Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Diffusion-based docking that predicts protein-ligand poses without a predefined site. Use for blind docking, when traditional docking fails, or exploring multiple binding modes. Pipeline: prep protein (PDB) and ligand (SMILES/SDF), run inference, analyze confidence-ranked poses.
Search and read DingTalk knowledge bases. Use it to quickly look up information in DingTalk knowledge repositories, understand project background, sort out team/department information, answer policy questions, prepare onboarding materials for new hires, read document bodies, export Markdown, and download files, with support for images and diagrams.
Short-form video editing director (Reels, TikTok, Shorts, YouTube, LinkedIn) — edits footage you recorded (word-level cuts, jump cuts, face + screen, text and images appearing over the speaker, word-by-word captions, viral sounds), finds references, screenshots and images online via the browser, writes the script and tells you what to record. Starts with brief questions (language, what you have, format, platform) and calls the motion-designer skill when a scene needs animation. Use when someone wants to edit recorded video, assemble a "yap" talking-to-camera video, create a Reels/TikTok script, find visual references for a video, review a video edit, or replicate the editing of a reference reel.
Generate django-modern-rest transport-layer skeletons from OpenAPI 3.1+ specs. Use when asked to turn an OpenAPI file, URL, or pasted document into typed DTOs, controllers, routers, Django URL wiring, and minimal tests for this repository or similar projects built on dmr. Trigger on requests to scaffold APIs, bootstrap apps, or map OpenAPI operations to Controller, Router, and OpenAPI view constructs without implementing business logic.
Build and operate reproducible genomics workloads on DNAnexus with the dx CLI, dxpy, apps/applets, native workflows, dxCompiler, and Nextflow. Use for DNAnexus data transfers, dxapp.json development, execution monitoring, workflow import, and project automation.
Check whether OpenHarmony API documentation follows the required templates and whether public API docs, system API docs, error code docs, and interface declarations/comments/implementations are consistent. Use when the user asks to review API doc quality, compare docs against code, audit error code docs, fill missing interface documentation, or generate a doc issue report.
Ghostwrite content in a specific person's voice from a VALIDATED voice profile — tweets, replies, short posts, launch copy, recruiting blurbs, emails. Loads the subject's voice profile (people/<slug>-voice) plus first-party context from the brain, drafts 2-3 options in-register, then runs a hard voice-fidelity self-check before showing anything. Includes the profile BUILDER: if no validated profile exists, drafting hard-stops and this skill walks the corpus-to-fingerprint build instead. Never auto-posts.
Guides systematic code refactoring following the DRY (Don't Repeat Yourself) principle. Use when user asks to eliminate code duplication, refactor repetitive code, apply DRY principle, or mentions code smells like copy-paste, magic numbers, or repeated logic. Implements a 4-step workflow from identifying repetition to verified refactoring.
Rewrite a spoken script or article into multi-platform versions. Triggers when the user says "多平台改写", "改成多平台版本", "改成三个平台", "适配多平台", "转抖音版", "转小红书版", or "转公众号版". Input a spoken script or article, and output adapted versions for Douyin, Xiaohongshu, and WeChat Official Account.
Eastmoney Miaoxiang financial skills suite (mx-skills-suite), containing 5 professional financial sub-skills: 1. eastmoney_fin_data - financial data queries (market quotes, financials, relationships) 2. eastmoney_fin_search - financial news search (news, announcements, research reports, policies) 3. mx_select_stock - intelligent stock selection (condition screening, sector queries, stock recommendations) 4. mx_self_select - watchlist management (query, add, delete watchlist stocks) 5. eastmoney_stock_simulator - simulated portfolio management (positions, buy/sell, order cancellation, orders, funds) Trigger words: Eastmoney, Miaoxiang, financial data, market quotes query, stock news, stock selection, watchlist, simulated trading, simulated stock trading, position query, Eastmoney data, Eastmoney API.
Provides comprehensive guidance for the Electron EGG framework, including project structure, main/renderer processes, IPC, window management, and desktop app development. Use when the user asks about Electron EGG, needs to create Electron applications with EGG, or work with Electron EGG patterns.
Musk's thinking operating system. Based on in-depth research into biographies, podcasts, posts, court testimony, decision records, and external criticism, it distills 5 core mental models, 8 decision heuristics, and a complete expression DNA. Use as a thinking advisor to analyze problems, review decisions, break down cost structures, and challenge industry assumptions from Musk's perspective. Use when users say “from Musk's perspective,” “what would Musk think,” “Musk mode,” “Musk perspective,” or “elon perspective.” It may also be triggered by questions such as “Is this cost reasonable?”, “Think from first principles,” “What is the idiot index?”, “the five-step algorithm,” or “Can we vertically integrate?” Do not trigger for general questions like “Can this be faster?” or “Is this process necessary?”—activate only for Musk's core methods, such as cost breakdowns, first principles, and aggressive iteration.
Diagnostic audit for a running cold email program. Checks domain authentication (SPF/DKIM/DMARC), inbox health/reputation from Smartlead, bounce rate by inbox type, and optionally runs a spam placement test via Smartlead's Smart Delivery API. Outputs markdown report + CSV with per-domain/per-inbox scores and concrete action items. Use when reply rates drop, when bounces spike, when onboarding someone else's account, or as a weekly/monthly health check.
