Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Expert guidance on building and deploying apps to WendyOS edge devices. Use when developers mention: (1) Wendy or WendyOS, (2) wendy CLI commands, (3) wendy.json or entitlements, (4) deploying apps to edge devices, (5) remote debugging Swift on ARM64, (6) NVIDIA Jetson or Raspberry Pi apps, (7) cross-compiling Swift for ARM64.
When the user wants citation gap analysis, managed citation building, review generation campaigns, or local rank tracking. Trigger on "Whitespark," "citation finder," "where are my competitors listed," "citation gap," "build citations," "review generation tool," or "get more reviews." Note that Whitespark does NOT have an MCP server — it's dashboard-driven with limited API.
Comprehensive Wikipedia research skill for extracting verifiable, citation-backed information in structured JSON format optimized for AI consumption and verification pipelines. MANDATORY TRIGGERS: Wikipedia research, Wikipedia citations, verify Wikipedia claims, extract Wikipedia references, fact-check with sources, research topic with citations, gather verifiable information, Wikipedia API, collect research data, build knowledge graph, entity extraction, research timeline Use when: (1) Researching topics that need source verification, (2) Extracting Wikipedia content WITH its underlying citations, (3) Building research datasets for AI verification, (4) Collecting structured bibliographic data, (5) Tracing claims to original sources, (6) Building knowledge graphs of entities and relationships, (7) Constructing timelines from biographical/historical data, (8) Cross-validating facts across multiple sources
Use this skill when the user asks to “analyze network traffic with Wireshark,” “capture packets for troubleshooting,” “filter PCAP files,” “follow TCP/UDP streams,” “detect network anomalies,” “investigate suspicious traffic,” or “perform protocol analysis.” It provides comprehensive techniques for network packet capture, filtering, and analysis using Wireshark.
Draft, execute, or track lean, verifiable implementation plans for non-trivial migrations, refactors, PR splits, task checklists, and other work with sequencing, tradeoffs, unknowns, or risks, and delete them when complete; use writing-roadmap for strategic direction and skip small obvious tasks.
Use when preparing anything that announces a release to the people who consume it — CHANGELOG entries, GitHub release descriptions, version announcements, upgrade or migration guides, or deprecation notices. Triggers include "write the changelog", "release notes for v2.3", "summarize what changed since the last release", "what do users need to know about this upgrade", and cutting a tag.
Wyckoff trading skill. Analyzes stock trends based on the Wyckoff method, identifies accumulation/distribution phases, and determines buy and sell points (signals such as Spring, JAC, UT). Triggered when the user mentions stock trading, 威科夫, Wyckoff, 炒股, stock analysis, buy signals, or sell signals.
Xiaohongshu / RedNote AI Agent Skill. Uses Python Playwright to search and read content, manage login sessions, publish image-text/video/long-form posts, comment, like, and save; JSON is output by default, and any write operation requires user confirmation first. Triggers when the user mentions xiaohongshu, 小红书, rednote, xiaohongshu search, posting to Xiaohongshu, Xiaohongshu note analysis, Xiaohongshu operations, or Xiaohongshu automation.
Write a high-retention YouTube script — explainer, tutorial, video essay, review, or talking head — on the packaging then cold-open then value-stack then retention structure that holds watch time past the drop-off cliffs. Use when asked to write a YouTube script, script a long-form or explainer video, draft a video hook, outline a video essay, or turn a blog post or talk into a video. Produces title and thumbnail concepts, multiple hook options, a beat-by-beat body with retention devices, and clear visual and audio cues.
Stop and consult this skill whenever your response would involve any fact or code related to ZIO core or the ZIO ecosystem. Covers: ZIO effects and type aliases (ZIO, Task, UIO, UEffect), fibers and fiber management, concurrency primitives (Hub, Queue, Ref, Semaphore), Software Transactional Memory (STM), ZIO Streams (ZStream, ZSink, ZPipeline, ZChannel), ZIO Test framework and test utilities, ZLayer and dependency injection patterns, error management and error types, scheduling and retries, resource management and scoping, ZIO Config, ZIO Schema, ZIO JSON, ZIO Kafka, and all official ZIO libraries and integrations. Trigger this for any ZIO coding task, type signatures, library features, architectural patterns, or comparisons involving ZIO. Any time you would otherwise rely on memory for ZIO details, verify here instead — your training data may be outdated or wrong.
