Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Analyze and update 68 US economic and social indicators from five government APIs (FRED, EIA, Treasury, BLS, Census) across 10 categories: GDP, Inflation, Employment, Housing, Consumer Finance, Markets, Trade, Government/Fiscal, Demographics, Health. Two workflows: UpdateData, GetCurrentState (10y/5y/2y/1y trend analysis). USE WHEN GDP, inflation, unemployment, economic metrics, gas prices, how is the economy, refresh data, FRED, US metrics, economic trends. NOT FOR pathogen surveillance.
Design or critique modals, dialogs, alerts, popovers, and bottom sheets — gate WHEN interrupting users is justified, then apply dismissal, title/button, and focus best practices. Trigger when the user asks to design or review a modal, dialog, popup, overlay, confirmation, alert, permission request, lightbox, or bottom sheet — or asks whether something should be a modal at all.
Turn a raw talking-head recording into a finished 1080x1920 Short, Reel, or TikTok with B-roll, motion graphics, captions, and music. Show the plan in chat, then iterate on drafts based on the user’s frame-by-frame comments. Use when someone wants to edit a raw recording into a vertical video or add captions, B-roll, or motion graphics to one
Production guidance for mainland-China Volcengine Doubao Speech text-to-speech. Use for TTS 1.0/2.0 selection, V3 bidirectional or unidirectional streaming, asynchronous long-text submit/query jobs, current voices and controls, timestamps and SSML caveats, expiring results, quota/error handling, authorized cloned voices, privacy, and audio QA. Do not use for international BytePlus endpoints.
Find similar creators on YouTube, TikTok, or Instagram with bounded quota-charging continuation. Use when a user asks for creator recommendations from a profile or brief, including region, language, followers, YouTube average or median views, YouTube gender, creator type or face visibility, TikTok average plays, or Instagram demographics and average likes.
Look up publicly discoverable contact data for up to 50 Instagram, TikTok, or YouTube creators with bounded concurrent WaveInflu requests. Use when a user supplies supported creator profile URLs and asks for public emails or contact links. Returned contact data is not ownership-verified. Do not use for private or guessed personal email discovery.
Full web app security assessment — app understanding, threat modeling, OWASP testing, ffuf fuzzing, Playwright automation, AI-assisted vuln analysis. Coordinates with Recon and PromptInjection skills. USE WHEN web assessment, pentest, security testing, vulnerability scan, threat model app, understand application, create threat model, vulnerability analysis, Gemini analysis, ffuf, fuzzing, bug bounty, OSINT, browser automation, Playwright.
Review the week using accumulated session evidence — retrieval rates, hint depths, calibration accuracy, transfer and unassisted results. The learner identifies patterns and sets a strategy goal. Use weekly or after a multi-session period.
Use when a customer needs guided troubleshooting or a support report for a Wuji device that freezes, disconnects, or behaves unexpectedly, including unresolved wuji command failures. Gather missing facts, collect and inspect evidence, check official troubleshooting sources, and produce a copy-paste report with available attachments for [email protected]. For a standalone health check use wuji-cli-doctor. For log export alone use wuji-cli-logs without starting an interview.
Search YouTube by keyword and return structured video metadata (title, URL, channel, views, duration, date) via yt-dlp. No API keys. Triggers on: "search youtube", "find youtube videos", "top youtube videos on", "trending videos on", "youtube results for", "yt search", "/yt-search".
Use when the user needs to plan, de-risk, or ground a software engineering / computer science undergraduate thesis from a real codebase before final writing. Trigger for requests such as "根据项目写毕业论文", "先做论文大纲", "用真实项目材料规划论文", "检查论文是否脱离代码", "根据检测报告降查重", "根据AIGC报告改写定稿", "继续在手改初稿上改", or when an existing draft thesis must be reworked against a school format sample. Produces an evidence-backed outline, chapter rewrite plan, figure plan, and handoff package for academic-paper-composer.
Independent audit of AI-implemented work — certifies a completed task actually did what it claims, checking files, diffs, tests, and CI rather than the agent's self-report. Flags skipped or weakened tests, mock-hidden integration, snapshot drift, happy-path-only coverage, flaky retries, and status/evidence mismatches. Use when validating completed Compozy tasks, AI-authored PRs, or codex-loop iterations. Not for real-user, persona, or journey QA — use qa-execution for those.
After any AI-generated explanation, require the learner to identify one place it could be wrong, one thing to check, and one source to consult. Builds epistemic vigilance — treats AI output as a claim to evaluate, not truth to absorb.
