Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and LaTeX Beamer.
Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell). Orchestrates matplotlib/seaborn/plotly with publication styles. For quick exploration use seaborn or plotly directly.
Classical ML in Python: classification, regression, clustering, dim reduction, evaluation, tuning, preprocessing pipelines. Linear models, tree ensembles, SVMs, K-Means, PCA, t-SNE. Use PyTorch/TF for deep learning; XGBoost/LightGBM for scale.
Use this skill to screenshot a local dev server or HTML file with shot-scraper whenever the user wants to "screenshot my app", "take a screenshot of localhost", "generate screenshots for the README", "batch screenshot my pages", or "set up shot-scraper" — even if they never name shot-scraper and just ask for an image of a page, an OG image, or pictures for the docs. Do NOT use this skill for terminal or CLI recordings (see record-tui), for starting or debugging the app itself (see the project's run skill), or for editing an image that already exists.
Security headers configuration and best practices for ASP.NET Core Razor Pages applications. Covers CSP, HSTS, X-Frame-Options, and comprehensive security middleware setup. Use when configuring security headers in ASP.NET Core applications, implementing Content Security Policy (CSP), or setting up HSTS and other security-related HTTP headers.
A short skit where every beat is laid down to serve one punchline. The joke has to land on something visible, and the absurdity only works when the camera and the physics stay dead serious. Use when the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (Twist-ending comedy skit; 中文触发词: 反转结尾搞笑短片, 搞笑, 反转, 梗, 沙雕), or asks how published cases of this type were prompted. Read references/cases.md before drafting.
Read, write, and manipulate SEG-Y seismic data files. Fast C library with Python bindings for trace, header, inline, and crossline access. Use when the agent needs to: (1) Read/inspect SEG-Y files, (2) Extract trace data or headers, (3) Access 3D survey data by inline/crossline, (4) Create new SEG-Y files from arrays, (5) Modify existing SEG-Y files, (6) Extract subsets of seismic data, (7) Read/write Seismic Unix format.
Publish the approved final video to platforms such as YouTube, Douyin, WeChat Channels, and Xiaohongshu. Use when the user asks to post a video, publish it across platforms, upload to YouTube, post to Douyin/WeChat Channels/Xiaohongshu, or schedule a post. Check the video version, thumbnail, subtitles, title and description, and AI/copyright disclosures for each platform, then prepare a platform-specific publishing package. Upload as private, draft, or scheduled only after the user authorizes each platform, using official APIs, form-filling assistants, or upload tools available at runtime; never publish everywhere with one click. If uploading is unavailable, provide a manual publishing package.
Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.
Hreflang and international SEO audit for multi-language and multi-region sites. Validates language-region codes, return tags, x-default, canonical alignment, and conflict detection across the per-URL HTML, the SE Ranking audit, and the XML sitemap. Use when the user asks "hreflang", "international SEO", "i18n", "language targeting", "x-default", "regional sites", or "multi-language SEO".
Professional technical SEO audit that analyzes crawlability, Core Web Vitals, site architecture, mobile readiness, security, structured data, and AI crawler configuration. Use when auditing websites for technical SEO issues, diagnosing indexation problems, or preparing comprehensive SEO reports.
Sets up a Mac or Windows PC for ButterCut. Installs all required dependencies (Homebrew on a Mac, Ruby, Python, FFmpeg, WhisperX). Use when user says "install buttercut", "set up my mac", "set up my pc", "get started", "first time setup", "install dependencies" or "check my installation".
Bootstrap a complete design-token system in Figma in one atomic step — create a variable collection, its modes (e.g. Light/Dark), and every variable with per-mode values together. Use when starting a token system from scratch: triggers 'set up design tokens in Figma', 'create a token collection with light and dark modes', 'scaffold variables', 'bootstrap a Figma theme'. Works on ANY Figma plan. For incremental edits to an existing system use manage-variables-figma; for syncing from a code tokens file use import-tokens-figma.
Use this skill to set up semantic-release and conventional commits in a repo whenever the user wants releases automated from commit messages. Triggers include "set up semantic release", "add conventional commits", "configure automated versioning", "set up commitlint", "add husky hooks", or "automate our changelog and GitHub releases" — even if they never name semantic-release and only ask for version bumps, tags, or a changelog to be generated for them. Do NOT use this skill for a hand-maintained CHANGELOG plus manual `git tag` flow (that stays manual by design), or for general CI pipeline work unrelated to releasing.
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.
