Skills
98,873 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Create professional cinematic scripts for AI video generation with character consistency and cinematography knowledge. Use when the user wants to write a cinematic script, create story contexts with characters, generate image prompts for AI video tools (Midjourney, Sora, Veo), or needs cinematography guidance (camera angles, lighting, color grading). Also use for character consistency sheets, voice profiles, anachronism detection, and saving scripts to Google Drive.
CRM-lite for managing GEO agency prospects and clients. Track leads through the full sales pipeline: Lead → Qualified → Proposal Sent → Won → Lost. Store audit history, notes, deal values, and generate pipeline summaries. Use when user says "prospect", "lead", "client", "pipeline", "crm", "nuovo prospect", "aggiungi cliente", or when managing the business side of GEO services.
Scrapes all tweets, replies, and media from any Twitter/X account using apidojo's Tweet scraper on Apify. Triggers when the user asks to: get all tweets from a Twitter account, export a user's tweet history, scrape a specific Twitter profile's posts, fetch the latest tweets from an account, download tweet data from a user timeline, or collect all posts from a Twitter username. Returns tweet text, likes, retweets, replies, media URLs, and timestamp per tweet. Ideal for journalists, researchers, competitive analysts, and data engineers.
Plans web-novel and novel topics for requests such as finding a story idea or genre, identifying popular or marketable genres, evaluating a novel concept, brainstorming a protagonist's special advantage, or analyzing web-novel market trends. Uses AI's knowledge of the web-novel market to generate 3–5 distinct concepts, including a special advantage, core selling points, payoff patterns, and feasibility scores. Flags conclusions that need human cross-checking against platform rankings.
Performs ARA Seal Level 2 semantic epistemic review on Agent-Native Research Artifacts, scoring six dimensions (evidence relevance, falsifiability, scope calibration, argument coherence, exploration integrity, methodological rigor) and producing a constructive, severity-ranked report with a Strong Accept-to-Reject recommendation. Use after Level 1 structural validation passes, when an ARA needs an objective epistemic critique before publication or release.
Pre-indexed code knowledge graph (MCP, SQLite + tree-sitter) for faster, lower-token exploration of brownfield codebases. Use when starting work on a repo larger than ~500 files or when the task involves cross-file traversal — "where is X used", "what calls Y", "what breaks if I change Z", "trace flow from A to B", "explain this subsystem". Skip for single-file edits or sessions shorter than the cold-start cost. Triggers include "codegraph", "code graph", "index this repo", "where is X defined", "find callers of", "callees of", "blast radius of changing X", "explore this codebase". Cuts the grep + Read loops needed to orient, via O(1) SQLite lookups and FTS5 search over 8 MCP tools — but it's an unsound tree-sitter approximation, so grep stays the completeness backstop for renames/exhaustive callers.
Finds industry event and conference coverage on Google using apidojo's Google Search scraper. Triggers when the user asks to: find coverage of an industry conference or event on Google, track press coverage of a trade show or summit, research what was announced at a conference, find news and recaps of an industry event, discover what happened at a recent trade show, find speaker quotes or session summaries from a conference, or compile event coverage for competitive intelligence. Returns article list with title, publication, date, coverage type, and key announcement signals. Ideal for industry analysts, competitive intelligence teams, PR professionals, and event marketers
Interview the user relentlessly to expand context and surface intent, constraints, hidden assumptions, and unstated alternatives. Use whenever the user invokes `/grill-me`, says "grill me", "interview me", "pressure-test this", "help me think through", or whenever the user's first message is more decision than task — across coding, business, marketing, personal branding, SOPs, systems thinking, process design, and tough decisions.
Rewrites Russian text with signs of AI generation so it reads as if written by a real person: removes bureaucratic language, ChatGPT clichés, empty lead-ins, “not just X, but Y,” triples, excess dashes and bold, and junk chat insertions (contentReference, utm_source, invisible characters). Preserves and checks numbers, names, dates, conditions, and negations. Use when asked to “humanize,” “rewrite naturally,” “remove GPT-ness,” “make it lively,” “remove bureaucratic language / fluff / clichés,” when text “sounds like AI,” to “edit” or “polish” text, and also for analysis without editing: “what gives away AI,” “check the text.” Russian only.