Build multi-step AI content creation pipelines combining image, video, audio, and text. Workflow examples: generate image -> animate -> add voiceover -> merge with music. Tools: FLUX, Veo, Kokoro TTS, OmniHuman, media merger, upscaling. Use for: YouTube videos, social media content, marketing materials, automated content. Triggers: content pipeline, ai workflow, content creation, multi-step ai, content automation, ai video workflow, generate and edit, ai content factory, automated content creation, ai production pipeline, media pipeline, content at scale
Generate and analyze AI Bill of Materials (AIBOM) for Python projects using AI/ML components. Identifies AI models, datasets, tools, and frameworks for security and compliance tracking. Use this skill when: - User asks to scan for AI components - User wants to know what AI models a project uses - User mentions "AI BOM", "AI inventory", or "ML security" - User is working with Python AI/ML projects (PyTorch, TensorFlow, HuggingFace) - User needs AI component compliance documentation
Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for visuals, Kokoro for voiceover. Types: product demos, testimonials, explainers, social ads, brand videos. Use for: Facebook ads, YouTube ads, product launches, brand awareness. Triggers: marketing video, ad video, promo video, commercial, brand video, product video, explainer video, ad creative, video ad, facebook ad video, youtube ad, instagram ad, tiktok ad, promotional video, launch video
Plan a feature or task in fast, full, or ultra mode. Ultra creates an indexed multi-file bundle with deeply specified phases for execution by a smaller model. Use for "plan", "new feature", "start feature", "create tasks", or exhaustive implementation planning.
Write an AI Producer project's captions as caption moments: static text the user can select, retype and restyle in the editor, timed to the cut by a script. How to time and mount them, the default look, and what keeps them legible. Listed, it makes captions the default.
Frame the speaker for an AI Producer project. Read once before authoring the root layout: pick the canvas first, then who owns the frame for each beat (the speaker, the footage, or the canvas), and for each of the three layouts (seat, overlay, and full cover) the forms it offers, where that canvas lets it sit, what it keeps, and how it is built, with the speaker measured, not guessed.
Create or update an editable AI Producer video. Use when someone provides footage or an existing project and asks AI Producer to cut or edit it, add captions or subtitles, motion graphics or animated effects, background music, or inserted images or video clips, restyle, export the finished video, or adapt a named Motion Library template, in any language. Cut a new project with fixed settings instead of asking about them, and copy the captions, motion graphics and transitions of a reference video the user supplies. Deliver the editable project link by default, export only on explicit request, and stop without inspecting the preview or output video.
Copy a reference video's captions, motion graphics and transitions onto the user's own AI Producer edit. Use when the user supplies a reference video file, a link to one on Instagram, TikTok or YouTube, images of a style, or picks or names one of the preset reference styles, here or on the AI Producer web page, and wants their footage edited in that style, in any language.
Set up AI Producer: connect the user's account, confirm the connection works, and start their first project from one video. Use only when the user chooses Set up for AI Producer, asks to get started with AI Producer or to continue AI Producer setup, or asks for help signing in to or connecting AI Producer. Do not use for an ordinary editing request once AI Producer is connected; that belongs to the aip skill.
Implement AI Coaching best practices on AnalyticDB for PostgreSQL (ADBPG): Leverage Supabase projects (training data management) + ADBPG instances with vector optimization to build RAG-driven coaching systems that guide users through domain-specific workflows, decision-making, or skill development. Use when: User wants to create Supabase projects (spb-xxx), ADBPG instances (gp-xxx), vector knowledge bases, or RAG-driven coaching systems on ADBPG. Triggers: "Supabase", "ADBPG", "vector database", "knowledge base", "RAG", "AI coaching", "coaching system", "spb-xxx", "gp-xxx"
ADBPG Knowledge Base Management: Create knowledge bases, upload documents, search, Q&A. Triggers: "knowledge base", "document library", "document upload", "knowledge search", "RAG", "Q&A", "embedding", "ADBPG", "AnalyticDB PostgreSQL"
Create, migrate, and optimize skills for this alicloud-skills repository. Use whenever users ask to add a new skill, import an external skill, refactor skill structure, improve trigger descriptions, add smoke tests under tests/**, or benchmark skill quality before merge.
Produce and review production image-generation and image-editing workflows with Amazon Nova Canvas on Amazon Bedrock, including native InvokeModel payloads, safe authentication, validation, retries, cost controls, provenance, and lifecycle migration checks. Use when a task names Nova Canvas, amazon.nova-canvas-v1:0, Bedrock image generation, Canvas inpainting/outpainting/background removal, image conditioning, color guidance, image variation, virtual try-on, or Canvas fine-tuning.