AstrBot plugin development reference and workflow guide. Use this skill when you are: - Writing AstrBot plugins, hooks, decorators, or message handlers - Implementing platform adapters, message chains, or event flows - Configuring plugin schemas, sessions, or lifecycle management - Working with Agent system (tools, subagents, personas, sandboxes, cron jobs) - Converting between AstrBot message models and platform-specific formats - Looking up AstrBot API signatures, hook inventories, or code entrypoints - Debugging plugin issues related to message routing, event handling, or provider integration Provides reference docs for: messages, platform adapters, plugin config, agent system, and core concepts.
Create or audit Claude Code skills. Synthesizes source material (articles, frameworks, talks) bottom-up into strategic, interactive skills — or audits existing skills through a multi-lens framework. Use when creating new skills, turning articles into skills, capturing AI workflows as skills, auditing/reviewing existing skills, or improving skill quality. Triggers on: create skill, build skill, new skill, skill from article, turn this into a skill, capture this as a skill, audit skill, review skill, evaluate skill, improve skill.
Set up a "smart lead + cheap execution" layered sub-agent setup on a new machine or in a new project: a Codex Sol lead + Luna workers, with optional project-level Claude Code agents and Pi/pi-flow cross-tool orchestration. Use for: (1) installing and configuring Codex / Claude Code / Pi from scratch (2) writing project-level .codex/agents, AGENTS.md, .claude/agents (3) fixing the multi-agent catalog problem where Sol cannot spawn Luna (4) running Sol/Luna/multi-agent smoke validation. Triggers: new machine setup, Sol-Luna, layered sub-agents, multi-agent configuration, codex agents initialization
Master smart contract security best practices to prevent common vulnerabilities and implement secure Solidity patterns. Use when writing smart contracts, auditing existing contracts, or implementing security measures for blockchain applications.
This skill MUST be used when the user names S-O-R, Stimulus-Organism-Response, or 刺激-有機體-反應, and when analyzing how marketing stimuli affect consumer psychology and behavior. SHOULD be used for requests such as 廣告有點擊卻沒轉換、 推播有開卻沒回購、品牌活動有聲量卻沒行動, or when turning 消費者行為分析、行銷心理 into a strategy or testable hypothesis. Users need not name the model. MUST NOT trigger solely for analytics implementation, general KPI reporting, or an A/B test that does not need a consumer-psychology hypothesis.
Always-on spam and deliverability guardrails for cold email copy. Apply these rules whenever writing, reviewing, or QA-ing subject lines, openers, follow-ups, CTAs, or any cold outreach copy. Trigger on phrases like "check this for spam", "spam word check", "deliverability review", "QA this copy", "flag banned words", "check subject line", "is this safe to send", "scan for spam triggers", or any time cold email copy is being generated or reviewed. Also trigger automatically as a background rule whenever the campaign-copywriting or cold-email-copywriting skill is active -- these guardrails apply to EVERY piece of outbound copy generated, even if the user does not explicitly ask for a check.
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
Apply this opinionated workflow when reverse-engineering legacy or undocumented systems: scope, explore the code, trace data flows, document in EARS format, flag uncertainties. For code archaeology, onboarding, and requirements extraction.
Start here for Deepgram speech-to-text. Use when a task says “speech to text,” “STT,” “transcribe,” “transcription,” “live transcription,” “captions,” “diarization,” “nova-3,” “Flux,” “turn detection,” or “end of turn.” Picks the model family (Nova on /v1/listen for general transcription, Flux STT on /v2/listen for conversational audio with built-in turn detection), gets a first request working, and routes to the api, docs, recipes, starters, examples, and per-language SDK skills for everything else
Build event streaming and real-time data pipelines with Kafka, Pulsar, Redpanda, Flink, and Spark. Covers producer/consumer patterns, stream processing, event sourcing, and CDC across TypeScript, Python, Go, and Java. When building real-time systems, microservices communication, or data integration pipelines.
Structure content for screen reader and assistive technology use. Chains: heading-structure, alt-text-design, table-accessibility, form-labelling. Use when building a new page, document, or content template and you want to get the structural accessibility right from the start.
Comprehensive Supabase expert with access to 2,616 official documentation files covering PostgreSQL database, authentication, real-time subscriptions, storage, edge functions, vector embeddings, and all platform features. Invoke when user mentions Supabase, PostgreSQL, database, auth, real-time, storage, edge functions, backend-as-a-service, or pgvector.
Use when: the user explicitly asks to analyze requirements, write a spec, produce a detailed design, write a proposal or proposal document, or make a plan following OpenSpec / OPSX; or when a new feature, feature change, process change, API change, data model change, state transition, role process, or module boundary adjustment would change external behavior; or when a single request mixes design and implementation intent.
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.