and friends.
E2E testing expert for Tauri applications using Tauri MCP server. Use when testing running Tauri apps - session management, webview interaction, IPC verification, screenshot capture, and debugging. ALWAYS use tauri_* tools, NEVER Chrome DevTools MCP for Tauri apps.
Mandatory audit workflow for UI/UX changes that reads current state FIRST, checks for redundancy, respects clean design philosophy, and identifies genuine gaps before implementation. Auto-invoked when user mentions UI, UX, design, layout, homepage, page improvements, visual changes, or interface modifications.
Use this skill to gate Python code (floors 3.10+, rules verified through 3.14) with a pass/fail adversarial review — a single blind reviewer subagent judges a diff or file set against 20 decidable rules hunting two failure modes. First, code modern Python makes unnecessary — branch ladders over match/registries, hand-written init/repr/eq over dataclasses, TypeVar ritual over PEP 695, typing.Optional over PEP 604 unions, os.path over pathlib, hand-rolled stdlib batteries, deprecated utcnow, orphan create_task over TaskGroup. Second, legacy-pattern propagation — single-implementation ABCs, pass-through layers, single-method classes, concrete-inheritance reuse, boolean-forked functions, shapeless payloads and parameter clumps — judged as if greenfield; consistency with legacy code is not PASS evidence. A version probe reads the target's Python floor, marks rules above it N/A, and fetches the official what's-new delta when the floor exceeds the verified version. Verdicts only, never fixes.
Use this skill to gate Elixir code built on the Reactor orchestration library (~> 1.0) with a pass/fail adversarial review — a single blind reviewer subagent judges a diff or file set against 28 decidable rules covering saga compensation and undo (side effects without undo, cleanup in the wrong callback, compensate returns that roll back vs continue, non-idempotent undo), retry discipline (uncapped retries under the max_retries infinity default, retrying business failures, missing backoff), dependency and data flow (lexical-order assumptions, context smuggling, missing return), step contracts (invalid run/3 returns, halt misused as failure, guard/where confusion, side effects in inline fns), composition (Reactor.run inside steps instead of compose, Enum loops over map steps, case over switch, unbounded recurse), concurrency (serial-by-default map, sandbox tests left async, process-context loss), and middleware contracts. Verdicts only, never fixes.
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.
Conducts comprehensive backend design reviews covering API design quality, database architecture validation, microservices patterns assessment, integration strategies evaluation, security design review, and scalability analysis. Evaluates API specifications (REST, GraphQL, gRPC), database schemas, service boundaries, authentication/authorization flows, caching strategies, message queues, and deployment architectures. Identifies design flaws, security vulnerabilities, performance bottlenecks, and scalability issues. Produces detailed design review reports with severity-rated findings, architecture diagrams, and implementation recommendations. Use when reviewing backend system designs, validating API specifications, assessing database schemas, evaluating microservices architectures, reviewing integration patterns, or when users mention backend design review, API design validation, database design review, microservices assessment, or backend architecture evaluation.
Use when profiling Bevy 0.19 with `DiagnosticPath`, `DiagnosticsStore`, `info_span!`, or `RenderDiagnosticsPlugin`: custom metrics, CPU/GPU pass timings, queue/task/upload telemetry, stale-result counts, and native, Steam Deck, or WebGPU budgets.
Project-wide coding conventions. TypeScript, naming conventions, function design, React/Next.js, etc. When to use: (1) code review (2) creating new files (3) refactoring (4) checking coding style (5) checking team development rules. Trigger examples: "coding conventions", "what are the naming conventions?", "TypeScript rules", "import order", "how to write commit messages"
Use this skill to drive the Compose test clock by hand with MainTestClock — currentTime, autoAdvance, advanceTimeByFrame, advanceTimeBy(milliseconds, ignoreFrameDuration), and advanceTimeUntil. Explains the 16 ms frame delay used by TestMonotonicFrameClock, the per-frame ordering where withFrameNanos awaiters resume before recomposition, and how the recomposer and MainTestClock share one TestCoroutineScheduler. Covers v1 versus v2 entry-point dispatcher differences (UnconfinedTestDispatcher vs StandardTestDispatcher) and when an explicit runCurrent or advanceTimeBy(0) is required after migration. If the user mentions MainTestClock, mainClock.advanceTimeBy, mainClock.advanceTimeByFrame, mainClock.advanceTimeUntil, ComposeTimeoutException, frame delay, TestCoroutineScheduler, "test clock vs wall clock", or "v2 createComposeRule queues tasks", use this skill.
Audit temporal and lifecycle modeling — soft-delete consistency and its uniqueness/query traps, presence and integrity of an audit/history trail, and retention / GDPR right-to-erasure handling (hard delete vs anonymization, retention windows). Module M8. Feeds the Design & Integrity score (Temporal category).
