Skills
98,067 packaged capabilities and playbooks for agents. Install any of them with one command.
All
This skill should be used when a team wants to create or refine the QA standards document — for example "create the QA steering doc", "document our test strategy", "write the QA standards", "document our definition of done", "set up the QA guidelines", or "update the QA doc". Generates docs/steering/QA.md as a living document capturing test strategy, coverage thresholds, test patterns, definition of done, and environments. Generated once and refined — not regenerated from scratch.
This skill should be used when a team wants to create or refine the project vision document — for example "create the vision document", "write our product constitution", "define the product principles", "document our bounded contexts", "what is our product vision", "set up the steering docs", "update our vision", "revise the product strategy", "align on product goals", "what are we building and why", "who are our users", "capture our product purpose", or "the vision doc is outdated". Generates docs/steering/VISION.md as a living document capturing product purpose, target users, principles, strategic goals, and bounded contexts. Generated once and refined — not regenerated from scratch.
Plan Southeast Asia market entry including mode selection, regulatory requirements, cultural research, and go-to-market timeline. Use this skill when the user is considering expansion to SEA, evaluating entry modes (marketplace vs direct vs distributor), or conducting market feasibility studies — even if they say 'should we enter Vietnam', 'how to sell in Indonesia', 'SEA expansion plan', or 'find a local distributor'.
A dedicated balcony renovation guide to help avoid common pitfalls. Covers the full process, including laundry and drying areas, opening up balconies and window enclosures, balcony storage and cabinets, leisure and functional renovations, waterproofing, insulation and construction, homes without balconies and remedies, and general balcony renovation. Curates the essential content of the Xi'an Home Renovation Classroom member edition knowledge base in reverse order to help users renovate with less hassle and fewer pitfalls.
Use when writing or reviewing CQL code, schema definitions, or application code that targets YugabyteDB's Cassandra-compatible YCQL API (port 9042). Triggers on YCQL tables, partition keys, TTL, batching, or any mention of YugabyteDB with Cassandra/CQL.
Product manager Yunxiao (Projex) automation: record requirements (compressed pick 1a2b3a4d: type only new/optimize, project, priority, tags), pick Yunxiao projects in real time, advance 待处理→已确认→分析中→设计中→设计完成→待开发, controlled requirement cancellation after development, delivery tree 【交付】ASSOCIATED /【分析】【设计】TASK_SUB, for no-single fast track and numbered direct push, hand off to a delivery owner who is already specified and uniquely confirmed by official read-back, create iterations and attach 【交付】 (not requirements). Use when the user says YunxiaoPM, 需求任务, 记录需求, 受理确认, 开始分析, 开始设计, 设计完成, 交棒开发, 快轨待开发, 编号直推, 创建迭代, 关闭迭代, 取消需求, 拉取待验收需求, 验收通过, 验收不通过, 验收续跑. All Yunxiao reads and writes prefer the official aliyun devops CLI/PAT; only "close iteration" may fall back to a controlled visual flow when the verified CLI lacks the corresponding status action, without relying on browser cookies. Do not create 【开发】/【测试】. Writes that create or expand scope use Plan first, then apply; idempotent refresh, continuation and re-read-back of the same batch with explicit numbers need no repeated confirmation; do not align with yunxiao-requirement-lifecycle. Development Skill after handoff: only for 【优化】 type, refine from the requirement MD and write the "pre-modification rules"; after the PM modifies the PRD/prototype, generate and read back the product handoff snapshot.
A dedicated skill for saving money on home renovations. Covers the full process, including what is and isn't worth spending on, negotiating and quotes, money-saving tips, and budget planning and allocation. Curates the essential content of the Xi'an Home Renovation Classroom member edition knowledge base in reverse order, helping users save money on renovations with less hassle and fewer pitfalls.
A dedicated guide to choosing renovation hardware. Covers the full process, including floor drains and drainage, faucets, showers and sinks, hinges, drawer slides and furniture hardware, door locks and fittings, selection principles and pitfalls to avoid, and general hardware. Curates the essential content of the Xi'an Home Renovation Classroom member edition knowledge base in reverse order to help users choose renovation hardware with less hassle and fewer pitfalls.
Fetches the latest daily review notes from 36Kr AI reviews. Use when the user asks about 36kr AI测评, AI测评笔记, 测评笔记, ainotes, 36kr测评, 查AI测评, 最新AI测评笔记, 今日AI测评, 36kr ainotes, 看测评, 查看测评内容, 36kr AI产品测评, 产品测评笔记, 今天有什么测评, 有哪些AI产品被测评了, 36aidianping测评笔记, 36kr ai notes.
