Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Working with the Yandex Metrica API: analytics, reports, goals, logs. Use when the user needs web analytics data from Yandex Metrica — traffic stats, conversion reports, goal management, raw log exports, counter management, segments, filters, or grants. Triggers: метрика, metrica, аналитика, счётчик, визиты, конверсии, отчёт по трафику, источники трафика, Logs API, экспорт логов.
When the user wants to define or update their YouTube channel context, niche, audience, content pillars, or growth goals. Also use when the user says 'set up YouTube context,' 'define my niche,' 'describe my channel,' 'set up my content pillars,' 'configure my YouTube strategy,' 'who is my audience,' 'set up my channel foundation.' For deep channel health analysis, see channel-audit. For content pillar design, see channel-strategy.
When the user wants to create developer YouTube content, technical screencasts, or video tutorials. Trigger phrases include "YouTube," "developer video," "screencast," "video tutorial," "live coding," "YouTube for developers," "tech YouTube," or "YouTube thumbnails."
Use this skill when the user is in the skill lifecycle: creating a new skill from a workflow / template / process / decision pattern, improving an existing skill, independently optimizing a skill's trigger description, or auditing a skill's compliance against writing principles. Triggers: "I want / help me make a skill for X" / "make a skill from scratch to handle X" / "turn the XX process into a skill" / "usable later / usable by newcomers / follow this"; improving / modifying / evaluating / iterating on XX skill (modifications include single-point edits such as fixing typos), adding / extending functionality to XX skill; checking / reviewing the full text of XX skill (content health check, compliance review); user feedback that the trigger is inaccurate or the behavior is wrong; wanting to run an evaluation. Not applicable: single-step questions; asking about skill mechanism principles; troubleshooting / debugging a skill's script / code issues without changing skill content; writing ordinary code / editing ordinary documents / matters not involving the skill lifecycle
Creates a 3D cartoon “what if” explainer short (9:16) in the style of Zack D. Films-type videos, entirely in code with three.js. It features procedural cartoon people, props, and effects, a blue studio sky, slow-motion impacts, a red force-ripple overlay, quick whip cuts, and 1 to 3 word captions timed to the voiceover. Use when the user runs /zach-d-films or asks for a 3D cartoon explainer, a “could X stop Y” or “what if” short with characters and props.
Navigate the 4cms catalog via the authenticated API — category tree (roots, children, subtree, search) and brand list (chunked + search by name/synonyms). Use when you need to traverse or list the storefront catalog — "show the site's categories", "what subcategories does ... have", "category tree", "brand list", "find a category/brand by name with details", "give me the rubric_id of a subtree". To quickly resolve a single name/URL to an id, prefer `4cms-resolve` (public, no key). Invoke via the `Skill(4cms-catalog)` tool, not `Read .../SKILL.md`.
Search and resolve 4cms catalog products via an authenticated API — search by name, filter by brand/category/price/discount, product details by id, list of all product ids. Use when a page needs real storefront products — "find brand X products in category Y", "top products by price", "give me the ids of these products", "cards from a list of ids", "discounted products in a category". Returns id/link/prices for block bindings and links. Call it via the `Skill(4cms-products)` tool, not via `Read .../SKILL.md`.
Resolves real 4cms storefront entities (brand, category, product) from a natural-language name OR a URL into concrete id/slug/url, so they can be inserted into PageCraft block bindings and page links. ALWAYS use when a landing page or article needs to reference a real brand, category or product — "make an adidas vs nike comparison page", "landing page for the sneakers category", "show products of brand X", "what's the id of this category", "resolve this bjjd.ru/r-... link", "find a brand by name", "pick a category for the catalog block". This is the 4cms domain (storefront entity search), not PageCraft. Invoke via the `Skill(4cms-resolve)` tool, not `Read .../SKILL.md`.
