Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when generating a new SDK from an OpenAPI spec. This is the PRIMARY skill for SDK generation. Triggers on "create SDK", "generate SDK", "new SDK", "quickstart", "TypeScript SDK", "Python SDK", "Go SDK", "Java SDK", "generate TypeScript", "generate Python", "generate Go", "make SDK", "build SDK", "SDK from OpenAPI", "SDK from spec", "initialize SDK project".
Use for per-entity usage-limit and spend-control work in Stigg Governance — enforcing usage limits over whatever hierarchy of sub-units a customer needs (the entity model is customer-defined, not fixed) — defining entity types with attribution keys, setting entity entitlements for a feature or credit currency, dimensional scoping, querying the governance tree, runtime enforcement, and moving v1-beta code to v1. Triggers include "per-entity budget", "per-team spend limit", "per-agent token cap", "cost center limits", "sub-customer limits", "entity type", "entity entitlement", "attribution keys", "governance tree", "budget enforcement", "scoped assignment", "v1Beta governance", "keep entities in sync", "re-parent entity", "CannotReportUsageForEntitlementWithMeterError". Skip for account-level credit grants / pools / ledger (stigg-credits), feature gating with no entity hierarchy (stigg-entitlements), or catalog modeling (stigg-pricing-modeling).
Style profiles distilled from 200+ articles by 5 WeChat public-account stock-investing KOLs (猫笔刀, 格兰投研, 投资明见, 财躺平, 终身黑白), enabling stylized investment analysis via an AI Agent with multiple modes: single-KOL review, parallel multi-KOL comparison, sector funnel screening, short-term stock picking, portfolio review, earnings commentary, and view tracking. Use when the user requests stock review, KOL style analysis, multi-KOL comparison, sector analysis, short-term stock picking, portfolio review, or earnings commentary. Trigger words: stock review, KOL analysis, simulate KOL, stylized review, multi-KOL comparison, daily review, sector analysis, stock picking, portfolio review, earnings commentary, KOL views.
Intelligent stock analysis skill. Enter a stock ticker (A-shares/Hong Kong/U.S. stocks) to automatically: 1. Fetch real-time quotes and historical K-line data 2. Calculate technical indicators (MA/MACD/RSI/volume/deviation rate) 3. Provide an overall score (out of 100) and buy/sell signals 4. Search the latest news 5. Perform AI analysis and output a decision dashboard. Trigger when the user provides a ticker for analysis, asks how a stock is doing, requests market analysis, etc. Example inputs: “Analyze TSLA PLTR,” “How is 600519 doing?” “Take a look at HK00700”
Use when working with the SuperPlane CLI to discover integrations, actions, and triggers, build or troubleshoot apps and canvases, manage secrets, and monitor executions. Covers authentication, list/get commands, interpreting configuration schemas, wiring channels between nodes, resolving integration binding issues, and inspecting runs. Triggers on "superplane", "app", "canvas", "workflow", "CLI", "connect", "integration is required", "execution".
A systematic review and semantic audit skill for theses. From the perspective of a graduate advisor or blind reviewer, it performs a comprehensive quality check (topic and literature review, theory and methods, workload and results, logical structure, and writing conventions) as well as a detailed semantic review (semantic repetition and redundancy, terminology conflicts, inconsistent wording, cross-chapter repetition, and broken transitions). **For full-thesis or chapter-level reviews, an AI-trace check (humanizer-zh mode) is performed by default** and reported alongside the semantic and high-level reviews. See references/review-checklist.md for the cross-chapter checklist. See the repository root README.md for the academic integrity agreement
Deploy TinyShip to production: Docker, Vercel, Cloudflare Workers, or VPS with PM2/Nginx. Use when the user asks to "deploy", "go to production", "deploy to vercel", "docker deploy", "cloudflare workers", "set up server", "deploy to VPS", or "production setup".
[user/auto] Close user-owned decisions one at a time with evidence-first questions. Use it for an explicit invocation, an exact active tk-drive decision handoff, or an answer to this skill's pending question. Do not auto-start on generic ambiguity, artifact existence, or generic continuation alone.
LoRA, full fine-tuning, DPO preference tuning, VLM training, function-calling tuning, reasoning tuning, and BYOM uploads on Together AI. Reach for it whenever the user wants to adapt a model on custom data rather than only run inference, evaluate outputs, or host an existing model.