Web accessibility as a framework-neutral review lens for building or reviewing UI, grounded in the W3C WAI: WCAG 2.2 level AA, WAI-ARIA, and the ARIA Authoring Practices Guide. Semantic HTML and structure, accessible names and ARIA, keyboard and focus, forms, perceivable content (text alternatives, contrast, motion, zoom), live regions and SPA route announcements, a11y testing. Composes with `react`, `angular`, and `vue` for the framework mechanism. Use it when the user says “accessibility”, “a11y”, “WCAG”, “ARIA”, “screen reader”, “keyboard navigation”, “focus”, “contrast”, “axe”, “landmark”, or “WAI”
Add TikTok-style, karaoke, YouTube or minimal captions to your Remotion video. Gets word-level captions through the official remotion-captions flow (whisper-webgpu, or ElevenLabs Scribe via @remotion/elevenlabs when there's no GPU), or imports the user's SRT with parseSrt, places one official caption element per clip, and applies a style preset with platform-safe placement.
Import an existing skill from a GitHub repository URL into the current workspace. Use only when the user provides or references a GitHub URL/repo to fetch from (e.g., `/add-skill https://github.com/OpenHands/extensions/tree/main/skills/codereview` or "add the codereview skill from https://github.com/OpenHands/extensions/"). Handles fetching the skill files and placing them in .agents/skills/. This does not author new skills — to create a new skill from scratch (no source URL), use the skill-creator skill instead.
Generate a voiceover narration and add it to your Remotion project. Provide a script or describe what the narration should say, and this will generate per-scene ElevenLabs TTS audio (official ElevenLabs text-to-speech skill) and wire it into your composition.
scikit-learn compatible Python toolkit for time series ML: classify, cluster, regress, segment, transform with 30+ algorithms (ROCKET, InceptionTime, KNN-DTW, HIVE-COTE, WEASEL). Handles panel, multivariate, and unequal-length series. Maintained successor to sktime. Alternatives: sktime (larger ecosystem), tslearn (fewer algorithms), catch22 (features only).
DTC competitive intelligence — competitor reverse engineering, traffic breakdown, pricing benchmarking, differentiation. Triggers: 竞品分析, competitor, 逆向工程, 竞品拆解, 差异化, 竞争格局, 对标, competitor analysis, competitive landscape, reverse engineer, differentiation. For complex questions, go through afa first.
DTC ad creative production and testing — creative angle matrix, hook variants, creative fatigue refresh, copy. Trigger words: 创意, ad creative, hook, 广告素材, 创意测试, 创意疲劳, 文案, video ads, creative testing, ad fatigue, ugc ads. Route complex questions through afa first.
DTC channel expansion and diversification — multi-market, Amazon, wholesale, international compliance, landed cost of tariffs. Trigger words: 扩张, expansion, 新市场, 亚马逊, 多渠道, 国际化, wholesale, 批发, MEURO, new market, amazon expansion, international expansion, tariffs, landed cost. Route complex questions through afa first.
Meta ads optimization — account structure, audiences, bidding, creative testing, Advantage+, CBO/ABO, Andromeda. Trigger words: Facebook广告, Meta Ads, Instagram广告, Advantage+, CBO, ABO, 像素, Meta投放, facebook ads, instagram ads, lookalike, retargeting, ad set. Route complex questions through afa first.
DTC PR and reputation management — media authority, UGC loops, crisis response, brand protection, GEO-friendly press releases. Trigger words: 公关, PR, 媒体报道, 新闻稿, 危机公关, 声誉管理, 舆情, UGC, media kit, press release, media coverage, reputation management, crisis pr. Route complex questions through afa first.
DTC retention and LTV growth — retention audits, RFM+LTV segmentation, micro-loyalty, subscription churn prevention, win-back. Trigger words: 留存, retention, 复购, LTV, 流失, churn, 会员, 订阅, win-back, RFM分层, repeat purchase, loyalty program, subscription retention. Route complex questions through afa first.
Build a minimal AG2 `Agent` end to end — pick a model provider, set a prompt, call `agent.ask()`, then continue the conversation with `reply.ask()` (multi-turn). Use when the user is starting a new AG2 project, has no working `Agent` yet, or needs the multi-turn chaining pattern. Covers `OpenAIConfig`, `AnthropicConfig`, `GeminiConfig`, `OllamaConfig` etc., and env-var fallback for API keys.
Workbench agent panel system — ef-edit CustomEvent pipeline, registry roll-up, selector grouping, and element property schema. Use when adding new GUI edit capture points, expanding the inspector schema, or continuing development of the EFAgentPanel feature.