How to work in a Knowledge Base project (the `knowledge-base` starter pack). Read when the project has the three-layer source-grounded layout — `external-sources/` → `research/` → `articles/` — or when asked how this project is organized. Carries the layer model, per-folder rules, status flows and log discipline so this guidance does NOT live inside template bodies or log.md. The three procedures live elsewhere: ingest in the platform `open-knowledge` skill, research and consolidate as their own sibling skills in this pack. Complements the platform `open-knowledge` skill; does not replace it.
Scrapes Instagram posts for any hashtag using apidojo's Instagram scraper on Apify. Triggers when the user asks to: get Instagram posts for a hashtag, scrape Instagram content by tag, export Instagram post data for a keyword or topic, fetch posts under an Instagram challenge or trend, collect Instagram media for a specific tag, or download Instagram post metadata by hashtag. Returns post URL, caption, like count, comment count, author handle, and timestamp per post. Ideal for trend analysts, UGC collectors, and social media researchers.
The AI music + sound-design skill for social — original/licensed audio beds and sound design for Reels/TikToks/Shorts/videos. Use when someone needs background music, a track, or sound effects for a social video, asks which AI music tool is safe to use, or asks "can I use this trending sound/song on my brand video?". The real brief is "audio that won't get muted, claimed, or sued," so it picks the safest licensed source and never uses copyrighted or trending music without a license. Uses the SCORE framework. Reads brand-profile + the video it scores first. The agent briefs the music + sound design, picks the safest licensed source (ElevenLabs Music/SFX or stock libraries over Suno/Udio; paid tier for commercial rights), and advises licensing/Content-ID/disclosure. The tool generates/licenses the audio; the creator bakes it in; WoopSocial publishes the video and does NOT generate music. Pure AI music may not be copyrightable; never "100% legally safe." Pairs with ai-voiceover.
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, FK replacement code generation, OCC retry patterns, ORM migration (Django/Hibernate/Rails), DDL operations, query plan explainability, SQL compatibility validation, and bulk data loading. Triggers on phrases like: DSQL, Aurora DSQL, distributed SQL database, serverless PostgreSQL-compatible database, migrate to DSQL, DSQL query plan, DSQL EXPLAIN ANALYZE, DSQL ENUM, DSQL foreign key, DSQL OCC retry, DSQL multi-region, DSQL JSONB, DSQL GIN index, load into DSQL, load CSV into DSQL, bulk load DSQL, aurora-dsql-loader.
Use this skill when working with Phaser 4 game object components and the mixin system. Covers Transform, Alpha, Tint, Origin, Depth, Flip, Mask, GetBounds, Lighting, and other shared component behaviors. Triggers on: component, mixin, transform, mask, bounds, lighting.
Use to write great prompts for Nano Banana (Google's Gemini image model: Nano Banana Pro = Gemini 3 Pro Image) to generate or edit images for social media — the image-prompt-craft mini-skill. Run when the user wants a nano-banana / Gemini image prompt, an AI image for a post (quote graphic, carousel slide, thumbnail, infographic, product shot, ad creative), or conversational image editing. Reads brand-profile for brand colours/style. Strengths: best-in-class legible in-image text (route typography/layout-led design to ideogram), multi-image consistency, conversational editing, and Google's photoreal lane (Imagen deprecated); surreal art stays Midjourney's. Teaches prompt anatomy, the text-first approach, reference-image consistency, and per-platform aspect ratios. Honest: SynthID watermark + AI disclosure; never real identifiable people or copyrighted characters/logos; verify spelling/data. The API/connection and WoopSocial upload flow live in tools/integrations/nano-banana.md.
Use when building Slack agents/bots with eve (Vercel's filesystem-first agent framework), @vercel/connect, or eve/channels/slack. Covers defineAgent/defineTool patterns, Vercel Connect credential brokering, Slack channel setup, testing requirements, and quality standards.
Use this skill when the user asks to "make a fake text message video", "animate an iMessage conversation", "create a text story video", "do a chat reply animation", "WhatsApp/SMS conversation video", "typing indicator animation", "render a chat thread to a video", or "batch text-message videos from a script/CSV". Covers sent/received bubble layout, staggered appear timing with typing indicators, read receipts/timestamps, per-message pop sound-sync, 9:16 safe-area, and data-driven render from a messages array.
