Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Enforces a test-driven approach to skill authoring — defining what a skill must achieve before writing content to prevent hallucinated utility or ungrounded advice. Use when creating new skills, editing existing ones, or verifying skill quality before deployment.
Use when working with Turso yield injection or synthetic failure injection machinery for safe resumable state-machine boundaries, including YieldInjector, FailureInjector, YieldPointMarker, inject_transition_yield!, inject_io_yield!, inject_transition_failure!, CommitYieldPoint, CheckpointYieldPoint, CursorYieldPoint, deterministic interleaving tests, abandoned statement/commit tests, and concurrent-simulator yield plans.
Interactive 8D coach for running a live G8D or TOPS-8D investigation step by step, validating root cause depth, rejecting weak containment, and checking D7 systemic prevention. Use when running an 8D investigation live, reviewing a draft 8D before customer submission, or training a team on the 8 Disciplines methodology.
Design and audit accessibility conformance programs for apps, SaaS, websites, desktop software, games, marketplaces, and developer tools. Covers WCAG targets, VPAT/ACR, audits, assistive-tech testing, design systems, issue severity, ownership, remediation, release gates, procurement evidence, and customer communication. Use when accessibility needs durable governance beyond one-off audits.
Use when you need to actually run security tests against a running application you own or are authorized to test — the shared execution harness for lab/proxy/scanner setup, safe non-destructive execution, and standardized proof-of-concept capture that the find/exploit specialist skills rely on.
Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video
Use this skill when a user wants to report, collect, normalize, classify, or template feedback about problems encountered while using AI tools in any scenario, including coding agents, chatbots, office assistants, search, writing, data analysis, or internal AI systems. The skill converts free-form problem descriptions into a structured feedback report with explicit labels, problem category, severity, scenario, impact, and follow-up questions.
(NS) Verify internal consistency of requirements.md and adherence to project rules before task generation. Use after scope confirmation, when the user asks to analyze or validate requirements, or after manual edits to requirements — automatically between Gate 2 and task generation. Produces consistency-report.md; does not modify requirements. Do NOT generate tasks.
A testing reference for Android app development (Kotlin). Covers JUnit4, AndroidJUnit4, Truth, Espresso (cheat sheet), the test pyramid, test doubles, Mockito, MockK, Robolectric; coroutines/Flow/ViewModel testing, ActivityScenario, FragmentScenario, UiAutomator, AndroidTestOrchestrator; createComposeRule, runComposeUiTest, ComposeUiTestConfig, Compose UI test synchronization, CI, and Window Testing (by screen size).
Interactively guides the documentation of arc42 Section 10 (Quality Requirements). Elaborates quality goals from Section 1.2 into concrete, measurable scenarios grounded in Q42 quality criteria (quality.arc42.org). Coaches against vague metrics and checks coverage against architectural decisions. Iterates until the user is satisfied.
Audit one research Workspace for declared Unit outputs and Pipeline target Artifacts, writing `output/CONTRACT_REPORT.md`; use for mid-Run coverage snapshots or final delivery completeness, not deep provenance integrity.
A recipe collection for baserCMS-specific breaking changes, deprecations, and test infrastructure handling when migrating baserCMS plugins from the 5.2 series to the 5.3 series (based on PHP 8.5 / CakePHP 5.2.x, in development). Refer to this when migrating the plugin itself or its test infrastructure, e.g. "make the plugin compatible with 5.3", "baserCMS 5.3 migration", "PluginCollection::create(): $config null given", "Plugin named X is already loaded (integration test)", "BcApp.testAppPluginsToLoad", "plugins.php null → []", "Class BcCcFile\... not found (sub-plugin not loaded)", "Cannot set a node''s parent as itself (TreeBehavior + Content fixture)", "validateUnique(): Argument #2 not passed (double loading of vendor CakePHP)", "MissingTemplateException error500.php masks the test's true cause", "deprecation of the BcFile constructor/delete() path argument". This is a skill for a minor update within the same major version (5.2→5.3); for the major upgrade from baserCMS 4 to 5 (a full rewrite from CakePHP 2 to 5), refer to basercms-plugin-4-to-5-upgrade. For issues caused by PHP itself refer to php-migration, for issues caused by CakePHP itself refer to cakephp-migration, and for test execution steps refer to the basercms-unittest skill. When handling a new baserCMS version, append it to this document by version.