Humanizes AI-generated text with a 5-pass rewrite workflow in English and six other languages, optional saved preferences, and optional stylometric voice matching from a writing sample. Works without Slop or Not. When Slop or Not Pro is reachable, adds on-device AI detector scoring (English only), native-language readability checks, Text Cleanup, and cleanup stats. Use when the user invokes /agentic-humanizer or asks to humanize text.
A shared, file-based town square where multiple coding agents talk, coordinate, and debate — no server required. Use whenever more than one agent works the same repo (parallel Claude Code or Codex sessions, separate git worktrees, a fleet splitting a task) and they must stay out of each other's way or think together. TRIGGER on phrasings like "coordinate with the other agent/session", "post to / check the agora", "ask the other agents", "leave a message for whoever's working on X", "announce what files you're touching", "is anyone else editing this?", or any time you're about to edit shared code while other agents are live. Also trigger when an agent is stuck and wants a peer's second opinion, or when several agents each drafted a design (an API, a schema, an architecture) and the group needs to compare the proposals and converge on the best one. Works for any agent that can run a Python script, not just Claude Code.
Fetches AI news from smol.ai RSS and generates structured markdown with intelligent summarization and categorization. Optionally creates beautiful HTML webpages with Apple-style themes and shareable card images. Use when user asks about AI news, daily tech updates, or wants news organized by date or category.
Use this skill for any explicit wiki mutation in ai-memory: saving durable or time-bounded project knowledge, recording a rule or annotation, updating a note, or deleting a memory page. Trigger by semantic intent rather than exact wording; routine session capture is not a durable-page request.
Use this skill for any request whose goal is session continuity across agents or time: finding a pending handoff, resuming previous work, re-grounding after a context compaction (a compacted or summarized conversation, a post-compaction anchor, or a `reload context` prompt), saving next-session context, wrapping up, or discarding a mistaken handoff. Trigger by semantic intent rather than exact wording
Use this skill for any request whose goal is read-only retrieval from ai-memory: project history, prior context, decisions, rules, gotchas, recent activity, full wiki pages, or status/briefing. Trigger by semantic intent rather than exact wording, including when ai-memory is not named.
Manually write a durable page to an ai-memory instance via the MCP (memory_write_page) — for decisions, rules, gotchas, schemas/contracts, or operational constraints the user explicitly wants remembered. Use when the user says 'remember this', 'save this decision', or 'annotate X'. Not for routine notes (auto-capture handles those).
Operate Alibaba Cloud CloudMonitor Service (CMS) AgentLoop ContextStore by using aliyun CLI with api version 2024-03-30. Use when users mention CloudMonitor, CMS, AgentLoop, agent loop, context, memory, experience, ContextStore, context store, context library, memory library, experience library, or ask to create/query/update/delete stores, write/search/update/delete context records, manage store API keys, or debug aliyun cms ContextStore commands.
Create an agent platform instance in DMS via Alibaba Cloud OpenAPI. Supports Simple Mode and Advanced Mode. Use this skill when the user wants to provision, deploy, or set up a new Dify instance on Alibaba Cloud DMS.
Use when generating or editing images with DashScope Wan 2.7 image models (wan2.7-image, wan2.7-image-pro). Use when implementing text-to-image, image editing, interactive editing with bounding boxes, sequential group image generation, or color palette control via the multimodal-generation API.
Applies computational methods to humanities research — text mining and NLP (LDA/BERTopic topic modeling, sentiment, named entity recognition with spaCy/NLTK), corpus linguistics (concordance, collocation, keyness), digital archives (Dublin Core, TEI XML), GIS for history, network analysis, stylometry and authorship attribution, OCR (Tesseract, Kraken, Transkribus), and data visualization (Gephi, Palladio). Use when distant-reading a literary corpus, mapping historical events or trade networks, attributing disputed authorship, digitizing historical documents, or building digital scholarly editions. Part of the AlterLab Academic Skills suite.
Writes scientific manuscripts in full flowing paragraphs (never bullet points) via a two-stage process — section outlines with key points using alterlab-research-lookup, then conversion to prose — applying IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, and current reporting guidelines (CONSORT 2025, STROBE, PRISMA 2020, TRIPOD+AI). Use when drafting or revising a research paper section by section (abstract, introduction, methods, results, discussion), tightening scientific prose, or writing professional/technical reports. For the end-to-end multi-agent paper pipeline (APA 7 LaTeX/DOCX output, bilingual abstracts, reviewer-driven revision roadmap) use alterlab-paper-writer; for a specific venue's LaTeX template and house style use alterlab-venue-templates; to build a BibTeX bibliography use alterlab-citation-mgmt. Part of the AlterLab Academic Skills suite.
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.