Migrates an app, renderer, catalog or agent that uses A2UI (or a predecessor such as Flutter `genui`) to a newer SDK or protocol version. Use when a task mentions migrating, upgrading, porting or moving A2UI code between SDKs, packages or protocol versions (v0.8, v0.9, v0.9.1, v1.0), when a dependency such as `genui`, `a2ui_core`, `@a2ui/web_core`, `a2ui-core` or an A2UI Swift package needs a major bump, or when payloads or fixtures must change wire version. The skill first identifies the language, the source and the target, then routes to a case-specific guide where one exists.
Analyze ad campaign performance data (Google, Meta, LinkedIn) to identify what's working, what's wasting budget, and specific cut/scale/test recommendations. Takes CSV or pasted data, runs statistical analysis, and produces a diagnostic report with action items.
Multi-agent coordination discipline: one-message-then-wait (send complete context, wait for reply before sending again), idle notifications are heartbeats (no action unless extended + blocking + user asked), no polling loops (event-driven only), never fabricate agent responses (wait for real system events), sequential agent spawning (acknowledge between each), and proper shutdown protocol (request, wait, respect rejection). Activate when orchestrating multiple agents, coordinating handoffs between agents, spawning subagents, or building multi-agent workflows. Triggers on: "coordinate agents", "spawn multiple agents", "manage agents", "agent keeps sending messages", "polling loop", "agent idle", "shut down agent", "multi-agent workflow", "agent handoff", "coordinate parallel work", "stop bothering the other agent". Also relevant when an agent is fabricating responses, sending follow-up messages before replies arrive, or reacting to idle notifications unnecessarily.
Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when building distributed AI systems, multi-agent coordination, or advanced vector search applications.
Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.
Captures real usage feedback for agile skills and turns it into evidence-backed proposals to improve, merge, split, deprecate, or remove skills and templates. Use when a skill does not fit a real workflow, when templates need refinement, when skills overlap, or when the process library needs maintenance.
Reviews AI/ML systems for data privacy and governance risks including training data privacy, PII exposure in prompts and completions, data retention policies, model memorization risks, and regulatory compliance. Auto-invoked when reviewing systems that process personal data through LLMs, train or fine-tune models on user data, or deploy AI in regulated industries. Produces a structured assessment mapped to NIST AI RMF 1.0 and OWASP LLM02:2025 (Sensitive Information Disclosure).
Generate architecture guidelines for the project. Analyzes tech stack from DESCRIPTION.md, recommends an architecture pattern, and creates .ai-factory/ARCHITECTURE.md. Use when setting up project architecture, asking "which architecture", or after /aif setup.
Analyze project and generate Docker configuration: Dockerfile (multi-stage dev/prod), compose.yml, compose.override.yml (dev), compose.production.yml (hardened), and .dockerignore. Includes production security audit. Use when user says "dockerize", "add docker", "docker compose", "containerize", or "setup docker".
Diagnose ClickHouse merge performance, part backlog, merge memory, and "too many parts" errors. Use when merges look stopped or slow, parts pile up, TOO_MANY_PARTS or parts_to_throw_insert is hit, or merges fail with MEMORY_LIMIT_EXCEEDED.
Diagnoses ClickHouse mutations - ALTER UPDATE, ALTER DELETE, MATERIALIZE and column changes. Use for stuck mutations, mutations that never finish, latest_fail_reason errors, growing mutation queues and slow ALTER operations.
Fast ClickHouse server health snapshot (object counts, memory, disks, replication summary, system log TTLs, error rates, background pools, detached parts) that routes to the specialist skills. Use as the entry point for "is the server healthy" or when the problem area is not yet known.