Check whether OpenHarmony API documentation follows the required templates and whether public API docs, system API docs, error code docs, and interface declarations/comments/implementations are consistent. Use when the user asks to review API doc quality, compare docs against code, audit error code docs, fill missing interface documentation, or generate a doc issue report.
HCCL (Huawei Collective Communication Library) performance testing for Ascend NPU clusters. Use for testing distributed communication bandwidth, verifying HCCL functionality, and benchmarking collective operations like AllReduce and AllGather. Covers MPI installation, multi-node pre-flight checks (SSH/CANN version/NPU health), and production testing workflows.
Score how ready a website, domain, or public MCP endpoint is for AI agents using Is Agentic, and read or act on the resulting report. Use when asked to check a site's agent readiness, get its Is Agentic score, fetch a scored report as JSON, or fix the issues that lower a site's score.
Deploy infrastructure to LocalStack using IaC tools. Use when users want to deploy Terraform, CDK, CloudFormation, SAM, or Pulumi to LocalStack, or need help with the lstk proxy commands (lstk terraform, lstk cdk, lstk sam, lstk aws) or the pulumilocal wrapper.
Review pull request feedback with discerning judgment. The lynx scans comments, identifies legitimate concerns, addresses minor issues directly, and plans responses to significant feedback. Use when responding to PR reviews and addressing reviewer concerns.
Review failed Nx Cloud CI pipeline executions and group recurring, evidence-based failure patterns. Use this skill whenever a user asks about failed CI pipelines, recurring task failures, failed CIPEs, a CI failure review, or a last-24-hours CI report. Use the nx-cloud-api skill for every Nx Cloud read. This read-only skill separates task, workflow, agent, timeout, cancellation, and unknown cases. It suggests diagnostic next steps without changing systems.
This skill should be used when the user asks to "review a PR", "review pull request", "PR review", "check this PR", "analyze PR changes", "review PR #123", "what's wrong with this PR", "is this PR safe to merge", "review my changes", "review local changes", "review my code", "review staged changes", "review my diff", or needs expert code review with architectural analysis, defect detection, and security scanning. Supports both remote PRs and local changes (staged/unstaged). Uses Octocode MCP tools for deep code forensics and holistic evaluation.
Execute a comprehensive Python project health audit. Analyze the tech stack, architecture, API/interface design, data layer, testing, code quality, CI/CD, and documentation. Produce a shareable Markdown report with section scores and a weighted overall score. Use when the user asks to audit a Python project, run a health check, evaluate backend quality, or assess technical debt. Triggers on: 'python audit', 'python health audit', 'fastapi audit', 'django audit', 'flask audit', 'tech debt assessment', 'python health', 'python project quality', 'python quality check', 'python code review'.
Use when a recursive-mode requirement involves debugging a bug, test failure, or unexpected behavior. Insert Phase 1.5 between Phase 1 and Phase 2 to perform systematic root cause analysis before attempting any fixes. Trigger phrases: "debug", "investigate", "failing tests", "crash", "root cause".
Use when implementing any code in recursive-mode Phase 3. Enforces strict RED-GREEN-REFACTOR discipline with The Iron Law - no production code without a failing test first. Trigger phrases: "implement this", "add feature", "fix bug", "write a failing test", "TDD".
Reduce an unoptimized-query-oracle test failure log to the simplest possible reproduction case. Use when you have unoptimized-query-oracle*.log files from a failed roachtest and need to find the minimal SQL to reproduce the bug.
Review code for performance: complexity, database/query efficiency, I/O and network cost, memory and allocation behavior, concurrency contention, caching, and latency/throughput regressions. Cognitive-only atomic skill; output is a findings list.
Analyzes a codebase's modularity imbalances using the Balanced Coupling model and produces a review of design issues. Use when reviewing existing code for coupling problems, assessing architecture quality, identifying distributed monolith risks, or finding areas where changes are unexpectedly expensive.
Use this skill to stand up an Android instrumentation test source set with the canonical `AndroidJUnit4` runner, the correct `AndroidJUnitRunner` Gradle wiring, and supporting infrastructure (Test Orchestrator, runtime permission grants, size annotations, SDK suppression, hermetic animation defaults). Covers `androidx.test:core:1.7.0` / `:runner:1.7.0` / `:rules:1.7.0` / `androidx.test.ext:junit:1.3.0` coordinates, `androidx.test.platform.app.InstrumentationRegistry`, and the `androidTestUtil` configuration trap for `androidx.test:orchestrator`. Use when the user reports `Test runner not found`, `AndroidJUnit4 deprecated`, `InstrumentationRegistry deprecated`, asks "why is my orchestrator not running", "how do I pass `-e` args to the test", "how do I grant a runtime permission in a test", or "instrumented test won't compile".
This skill should be used when auditing Effect TypeScript compliance, or when users mention effect scan, effect audit, effect best-practices checks, or scan-effect-solutions. It provides a structured compliance checklist for TypeScript configuration, services/layers, data modeling, error handling, config, testing, runtime execution, and Option/Either anti-patterns.
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.