Covers the EvolutionaryScale/Biohub `esm` Python SDK: ESM3 generative protein design (sequence, structure and function tracks, chain-of-thought), ESMC embeddings, inverse folding, ESMFold2 structure prediction, and hosted Forge/Biohub inference with ESM_API_KEY. Use when generating or completing proteins with ESM3, extracting ESMC embeddings for classification or similarity, folding a sequence or designing sequences from a structure, or choosing between esm3-open, esmc_300m and Forge-hosted models. Use when batching async Forge or Biohub API calls. Not for other protein models such as AlphaFold or generic Hugging Face transformers usage.
ETE Toolkit (ETE3): Python phylogenetic tree analysis and visualization. Parse Newick/NHX/PhyloXML, traverse/annotate nodes, render figures with TreeStyle/NodeStyle, integrate NCBI taxonomy, run PhyloTree comparative genomics. Use for species trees, gene family evolution, annotated tree figures.
Find where an AI/LLM application is failing in production and surface the failure patterns, working from real traces. Use when someone wants to understand what's going wrong with an AI feature, find and categorize failure modes, triage errors, or investigate quality issues (wrong answers, ignored instructions, hallucinations, tool misuse) — "what's failing in my agent", "surface error patterns", "why are the responses bad", "find the common failure modes", "what should I fix next". Covers scoping to one use case, finding failing traces by whichever signal fits the context (code errors, metric outliers, trace-type slices, manual review, existing-eval spikes, clustering), and reading them into a ranked failure taxonomy.
Comprehensive guide for authoring Claude Code extensions including skills (SKILL.md), hooks, slash commands, and subagents. Use when: creating skills, writing hooks, making slash commands, building subagents, learning Claude Code extensions.
Extract keywords from documents using YAKE algorithm with support for 34 languages (Arabic to Chinese). Use when users request keyword extraction, key terms, topic identification, content summarization, or document analysis. Includes domain-specific stopwords for AI/ML and life sciences. Optional deeper extraction mode (n=2+n=3 combined) for comprehensive coverage.
Complete fal.ai API reference system. PROACTIVELY activate for: (1) @fal-ai/client JavaScript setup, (2) fal_client Python setup, (3) fal.subscribe/run/stream methods, (4) Queue management (submit/status/result), (5) Webhook configuration, (6) File upload to fal.media, (7) REST API endpoints, (8) Real-time WebSocket connections, (9) Error handling patterns. Provides: Client configuration, method signatures, queue workflow, webhook payloads, common parameters. Ensures correct API usage with proper authentication and error handling.
Complete fal.ai optimization system. PROACTIVELY activate for: (1) Queue vs run performance, (2) Parallel request batching, (3) Streaming for real-time UI, (4) WebSocket for interactive apps, (5) Model cost comparison, (6) Image size optimization, (7) Inference step tuning, (8) Webhook vs polling, (9) Result caching by seed, (10) Serverless scaling config. Provides: Parallel patterns, cost strategies, caching examples, monitoring setup. Ensures optimal performance and cost-effective usage.
Use when authoring or validating an FFCPE (Firefly Creative Production for Enterprise) custom-action catalog-entry.json for the run-workflow service (App Builder actions). Covers installing the Adobe I/O CLI and this plugin, schema shape, org/auth, agent discovery, customActionConfig, validation, workflow usage, and troubleshooting. Use **`aio ffcpe catalog`** to validate/register—never raw curl. Older searches may say **Workflow Builder**; same plugin and topic **`ffcpe`**.
Use this skill to set up Salesforce Field Service — Work Types, Skills, Service Territories, Operating Hours, Scheduling Policy, Work Rules, Service Objectives, Data Capture Forms, FSL mobile forms, Pre-Work Brief, Mobile Branding, or any FSL setup, enablement, or configuration request. Entry point that identifies what the user wants to configure and routes to the right sub-workflow: Foundation Setup, Scheduling Policy, Data Capture Forms, Pre-Work Brief, or Mobile Branding.
When the user wants to manage vehicle fleets, optimize fleet size, or plan vehicle acquisition and maintenance. Also use when the user mentions "fleet sizing," "vehicle lifecycle," "fleet utilization," "maintenance planning," "replacement strategy," "total cost of ownership," or "fleet optimization." For route planning within a fleet, see route-optimization. For last-mile operations, see last-mile-delivery.
Fotor AI image generator and AI video generator for photo editing, background remover, background replacement, product photos, ad creatives, social media graphics, poster and banner design, image upscaling, photo restoration, portrait enhancement, text-to-video, and image-to-video. Built for e-commerce, marketing, branding, and content creation.
Framer Plugin SDK expert. Use when building, debugging, or modifying Framer plugins. Covers plugin modes, UI, permissions, data storage, canvas insertion + code files, CMS/ManagedCollection sync, licensing, marketplace submission, and common pitfalls.
Audit an entire repository with fresh eyes for correctness errors, bugs, omissions, duplication, inconsistencies, stale, duplicate, or tautological tests, stale comments, and other mistakes supported by evidence. Fix every safe issue and verify the result.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics
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.