Produce and operate Amazon Nova Reel video-generation jobs through Amazon Bedrock. Use for Nova Reel text-to-video, image-conditioned animation, automated or manual multi-shot storyboards, async S3 delivery, cost and approval gates, production continuity, output custody, and AWS-specific safety, privacy, IAM, and provenance decisions.
Use Amazon Transcribe for AWS-based speech-to-text production: batch S3 transcription, real-time streaming, captions/subtitles, diarization, channel identification, custom vocabularies, vocabulary filters, language identification, PII/PHI handling, toxicity detection, Call Analytics, Medical, and secure S3/IAM/KMS workflows.
Create a classic 60-90 second animated explainer video - hook, problem, solution, how-it-works, CTA - from generated animations, on-screen text, and warm narration. Use when the user says "make an explainer video", "animated explainer for X", "explain our product in a video", "60-second explainer", "problem-solution video", or describes a product, feature, or concept they want explained to an audience in an engaging animated format.
Create, edit, repair, and validate Arabic-first or Arabic-English PowerPoint decks with native editable PPTX text, paragraph-level RTL, correct mixed Arabic/Latin/number behavior, native bullets, Arabic language metadata, and PowerPoint-first QA. Use together with the Presentations skill whenever a deck contains Arabic, requires RTL or bilingual slides, must remain editable as .pptx, or renders Arabic differently in PowerPoint, Keynote, Google Slides, or Codex preview.
Generate instrumental music / BGM without vocals or lyrics, suitable for background music, atmosphere building and emotional rendering, 30–120 seconds long. Trigger only when the user explicitly asks to generate instrumental music/background music. During execution it reads Meitu credentials, calls the local `meitu` CLI, sends audio generation requests to the Meitu OpenAPI, and writes results to a local output directory.
Find or create avatar animations (scene emotes): built-in emotes, the Creator Hub Avatar Animations pack, or a custom `_emote.glb` made in Blender on the official Decentraland rig, including upper-body (masked) clips and clips with props or particles. Use when the player's avatar must perform a pose or motion, or for work on the avatar rig. To play an existing emote see player-avatar; for model or prop clips see animations-tweens; for NPCs see npcs.
Verify and transform Lean 4 proofs using the Axiom (Axle) API. Use when the user works with Lean 4 code, formal mathematics, Mathlib theorems, or mentions axiom, axle, lean verify, proof verification, formal proof, or theorem checking -- even if they don't explicitly say "axiom" but are clearly working with Lean proofs that need machine verification.
Use Microsoft Azure Speech in Foundry Tools for media-production speech workflows: speech-to-text, fast and batch transcription, diarization, captions/subtitles, real-time transcription, text-to-speech neural and HD voices, SSML, custom/personal voices, text-to-speech avatars, speech/video translation, localization, quotas, regions, privacy, consent, rights, and production QA.
Use when the user wants to analyze or distill a blogger/account on Xiaohongshu or Douyin, benchmark a target creator, or diagnose their own content strategy. Trigger on requests such as "拆解博主", "蒸馏博主", "分析小红书博主", "分析抖音博主", "诊断我的账号", "对标账号", "内容策略分析", "小红书账号分析", "抖音账号分析", "分析封面", "关键词趋势", "升级我的skill".
Solutioning-phase UX planning skill (optional; activate when the project has a UI). Produces TWO planning documents: DESIGN.md (the visual system — design tokens, color palette, typography, spacing, component specs, WCAG 2.1 AA contract) and EXPERIENCE.md (user journeys, flow diagrams, screen states, error/empty/loading handling). Use when the user says "design the UX", "create UX planning docs", "define the design system", "map the user flows", "UX for this feature", "wireframe the flows", "what are the user journeys", "accessibility design", "WCAG compliance", "design tokens", "responsive design plan", "mobile-first design", or "create DESIGN.md / EXPERIENCE.md". Runs after architecture is drafted and before stories are created. Supports Create / Update / Validate intents.
Reach sites that BLOCK ordinary automation — the same navigate/inspect/interact/report loop as the `browse` skill, but on browse's camoufox runtime: a hardened Firefox with C++-level fingerprint spoofing, geoip, and humanized timing that passes Cloudflare Turnstile, Google "unusual traffic", DataDome, and PerimeterX, with named profiles, authenticated sessions, and proxy rotation. Honest about its limit: fingerprint spoofing alone will not defeat IP-reputation blocks — pair it with a residential proxy. Use when a page challenges or 403s a normal browser.
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.