Persistent browser automation via Playwright daemon. Keep a browser window open and send it commands (navigate, execute JS, inspect console). Perfect for interactive debugging, development, and testing web applications. Use when you need to interact with a browser repeatedly without opening/closing it.
Browser automation using Playwright MCP. Navigate websites, fill forms, click elements, take screenshots, and extract data. Use when tasks require web browsing, form submission, web scraping, UI testing, or any browser interaction. NOT when only fetching static content (use curl/wget instead).
Use PROACTIVELY when users ask about React project structure, Bulletproof React patterns, or need architecture guidance. Covers structure setup, codebase auditing, anti-pattern detection, and feature-based migration planning. Triggers on "bulletproof react", "React structure help", "organize React app", or "audit my architecture".
Browser automation and testing using chrome-devtools MCP server. Use when automating web browsers, taking screenshots, inspecting console logs, monitoring network requests, testing responsive layouts, collecting performance metrics, or debugging web applications. Critical for visual testing workflows and browser-based automation tasks.
Language-agnostic skill for authoring and reviewing code with low cognitive complexity, readability, and long-term maintainability. Covers guard clauses, single-responsibility functions, type-driven design (illegal states unrepresentable, branded primitives, discriminated unions), schema-first validation, single source of truth for union metadata, functional core + imperative shell, idempotency, and neighbour-pattern symmetry. Pairs with `tdd` for new code (rules apply in GREEN/REFACTOR). Stack-specific extensions live under `rules/stacks/<stack>/` (React, Next.js today; drop a subdirectory for any other language or framework). Use during PR review, after writing new code, in TDD GREEN/REFACTOR, or when asked to "improve quality", "make this readable", "reduce complexity", "deduplicate", "clean this up", or "/code-quality".
Analyzes Rails code quality, architecture, and patterns without modifying code. Use when the user wants a code review, quality analysis, architecture audit, or when user mentions review, audit, code quality, anti-patterns, or SOLID principles. WHEN NOT: Actually implementing fixes (use specialist agents), writing new tests (use rspec-agent), or generating new features.
Run any question, plan, PR, or code through a Diverse Multi-Agent Debate (DMAD) council of 5 AI advisors with distinct reasoning methods. Advisors collaborate, peer-review each other anonymously, and a chairman synthesizes a verdict. Empirically outperforms adversarial debate (M3MADBench 2026, DMAD ICLR 2025). Use when: 'council this', 'run the council', 'council review', 'pressure-test this', 'stress-test this', 'war room this', or when facing a genuine decision with stakes and tradeoffs
Supports design decisions for cross-aggregate constraint checks ("I want to check the state of aggregate B in a use case for aggregate A"). Covers detecting misuse of Saga, re-examining business requirements, understanding technical constraints in CQRS/ES, and deciding whether to tolerate inconsistent data. Use when facing cross-aggregate constraint problems during code review, architecture design, or requirements analysis. Target language: language-agnostic. Triggers: requests related to cross-aggregate constraints such as "cross-aggregate constraint check", "I want to check the state of another aggregate", "constraint check with Saga", "check whether a product is linked to a brand", "validation across aggregates", "reverse lookup with event sourcing", "business rules spanning aggregates", "constraints in CQRS/ES", "can the command side reference the read model?", "reference another aggregate in a use case".
Use when developing BigQuery Dataform transformations, SQLX files, source declarations, or troubleshooting pipelines - enforces TDD workflow (tests first), ALWAYS use ${ref()} never hardcoded table paths, comprehensive columns:{} documentation, safety practices (--schema-suffix dev, --dry-run), proper ref() syntax, .sqlx for new declarations, no schema config in operations/tests, and architecture patterns that prevent technical debt under time pressure
Build a design risk analysis, DFMEA worksheet, or interface analysis using the AIAG-VDA FMEA Handbook 2019. Covers design intent, interface failures, boundary diagram, and design robustness before manufacturing. Use during new product development, design changes, or when a field failure reveals a design weakness. Required for IATF 16949 §8.3 scope.
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.
Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after recipe-runner brings a deployment up (especially disagg/multi-node) to confirm the KV transport is correct; use troubleshoot for diagnosing already-failed pods.
Design and audit experimentation platform governance for A/B tests, holdouts, feature tests, pricing experiments, lifecycle campaigns, marketplace ranking tests, game economy tests, AI experiments, exposure allocation, metrics, guardrails, conflicts, ethics, rollout, and decision review. Use when experiments should create reliable product learning without harming users or corrupting decisions.
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.