Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
HTML-native design skill for high-fidelity prototypes, slide decks, animations, data visualizations and expert design review, with a library of named design styles and PPTX, PDF, MP4 and GIF export. Agent-agnostic; its own prompts are written in Chinese.
Kamae (構え) — robust server-side TypeScript design. Functional domain modeling with discriminated unions, pure state transitions, Result types, schema-validated boundaries, and PII protection. TRIGGER when: writing TypeScript domain models, use cases, repositories, state transitions, error handling, boundary validation, or PII handling on the server side; designing types for business logic; implementing entity/value-object semantics in TS. SKIP: frontend React/Vue components, browser code, build tooling, code generation scripts, pure infrastructure-as-code; code unrelated to domain logic
Professional AI animation and anime production workflows with Krea MCP. Use for long-form animation, anime series, storyboard-to-video, shotlist-to-sequence, asset bibles, model sheets, keyframes, animatics, AI video clips, edit assembly, QA, retakes, and studio productivity workflows. For one-off generic image/video generation use krea-generate; for product/campaign/UGC marketing use krea-marketing.
Plan product launches with the right tier and coordinated checklists. Use when asked to plan a launch, coordinate a release, prepare for go-to-market, or figure out how to announce a new feature or product. Covers silent, soft, and big-bang launch tiers
Capture a correction or lesson as a persistent learning rule with category, mistake, and correction. Stores, categorises, and retrieves rules for future sessions. Use after mistakes or when the user says "remember this", "don't forget", "note this", or "learn from this".
Complete Metaplex Protocol guide for Solana NFTs and digital assets. Covers Core (next-gen NFTs), Token Metadata, Bubblegum (compressed NFTs), Candy Machine, Genesis (token launches), MPL-Hybrid, Inscriptions, DAS API, and the Umi framework. The single source of truth for all Metaplex integrations.
createMiddleware, request middleware (.server only), server function middleware (.client + .server), context passing via next({ context }), sendContext for client-server transfer, global middleware via createStart in src/start.ts, middleware factories, method order enforcement, fetch override precedence
Olares Dashboard via olares-cli dashboard — CPU, memory, disk, network, pod counts, fan, GPU, application/resource rankings, JSON envelopes, and --watch. Use for Dashboard metrics, overview, resource usage, and Olares One fan; not for pod logs or K8s object inspection (olares-cluster).
Modern PHP 8.4 and Laravel patterns: architecture, Eloquent, migrations, queues, testing. Use when working with Laravel, Eloquent, Blade, artisan, or building/testing a framework-based PHP app. Not for php-src internals, standalone PHP libraries, or general PHP language discussion
Use when adding a heavyweight browser dependency (such as diagram or chart renderers like mermaid, code editors, or big wasm-adjacent libs) to a lightweight DSH Web plugin that must stay small; wiring a lazy-loaded chunk through a host route; troubleshooting intermittent lazy import failures or fallbacks; or rendering untrusted markup (SVG/HTML) produced by such a dependency.
Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.
Expert in modern, cross-platform PowerShell Core. Specializes in Linux/macOS automation, parallel processing, REST API integration, and modern scripting patterns. Use for cross-platform automation and modern PowerShell features. Triggers include "PowerShell 7", "PowerShell Core", "pwsh", "ForEach-Object -Parallel", "cross-platform PowerShell"
Granola notes, transcripts, audit events, and webhooks — plus offline SQLite cross-meeting search, attendee timelines, and a MEMO pipeline runner. Trigger phrases: `memo run for today's meetings`, `what's in granola but not yet memo'd`, `every meeting we had with trevin`, `verify granola webhook`, `list granola audit events`, `talk time in last week's meetings`, `extract granola meeting`, `use granola`, `run granola`.
Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem. Judge simplicity in the resulting design rather than diff size
Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, refuse to lie to the compiler, exhaust variants, derive from authoritative schemas.
Only for explicit prior-work/reuse/history requests, not status checks. Finds and verifies existing work before new production when reuse is plausible. Use when the user explicitly references earlier work, existing code, history, or prior decisions, or says 以前做过, 已有代码, 别重复造轮子. Not for current tests, files, bug fixes, or mechanical verification. Produces a reuse/adapt/reject receipt; zero hits never prove absence.