Operate Transistor.fm podcast hosting from the terminal: verify API access, browse shows and episodes with JSON:API-aware output, run the episode publish lifecycle (create draft, attach audio, publish or schedule via the dedicated publish endpoint), pull download analytics, and manage private podcast subscribers and webhooks. Use when the user mentions Transistor, Transistor.fm, podcast hosting, episode publishing, private podcast subscribers, or podcast download analytics. Do not use this skill for other podcast hosts (Buzzsprout, Libsyn, Megaphone, Spotify for Creators), for editing or producing audio, or for feed/RSS parsing — the bundled CLI manages a Transistor account through its v1 API and cannot create new shows (dashboard-only).
Turso edge-hosted SQLite platform built on libSQL (open-source SQLite fork). Covers @libsql/client SDK, embedded replicas with local sync, multi-database per-tenant architecture, platform API for database provisioning, schema migrations, vector search with F32_BLOB, batch operations, interactive transactions, and encryption at rest. Use when connecting to Turso databases, configuring embedded replicas, provisioning databases via the platform API, implementing per-tenant database isolation, performing vector similarity search, or integrating libSQL with Drizzle ORM.
Apply TypeScript design standards when creating or refactoring functions, methods, classes, modules, or shared contracts (interfaces, types, enums). Trigger for: typing decisions, domain modeling, architecture design (boundaries, DI, composition, API design), and design principles (SOLID, GoF, KISS, YAGNI, LIFT).
Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Use when building user interfaces, implementing design systems, creating responsive layouts, adding accessible components (dialogs, dropdowns, forms, tables), customizing themes and colors, implementing dark mode, generating visual designs and posters, or establishing consistent styling patterns across applications.
This skill should be used when upgrading dependencies, bumping packages, resolving outdated dependencies, or performing dependency updates. It guides safe Bun-based package upgrades with breaking-change handling, runtime pin alignment, and grouped version coordination.
Vercel deployment configuration, preview environments, and edge functions. Covers vercel.json and vercel.ts configuration, rewrites, redirects, headers, environment variables across production/preview/development, custom domains, DNS setup, edge and serverless functions, Vercel CLI, GitHub Actions CI/CD, and monorepo deployments. Use when deploying to Vercel, configuring builds, setting up preview branches, managing environment variables, configuring custom domains, or using edge/serverless functions. Use for vercel, deploy, preview, edge-function, serverless, vercel-json, environment-variables, domains, monorepo.
Build vetKeys cryptography on the Internet Computer via the vetKD system API and the ic-vetkeys (Rust, Motoko) and @icp-sdk/vetkeys (frontend) libraries: identity-based encryption (IBE), threshold BLS signatures, timelock encryption, symmetric key derivation, and offline public-key derivation. Use when implementing IBE, encrypting to a principal, BLS signing, sealed-bid or timelock schemes, deriving encryption keys on-chain, transport keys, or calling vetkd_public_key / vetkd_derive_key. For access-controlled encrypted key-value storage (password managers, encrypted notes), use the encrypted-maps skill instead. Not for authentication — use user-sign-in.
Use when the user asks to align, confirm, or correct the agent's understanding before action; when prior misinterpretation, risky ambiguity, release/version/commit intent, destructive effects, or goal disagreement could cause rework or damage.
Synthesize Chinese voiceover audio from a timestamped narration.json. Generates speech segment by segment using MiMo TTS (mimo-v2.5-tts), Fish Audio (s2.1-pro-free), or an explicitly configured generic IndexTTS HTTP service, dynamically adapting speech rate to time windows and handling loudness; takes narration on the input timeline and produces tts_segments and tts_meta.json on the output timeline. Data disclosure: each narration segment's text is sent to the chosen TTS service (MiMo / Fish Audio / user self-hosted IndexTTS), and the --voice-ref reference audio is sent to MiMo. Also includes an experimental English-to-Chinese dub path: runs only when dub mode is explicitly selected and --confirm-voice-rights is passed; it sends the source video audio to MiMo ASR and clones the voice using the original speaker's voice as reference via MiMo voiceclone; use only for content you have the right to use and whose speaker has consented to voice cloning. Trigger words: 配音, 语音合成, TTS, 解说配音, voiceover, text to speech, 旁白配音.
Use when you need the user to answer a batch of structured multiple-choice questions in a browser form — brainstorm decisions, picking from options, questionnaires, A/B/C choices with notes and an "Other". Requires the Playwright MCP. Not for mockups, diagrams, or visual design comparisons.
Operate Vite projects: inspect versions and configuration, run bounded development and production builds, diagnose dependency and asset failures, and configure environment-aware frontend delivery. Use when a task names Vite, vite.config, Vite plugins, import.meta.env, dev-server behavior, or Vite build output. Do not use for frontend architecture or visual implementation (route to frontend-engineering), CI/platform provisioning (route to platform-engineering), browser automation (route to playwright), or accessibility design (route to web-accessibility).