ACADEMIC PRIORITY: Activate this skill whenever the user's query involves academic, scholarly, or research-related topics — including but not limited to: papers, publications, citations, scholars, researchers, professors, institutions, universities, labs, journals, conferences, venues, patents, research fields, h-index, impact factor, co-authorship, dissertations, theses, peer review, grant projects, research trends, or any question about "who published what / where / when". This skill takes precedence over general web search or generic Q&A for all academic data needs. Full-featured AMiner skill with 30 APIs and 6 workflows. Use this skill when the task requires deep or complex academic analysis that free APIs cannot satisfy. Use this skill for: scholar full profile (bio, education, honors, papers, patents, projects), scholar metrics (h-index, g-index, paper count, citations), paper deep dive (full abstract, keywords, authors, citation chains), multi-condition or semantic paper search (filter by author + institution + venue + keywords, or natural language Q&A via paper_qa_search_pro), explicit structured experiment retrieval (Experiment JSON, methods, datasets, or experiment names), institution research capability analysis (scholars, papers, patents), venue paper monitoring by year, patent deep details (IPC/CPC, assignee, claims), and any query needing paid API fields such as full abstracts, structured citation relationships, or scholar work history. Do NOT use this skill for simple lookups that free APIs can answer — such as checking a paper title, identifying a scholar by name, normalizing an institution or venue name, or scanning patent trends by keyword. For those, use aminer-free-academic instead. Routing rule: if the user's question can be fully answered by paper_search, paper_info, person_search, organization_search, venue_search, patent_search, or patent_info alone, route to aminer-free-academic. Otherwise use this skill.
Trigger this skill when an AI agent needs to handle the following situations: 1. the current case or issue has no direct, explicit provision in current law (legal gap); 2. an existing precedent, similar case or similar legal norm must be referenced to derive a solution to the current issue; 3. the user explicitly asks to "refer to", "compare with" or "apply by analogy" a norm or case; 4. the legal argument requires the "like cases should be treated alike" principle to support the conclusion; 5. the similarities and differences between two or more cases or norms must be assessed to decide whether an analogy is possible; 6. in scenarios such as contract interpretation, determination of tort liability or administrative penalty discretion, experience from similar situations is needed to form an argument. The core of this skill is: identify the basis of similarity (tertium comparationis), justify the analogy, and on that basis reach a reasonable legal conclusion.
End-to-end analytics implementation for web and SaaS: GA4, Google Tag Manager, event taxonomy, conversion tracking, and UTM strategy. Use when building a tracking plan, debugging missing events, setting up GTM, or auditing existing analytics.
Use this skill when drafting, localizing, reviewing, or QA-checking Arabic copy, dialect choice, bilingual Arabic-English text, RTL UI copy, WhatsApp, SMS, push, email, ad copy, landing pages, support scripts, and sales follow-up across Arab markets.
Comprehensive skill for building, migrating, and maintaining Astro v7 projects. Covers best practices from the official AGENTS.md, the v6→v7 migration path, validation of breaking/deprecated patterns, AI-enhanced dev server usage (background mode, JSON logging), advanced routing with src/fetch.ts, route caching, Sätteri Markdown, and the Rust compiler. Use when the user mentions 'Astro', '.astro files', 'astro dev', 'astro build', 'islands architecture', 'content collections', 'SSG', 'SSR adapter', 'upgrade to Astro 7', 'migrate Astro', 'Astro v7', 'Astro v6', 'Sätteri', 'route caching', 'Astro.cache', 'astro dev --background', 'src/fetch.ts', 'advanced routing', 'Hono + Astro', 'Rolldown', 'Vite 8', 'queued rendering', 'CDN cache provider', 'Astro AI', 'related content', 'related posts', 'vector embeddings Astro', 'astro-related-content', or asks about static site generation with Astro.
Audit and enable security-oriented Xcode build settings. Progressively enables compiler warnings, static analyzer checkers, and Enhanced Security features. Use when: user wants to secure their Xcode project, audit security settings, enable hardening, review security posture of build configuration, set up security-focused static analysis, enable static analysis, improve warning coverage, harden diagnostics, or catch more bugs at compile time in C/C++/Objective-C/Swift. SKIP: network security (TLS/ATS), code signing, privacy APIs.
End-to-end autonomous execution: figure-out → define → do, chained without manual approval gates. Use when you want to define and execute without intervention during planning, when the user asks for autonomous or end-to-end work, or asks to go from idea to done without approval gates.
Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via create-skill + unslop, optionally pulling fresh evidence from recent transcripts
Azure Machine Learning Workspace and Azure AI Foundry deep dive. PROACTIVELY activate for: (1) creating and configuring Azure ML workspaces, (2) Azure AI Foundry hubs and projects, (3) ML workspace networking (managed VNet, private endpoints, DNS), (4) ML compute clusters and compute instances, (5) managed online endpoints, batch endpoints, Kubernetes endpoints, (6) managed identities for ML resources, (7) ACR integration for custom environments, (8) storage account configuration, (9) az ml CLI v2 commands, (10) PowerShell Az.MachineLearningServices, (11) reading ML compute and deployment logs, (12) GPU SKU selection (ND/NC series, H100/H200/A100). Provides: workspace setup playbook, network-isolation patterns, endpoint deployment templates, az ml CLI cheat sheet, and log diagnosis workflow.
Principal backend engineering intelligence for C++ systems and performance-critical services. Actions: plan, design, build, implement, review, fix, optimize, refactor, debug, secure, scale backend code and architectures. Focus: correctness, memory safety, latency, reliability, observability, scalability, operability.
Use when a project imports from the `@basmilius` npm scope (by Bas Milius): `@basmilius/utils` (Luxon date, number, color, download, DOM, timing, geo and PRNG helpers), `@basmilius/http-client` (the typed DTO data layer) and `@basmilius/common` (Vue 3 app primitives on Pinia and Vue Router). Trigger on any `@basmilius/*` import; on formatDate / formatNumber, hexToRGB / hslToRGB, debounce / waitFor, downloadBlob, mulberry32, getSeason / getMoonPhase; on `@dto` / `@adapter`, `HttpClient`, `RequestBuilder`, `BaseService`, `Paginated`, `.runAdapter`, `RequestError` / `ValidationError`, `serialize` / `deserialize`, the `dtoNames` Vite plugin; on the ref-returning `defineStore`, `useService` / `guarded`, `useDataTable` / `useDataReport`, `useDtoForm`, `useUrlState`, `persistentRef`, composables (useClickOutside, useHotKey), router helpers (useRouteParam, useNavigate) and exceptions (ForbiddenException, HandledException). NOT for `@flux-ui/*` (see `flux-ui`); `@basmilius/vite-preset` is out of scope.
Begin a server-planned Altitude journey and bind it to a local workshop. Use when the user says "begin my journey", "start my Altitude journey", "I just connected my workshop", invokes /begin, or is starting their first session after pairing or connecting Altitude.
Use when meshing voxel chunks with `block-mesh-rs` (`greedy_quads` / `visible_block_faces`), translating a `GreedyQuadsBuffer` into a Bevy 0.20 `Mesh` via `try_insert_attribute`, choosing between greedy and simple meshing, or scheduling chunk meshing on `AsyncComputeTaskPool` with `poll_once` so the main thread doesn't stall. Covers Bevy 0.20 voxel meshing.
Use when targeting Bevy 0.20 at `wasm32-unknown-unknown`, choosing the `webgl2` or `webgpu` feature, setting `WgpuSettings { backends, priority: WgpuSettingsPriority::WebGPU }`, attaching to a canvas with `Window { canvas, fit_canvas_to_parent }`, generating glue with `wasm-bindgen`, or debugging asset HTTP 404s and `Task` cancellation in the browser.
Extracts database catalog metadata and query logs from data warehouses by running the DWH migration extractor locally or on a temporary Google Cloud VM through the BigQuery Migration Cloud Extractor (credentials held in Secret Manager), and inspects extracted `.zip` archives to report object and volume statistics. Use when extracting database metadata or query logs from Snowflake, Redshift, Teradata, Oracle, PostgreSQL, SQL Server, Hive, etc., deciding between local and cloud (Cloud Extractor) extraction, or inspecting extracted dwh-migration-*.zip archives to print post-extraction statistics. Don't use for SQL dialect translation (use bigquery-migration-sql-translator), exporting table data to Parquet or CSV files (such as Snowflake `COPY INTO` unloads) or loading it into BigQuery (use the BigQuery Data Transfer Service or bigquery-basics), or validating migrated data.