Expert in building 3D experiences for the web using Three.js, React Three Fiber, Spline, WebGL, and interactive 3D scenes. Covers product configurators, 3D portfolios, immersive websites, and adding depth to web experiences. Use for: 3D websites, three.js, WebGL, react three fiber, and 3D experiences
Drill into root cause with a 5-Why chain, why analysis, or structured root cause investigation. Builds a Why chain from symptom to systemic root cause, validates each step with evidence, and detects circular reasoning. Use for 8D D4, CAPA, FMEA cause analysis, or any quality investigation requiring confirmed root cause identification
Open an 8D, run a G8D or TOPS-8D investigation, respond to a warranty complaint, or handle a customer quality escape with the 8 Disciplines methodology. Covers D0 emergency response through D8 team recognition with gate validation. Required for automotive OEM complaints — Ford, BMW, VW, Stellantis — and any quality escape needing documented root cause and PCA.
Plan evidence-backed figures for a paper draft, markdown notes, outline, manuscript, PDF, or paper webpage. Supports Draft-to-Figure fast-track for Markdown notes as well as comprehensive multi-figure planning for full manuscripts.
12-agent academic paper writing pipeline. 11 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure/rebuttal-audit). 6 paper types, 5 citation formats, bilingual abstracts, LaTeX/DOCX-via-Pandoc/PDF output. Style Calibration + Writing Quality Check + Anti-Patterns with IRON RULE markers. Triggers: write paper, academic paper, guide my paper, parse reviews, audit my rebuttal, check my response draft, AI disclosure, 寫論文, 學術論文, 引導我寫論文, 審查意見, 評估回覆.
Skip the learning curve of professional editing software. Describe what you want — add background music to my Canva video and fade it out at the end — and get music-backed videos back in 20-40 seconds. Upload MP4, MOV, WebM, AVI files up to 500MB, and the AI handles AI music overlay automatically. Ideal for Canva users and social media creators who want to add music to Canva videos without re-editing the whole project.
Get music-backed videos ready to post, without touching a single slider. Upload your video and audio (MP4, MOV, AVI, WebM, up to 500MB), say something like "add this song to my video and sync it from the beginning", and download 1080p MP4 when it's done. Built for content creators who move fast and want to add music to videos without using complex editing software.
Assess review feedback from any source (pull or merge request, issue, ticket, document comments, pasted notes), propose dispositions, then implement and reply. Use when the user shares review feedback to work through, or asks to handle and answer review comments.
Design and audit admin settings information architecture, workspace controls, role and permission settings, billing/admin separation, security settings, defaults, auditability, dangerous actions, policy inheritance, team management, and enterprise admin UX. Use when building settings for SaaS, developer tools, marketplaces, desktop apps, or multi-user products.
Produces a Bayesian prior probability that an offered transaction is +EV for the recipient, given that the counterparty chose to propose it. Applies Akerlof market-for-lemons logic -- if they offered it, they believe it is +EV for them, so the prior that it is +EV for us is materially below 50%. Reusable across trade evaluation, waiver drops (another team dropping a player is also adverse selection), job-offer analysis, M&A, and any "someone offered me this" situation. Use when you receive an unsolicited trade/offer/proposal, analyzing incoming trade prior, evaluating why a counterparty proposed a deal, or when user mentions adverse selection, market for lemons, why did they offer this, incoming trade prior, they proposed it, Bayesian adjustment on received offer.
Measurement framework for Answer Engine Optimization (AEO). Provides AI visibility metrics, share of voice tracking, citation monitoring, and referral demand measurement. Use when discussing AEO/GEO metrics or AI visibility performance.
Host an MCP server that exposes an AG2 `Agent` (plus prompts and resources) to MCP clients like Claude Desktop, Cursor, or the MCP Inspector. Wrap the agent with `MCPServer(agent)` — it surfaces `Agent.ask()` as a single conversational tool and serves over stdio (`run_stdio()`) or streamable HTTP (it is itself an ASGI app for uvicorn). Covers `MCPServer`, `SessionConfig` (multi-turn history), `Prompt`/`PromptArgument`/`PromptMessage`, `Resource`/`ResourceTemplate`, `AskContext`/`ContextProvider` (per-request injection), `build_ask_tool`, OAuth2 `security=`, and in-process `testing.connect`/`testing.serve` helpers. Use when you want OTHER MCP clients to call YOUR agent. This is the SERVER side — for CONSUMING external MCP servers from an agent (client side) see `ag2-use-builtin-tools` (`MCPServerTool`).