Ethical people-finding and identity verification via parallel research agents across people-search sites, social media, public records, and reverse phone/email/image/username lookups, with confidence-scored results requiring 3+ matching identifiers. Use when finding or locating someone, reconnecting with a lost contact or old friend, reverse phone lookup, identifying an email owner, reverse image search, finding someone by username, verifying identity, people search, public-data background checks, or identifying a caller. Not for structured due diligence or company/entity intelligence investigations, or general web research synthesis (use Research).
This skill should be used for project-level decisions about LLM-powered systems: whether an LLM is the right primitive for the task at hand, the shape of a multi-stage batch or agent pipeline, token and cost estimation, choosing between single-agent and multi-agent at the project level, structured output design for downstream parsing, and structuring agent-assisted iteration. Use this when the unit of work is a whole project or a multi-stage pipeline. Route individual tool design to tool-design and individual skill-loading or context-budget tactics to context-optimization.
Writes, rewrites, diagnoses, and improves any LLM prompt with minimal, high-signal edits. Use when the user wants to create a new prompt from scratch, review or fix a prompt that produces poor output, simplify or tighten instructions, restructure a long prompt, or expand an existing prompt. Covers system prompts, agent instructions, CLAUDE.md rules, SKILL.md prompt bodies, chat templates, structured-output prompts, RAG context templates, and prompt strings embedded in code. Also use when editing any file whose primary content is LLM instructions. Do not use for skill scaffolding, packaging, or evaluation runs; rewriting an existing skill's prompt body is in scope.
Comprehensive mobile push notification guide for iOS (APNS) and Android (FCM). Use when setting up push notifications, debugging delivery issues, implementing background/foreground handlers, managing push tokens, integrating deep linking, or troubleshooting platform-specific issues.
QQ Channel management skill (not QQ Groups). Query channel lists, subchannels, members, posts, announcements, schedules, and more. Uses the qqbot_platform_api tool to proxy QQ Open Platform HTTP interfaces and automatically handle Token authentication. For QQ Channels only (Guild/Channel). Trigger conditions: the user mentions “channel,” “subchannel,” “guild,” “channel,” “post,” “schedule,” or “announcement.”
Generate production subtitle artifacts from the final narration audio or final merged video using Volcengine Doubao ASR word timestamps. Use for local IndexTTS2 videos, Xiaohei page videos, talking-head delivery subtitles, SRT/VTT export, or whenever subtitle timing must match the final audio. Do not use script-length interpolation for final deliverables.
Deploy applications to Render by analyzing codebases, generating render.yaml Blueprints, and providing Dashboard deeplinks. Use when the user wants to deploy, host, publish, or set up their application on Render's cloud platform. Do NOT use for deploying to Vercel, Netlify, or Cloudflare (use their respective skills).
Generate, refine, and optimize production prompts for LLMs with an explicit output contract, completeness criteria, handling of missing context, and concise verification. Use when the user asks to create or improve prompts intended for runtime, or when an SDD design/build flow creates or changes system prompts, pipeline passes, classifiers, synthesizers, edge/worker/runtime prompts, **/prompts/** files, inline system prompts, or templates in _shared. Do not use for human documentation, SDD internal orchestration prompts, emails, notifications, or transactional UI copy.
Wires every side effect and native channel as an injectable interface behind a Provider that throws UnimplementedError until the composition root overrides it, with one live impl per flavor, value-typed signatures returning typed results, hand-written contract-honouring fakes over mocks, MethodChannel quarantined to one lib/native/ directory, and versioned cross-language contracts edited on both sides in one commit. Use when adding or changing a ShareService/AnalyticsService/RemoteConfigService or any side-effect port, injecting a Clock (package:clock) via clockProvider, a MethodChannel/platform channel or native widget bridge, a flavor entrypoint (main_*.dart) or per-flavor provider override, a shared-file/JSON contract mirrored in Kotlin/Swift, replacing a stray DateTime.now() or direct SDK call inside a widget/notifier/repository, or wiring a fake via ProviderScope(overrides:) in tests.
Complete catalog of page layout patterns for SGDS applications. Use this skill whenever a user asks about page layouts, content arrangement, aside panels, split views, sidebar layouts, breadcrumb layouts, or viewport-height layouts — even if they just say 'how should I lay out my page' or 'I need a two-column layout'. Covers Full Width layouts (public-facing pages with sgds-container) and With Sidebar layouts (dashboards/internal tools with sgds-container-sidebar). Trigger on: layout, aside, split view, sidebar layout, two-column, three-column, content arrangement, page structure with aside
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.