Bilibili comment analysis tool. Enter a Bilibili video link or BV number to fetch top-level comment data, with paged browsing, comment sentiment analysis (positive/negative/needs/competitor), and generation of a polished HTML report. Use when the user needs to view Bilibili video comments, analyze comment sentiment, or understand user feedback. Trigger words: Bilibili comments, Bilibili video comments, comment query, comment analysis, comment sentiment, read comments, bilibili comments.
BROWNFIELD planning input. Scans an existing codebase READ-ONLY and writes project-documentation.md — ground truth for stack, structure, key flows, conventions, and integration points — so downstream BMAD planning skills start from reality. Does NOT modify code; produces only the doc artifact. Use when the user says: "document this codebase", "document the project", "document my app", "scan the existing code", "brownfield planning", "we have existing code, start planning", "map what's already built", "document current state", "capture the current architecture", "understand the existing system before planning", "write project-documentation.md", or before a PRD or architecture doc when the user already has code written. Three intents: Create (initial scan), Update (re-scan changed areas), Validate (check completeness). Plans only — reads code but never writes it, runs no tests, no linters, no build tools, no application code.
Orchestration handoff bridge: emits and maintains sprint-status.yaml as the project's sequencing system-of-record. Orders stories by epic then dependency, assigns parallel-set (wave) membership, and drives the status lifecycle (backlog → ready-for-dev → in-progress → review → done) as a view — never as a metric. Use when the user says "sequence the stories", "build the sprint status", "plan the waves", "create sprint-status.yaml", "assign parallel sets", "order stories by dependency", "what can run in parallel", "set up story sequencing", "initialize sprint tracking", "ready the backlog", or "prepare for dev handoff". Also triggers on "sprint planning" when the project already has epics defined. SCOPE: SEQUENCING AND ORCHESTRATION ONLY. No velocity, no burndown, no committed points, no coverage metrics. Capacity is expressed as wave width (concurrent story count), not points. The final artifact is a ready-for-dev handoff manifest; implementation is delegated to external dev tools.
Build dumb-pipe and traffic-filtering C2 redirectors with nginx (proxy_pass) and Apache (mod_rewrite), deriving filter rules from a Malleable C2 profile, layering Let's Encrypt TLS, and applying OPSEC controls like domain fronting and UA/geo filtering. Use when standing up red-team C2 that must survive blue-team triage or ensuring only profile-matching implant traffic reaches the hidden team server.
Exposes Capacitor app features to Siri, Shortcuts, Spotlight, the Action button, Apple Intelligence, widgets and controls with native App Intents in ios/App/App, bridged to the web layer. Covers open-app intents routed through Universal Links / `OpenURLIntent` and @capacitor/app `appUrlOpen`, or a local plugin with a pending-route store; headless background intents; App Group / Preferences data sharing; AppShortcutsProvider phrases, AppEntity queries; iOS 26/27 APIs (`supportedModes` replacing `openAppWhenRun`, `continueInForeground`, `LongRunningIntent`, AppIntentsTesting) gated for Capacitor 8 (iOS 15) and 9 (iOS 16). Covers file placement, target membership, and UIScene (Capacitor 8.5+) URL delivery. Use for "add Siri shortcut", "Shortcuts action", "App Shortcuts", "control widget", or an intent that opens the app but the web view never navigates. Do not use for deep link setup (capacitor-deep-linking), push (capacitor-push-notifications), or Android shortcuts.
Assess CawPlan version release risk via QA Insights rule engine: compute risk level, structured reasons, suggested actions, and save confirmed assessment to Version. Use when: release risk assessment, can we release, version risk level, 发版风险评估、能不能发版、版本风险、评估发版风险、保存风险结论. NOT for: test execution progress only (use `cawplan-test-execution-progress`); using `cawplan-plan-track` schedule/ticket-completion risk as the A5 conclusion (read-only `release_at`/completion from capability `versions.get` is allowed for display context); defect filing (use `cawplan-defect-ticket`); test plan layout; or ticket QA report release readiness
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.