Operational buying-signal engine for B2B service agencies (BIM/MEP, custom dev, GIS, AI/SaaS engineering outsourcing). Covers the operational half of signal-based outbound: how to detect a signal (which tool, Clay credit cost), when it expires (freshness and decay windows), how to score and prioritize accounts (recency multipliers, multi-signal stacking, heat tiers with SLAs), and what to do when it fires (signal-to-action plays). Use for detecting buying signals; which tool finds which signal; Clay cost per signal; signal freshness, decay, and timing; signal scoring; heat-tier SLAs; signal-to-action plays; visitor-tracking and intent tools (RB2B, Trigify, Common Room, Bombora, Koala, Warmly, 6sense, with EU/GDPR and agency-budget caveats); or "how do we operationalize signal X". Pairs with the strategy layer (which signal x ICP x offer to test). Do NOT use it to invent the signal list (hypo-generator's signals-catalog) or write outreach copy (sequence-writer)
Mint a tamper-evident, post-quantum-signed receipt for a consequential agent action (deploy, delete, pay, grant-access, model decision) so it can be verified later from the certificate alone. Use when an autonomous agent takes a side-effecting action that may need to be proven later, or when satisfying EU AI Act Article 12 record-keeping. Three decisions: whether an action needs a receipt, minting it, verifying it. Signing is delegated to the open-source OpenAgentOntology package. Not after-the-fact log analysis; not a hosted notary; not a legal opinion.
Guidance for governing the identities of AI agents and non-human identities (NHIs) — Microsoft 365 Copilot Studio agents, Microsoft Foundry agents, custom AI agents, and traditional service principals/managed identities — through their full lifecycle. Covers ownership and tagging, scoped permissions and consent (delegated vs application; Sites.Selected; mailbox-scoped Graph), credential hygiene (federated credentials, certificates, no secrets), Conditional Access for workloads, agent-level access reviews via Entra ID Governance, lifecycle workflows for agent decommissioning, audit (agent prompts, agent actions, agent identity sign-ins), incident response when an agent is compromised, and integration with Purview AI Hub for usage signals. WHEN: AI agent identity governance, non-human identity governance, NHI lifecycle, Copilot Studio agent identity, Foundry agent governance, agent service principal, scoped Graph permissions agent, agent access review, decommission AI agent, agent credential rotation, compromised agent response. DO NOT USE for workload identity federation patterns alone (use entra-workload-identity), Entra ID Governance for humans (use entra-id-governance), or Copilot Studio agent build guidance unrelated to security.
Employee agent lifecycle management system. Use when working with agents/ directory employee agents - starting, stopping, monitoring, or assigning tasks to Dev/QA agents running in tmux sessions. Completely independent of CAO, uses only tmux + Python.
Persistent memory architecture for AI agents across sessions. Episodic memory (past events), procedural memory (learned skills), semantic memory (knowledge graph), short-term memory (active context). Use when implementing cross-session persistence, skill learning, context preservation, personalization, or building truly adaptive AI systems with long-term memory.
Add persistent memory to AI coding agents — file-based, vector, and semantic search memory systems that survive between sessions. Use when a user asks to "remember this", "add memory to my agent", "persist context between sessions", "build a knowledge base for my agent", "set up agent memory", or "make my AI remember things". Covers file-based memory (MEMORY.md), SQLite with embeddings, vector databases (ChromaDB, Pinecone), semantic search, memory consolidation, and automatic context injection.
Quickly creates new Claude Code skills or translates ChatGPT projects into Claude Code skills. Handles skill scaffolding, frontmatter, directory structure, and ChatGPT-to-Claude migration. Use when the user wants to 'create a skill,' 'make a new slash command,' 'convert a ChatGPT project,' 'translate a GPT to Claude,' or 'migrate prompts to Claude Code.' For full eval/testing/benchmarking workflows, use skill-creator instead.
Data security testing methodology for AI systems. Triggered when assessing data leakage risk in LLM/AI systems, training data security, or the data integrity of RAG/vector stores. Covers: System Prompt leakage (meta-prompt/role-play/keyword localization), training data inference and extraction, membership inference attacks, model inversion attacks, RAG data poisoning, API information leakage, cascading hallucination attacks, and information leakage from external data sources.
Comprehensive AI-generated text detection analysis. Use when asked to evaluate whether a paper, essay, or document is AI-generated, human-authored, or collaboratively produced. Applies a 9-category research-backed framework with weighted scoring to produce a detailed report with actionable revision recommendations.
Detects AI-written text, scores it against a detection rubric, provides line-by-line edit recommendations, and rewrites content to sound genuinely human. Use when the user asks to 'humanize' text, detect AI writing, remove 'AI voice,' make copy 'less robotic,' pass AI detection tools, or rewrite content to 'sound human.'