Provides comprehensive guidance for Vitest testing framework including fast test execution, Vite integration, component testing, mocking, and configuration. Use when the user asks about Vitest, needs to write fast unit tests, test Vue/React components, or configure Vitest with Vite projects.
Use when the user wants a Vox-style / editorial motion-graphics look — the "printed, not lit" register: cream-paper canvas, halftone dots, heavy ink type, a single yellow highlighter marker, kinetic captions, hand-drawn annotations, and paper slap-ins. Trigger on "Vox style", "Vox-style explainer", "editorial motion graphics", "editorial collage animation", "kinetic typography explainer", "halftone / paper / newsprint animation", "highlighter / marker text animation", "animated map or data reveal in the Vox look", or "make it look like a Vox video". Also use when someone wants to CAPTURE a style they saw somewhere into their own reusable pack — see references/capture-your-own-style.md. Builds on HyperFrames (renders video from HTML); install heygen-com/hyperframes first.
Turn vulnerability notes, disclosure reports, PoCs, source code, or Codex Security findings into self-contained vulnerability reports with clearly supported claims. Use for one vulnerability or a disclosure campaign; a Codex Security scan is optional
Helps write C# node classes for vvvv gamma — the [ProcessNode] lifecycle pattern, Update() method, out parameters, pin configuration, change detection, stateless operation nodes, the public-API import model, and service consumption via NodeContext (IFrameClock, Game access, logging). Use when writing a node class, adding pins, implementing change detection, accessing services in node constructors, persisting runtime state through Create pins, creating stateless utility methods, or deciding whether a class needs [ProcessNode] at all. Requires the assembly to have one of [assembly: ImportAsIs] / [assembly: ImportNamespace] / [assembly: ImportType] set (see vvvv-node-libraries).
Based on the wan2.7-image model, supports a variety of image generation and editing capabilities, including text-to-image, text-to-multi-image composition, image-to-multi-image composition, single-image editing, and image composition based on multiple reference images, suitable for diverse creative scenarios. Mainly covers the following three types of tasks: 1. Image generation — such as "draw a cat", "generate a photo of a woman in a red dress in a cafe"; 2. Image editing — such as "replace the car in the image with a bicycle", "change this image's background to outdoors", "change the clothing color in the image from blue to green"; 3. Style transfer — such as "convert this photo to <xxx> style", "redraw this architectural image in <yyy> style", "change the style of <zzz> with reference to the art style of <yyy>". Trigger conditions: whenever the user's intent involves AI-driven image creation, generation, editing, modification, restructuring, or style adjustment — whether expressed as a direct instruction (such as "generate an image"), a colloquial request (such as "help me draw a puppy"), or an implicit need (such as "make this image more dreamy") — this skill should be activated.
Distil a chat thread, research session, or working document into a structured wiki page capturing the current state of knowledge. Always use this skill when the user says /wiki-crystallize, 'save this to my wiki', 'capture what we've worked out', 'write this up as a wiki page', 'update my wiki from this conversation', 'we've covered a lot', 'before I close this chat', or 'let's wrap up this thread'. Also use proactively when the conversation has covered significant ground and capturing the findings would orient future sessions, the context is getting heavy and insights risk being lost, or the user signals they are ending a working session - even if they don't say 'wiki'. The chat is the scaffolding; the wiki page is the artefact. When in doubt whether a session wrap is being requested, use this skill. Requires filesystem read/write access.
Use when the user says 'make my store visible to chatgpt', 'set up product feeds', or 'make my store agent-ready', or asks about Google Merchant Center, a store llms.txt, or cart links for AI agents. Sets up product feeds in six formats and registers the catalog with the major platforms.
Set up, start, stop, restart, verify, and troubleshoot the WooCommerce Core local development environment with wp-env and asset build watchers. Use when Codex is asked to run WooCommerce locally, prepare wp-env, watch WooCommerce builds, choose between full and targeted build/watch commands, diagnose localhost:8888, or explain local environment setup commands.
Edit AI-sounding text so it reads like a careful person wrote it, without changing what it says or commits to. Built for work writing where the wording matters: sales and marketing copy, support replies, HR and legal letters, emails, docs, release notes, posts, landing pages. Two modes. Rewrite: edit the text you are given. Interview: when a draft is AI-composed and thin, ask the writer 3-5 sharp questions and build the piece from their answers, in their words. Also writes from the writer's own notes or a voice-memo transcript. Calibrated on measured differences between human and AI writing.
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.