Expert patterns for AI-powered image editing including inpainting, outpainting, ControlNet, image-to-image, and API integration with Replicate, Stability AI, and FalUse when "ai image editing, inpainting, outpainting, controlnet, image to image, remove object from image, extend image, flux inpaint, sdxl editing, image-editing, inpainting, outpainting, controlnet, stable-diffusion, flux, replicate, stability-ai, comfyui" mentioned.
Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image
convert static images into animated video clip with this skill. Works with JPG, PNG, WEBP, HEIC files up to 200MB. marketers, social media creators use it for turning still photos into short animated videos — processing takes 30-60 seconds on cloud GPUs and you get 1080p MP4 files.
Skip the learning curve of professional editing software. Describe what you want — animate this image into a 5-second video clip — and get animated video clips back in 30-60 seconds. Upload JPG, PNG, WEBP, HEIC files up to 200MB, and the AI handles AI video creation automatically. Ideal for marketers, social media creators who want to bring still photos to life without filming new footage.
Conducts privacy auditing of AI models including training data extraction testing, membership inference attacks, model inversion testing, and attribute inference assessment. Uses ML Privacy Meter and related tools to quantify privacy leakage. Keywords: model audit, membership inference, privacy meter, model inversion, training data extraction.
Use this skill when a browser/Web app (React, Vue, Next, Nuxt, static sites, SPAs, dashboards, AI chat UI, 页面, 前端, 网页) needs AI models via @cloudbase/js-sdk. Default routing for Web/frontend AI — call directly from the browser, do NOT propose a Node.js proxy. Covers generateText and streamText; models via ai.createModel with groups cloudbase, hunyuan-exp, or custom-*, model id in the `model` field. MUST run two-step preflight before code — see body. NOT for Node.js backend (use ai-model-nodejs), Mini Program (use ai-model-wechat), or image generation (Node SDK only).
Generate professional AI product photography and commercial images. Models: FLUX, Imagen 3, Grok, Seedream for product shots, lifestyle images, mockups. Capabilities: studio lighting, lifestyle scenes, packaging, e-commerce photos. Use for: e-commerce, Amazon listings, Shopify, marketing, advertising, mockups. Triggers: product photography, product shot, commercial photography, e-commerce images, amazon product photo, shopify images, product mockup, studio product shot, lifestyle product image, advertising photo, packshot, product render, product image ai
Create AI-powered social media content for TikTok, Instagram, YouTube, Twitter/X. Generate: images, videos, reels, shorts, thumbnails, captions, hashtags. Tools: FLUX, Veo, Seedance, Wan, Kokoro TTS, Claude for copywriting. Use for: content creators, social media managers, influencers, brands. Triggers: social media content, tiktok, instagram reels, youtube shorts, twitter post, content creator, ai influencer, social content, reels, shorts, viral content, thumbnail generator, caption generator, hashtag generator, ugc content
Implements AI transparency requirements under EU AI Act Arts. 13-14 and GDPR Arts. 13-14. Covers user notification of AI interaction, system capability disclosure, limitation documentation, and meaningful information about automated logic. Keywords: AI transparency, EU AI Act, GDPR notification, explainability, automated decision.
edit raw video footage into edited video clips with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. content creators and marketers use it for trimming and polishing raw footage into a finished video — processing takes 1-2 minutes on cloud GPUs and you get 1080p MP4 files.
Edit raw video footage into polished edited videos with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. Online course creators use it for learning to edit course videos using AI tools — processing takes 1-2 minutes on cloud GPUs and you get 1080p MP4 files.
Turn a 30-second clip with a photobomber in the background into 1080p clean edited clips just by typing what you need. Whether it's removing unwanted objects or people from video footage or quick social content, drop your video footage and describe the result you want. No timeline dragging, no export settings — 1-2 minutes from upload to download.
Turn a short product description text or three product photos into 1080p finished video clips just by typing what you need. Whether it's generating short videos from text or images for free or quick social content, drop your text or images and describe the result you want. No timeline dragging, no export settings — 1-2 minutes from upload to download.
Executes QA test cases created by /aif-qa in human-guided or automated-agent mode, including reusable browser replay scripts. Use when you need to walk through QA one case at a time, record pass/fail results, or have an agent verify and rerun cases through browser, CLI, API, automated tests, or file/document checks.
When the user wants to optimize airline cargo operations, manage air freight, or improve cargo revenue. Also use when the user mentions "air cargo optimization," "cargo capacity management," "freight yield management," "ULD optimization," "cargo routing," "air freight network," or "belly cargo management." For passenger operations, see hotel-inventory-management (for yield management concepts). For tour operations, see tour-operations.
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.