Write and publish single posts on Meta's Threads — the Threads format-execution skill. Use when someone wants a “Threads post,” to “post to Threads,” grow on Meta's Threads, or publish a Threads post via WoopSocial. Writes a Threads-native conversation post (text <=500 + optional media) designed to earn replies — Threads is conversation-first: replies outweigh likes and engagement velocity drives distribution. Uses the REPLY framework. Reads brand-profile + goals-and-kpis first. WoopSocial publishes ONE Threads post (no native multi-post chain, no polls/voice/GIF, no reply surface); the replying that drives reach is a human/community-management job; metrics are never fabricated; no engagement bait. Distinct from thread-writer (a user saying “write a thread” wants that multi-post X chain, not this), x-growth (sibling text platform, different culture) and caption-writer (text only)
Use when writing, reviewing, or refactoring code for maintainability and readability. Triggers on code reviews, naming discussions, function design, error handling, and test writing. Based on Robert C. Martin's Clean Code handbook with modern corrections.
The Facebook Groups strategy skill -- Groups as Facebook's real organic surface, deeper than what facebook-strategy routes to community-management. Use when someone wants to build/grow/run a Facebook Group, decide Group vs Page, or turn a community into leads. Groups reach 40-50% of members per post vs ~1.5% for Pages; Facebook deliberately favors Groups. Uses the TRIBE framework. Reads brand-profile + goals-and-kpis first. The agent designs the group strategy (niche, setup, content, growth, moderation, value-first monetization) and drafts group posts + the join-funnel content. CRUCIAL: WoopSocial does NOT post to Groups -- it publishes the Page + cross-channel content that funnels people to JOIN; in-group posting, admin, moderation, and Group analytics stay native/human, routed to community-management. No automation/spam or fake members; value-first, never fabricates metrics. Distinct from facebook-strategy (the Page play) and community-management (the engagement routine).
Auto-generate a professional, client-ready GEO service proposal from audit data. Creates a full proposal in markdown and PDF including executive summary, findings, recommended service packages (Basic/Standard/Premium), pricing, timeline, and terms. Use when user says "proposal", "proposta", "offerta", "preventivo", "generate proposal", or after completing a GEO audit for a prospect.
Writes failing tests first for test-driven development and hands off a strict implementation contract that requires agents to make those tests pass without weakening the tests. Use when users ask for test-first workflows, RED/GREEN cycles, or behavior-gating tasks with automated tests.
Use when the spoken content of a YouTube video is needed — even if not explicitly requested: pasted video links or IDs, requests to summarize, quote, transcribe, translate, fact-check, or extract anything from a video. Also use for research or learning when a video is the source. Not for uploads or account management.
Consumer-side guide for integrating @lodev09/react-native-true-sheet into a React Native app. Use this skill whenever the user wants to add, configure, control, or debug a bottom sheet using TrueSheet — including ref-based sheets, named global sheets, web support with TrueSheetProvider/useTrueSheet, React Navigation or Expo Router sheet flows, Reanimated-driven animations, scrolling content, stacking, headers/footers, detents, peeking, side sheets, keyboard handling, dimming, backgrounds, liquid glass, and Jest testing. Also use when the user is migrating from v3 to v4, troubleshooting layout or gesture issues, or asking about any TrueSheet prop, event, or method — even if they don't mention "TrueSheet" by name but describe a bottom sheet in a React Native context.
Analyze short-form videos with Gemini AI to extract hooks, content structure, and replicable patterns. Supports Instagram Reels, TikTok, and YouTube Shorts. Use when asked to: - Analyze video content for hooks and structure - Extract replicable formulas from viral videos - Understand why a video performed well - Get AI analysis of video content patterns Triggers: "analyze videos", "extract hooks", "video analysis", "analyze reels", "what makes this video work", "hook analysis", "content structure analysis"
Analyzes a competitor's Instagram content strategy and performance using apidojo's Instagram scraper on Apify. Triggers when the user asks to: analyze what a competitor posts on Instagram, benchmark a competitor's Instagram engagement, see what content types perform best for a competitor on Instagram, reverse-engineer a competitor's Instagram content calendar, identify content gaps vs. a competitor on Instagram, compare posting frequency or content themes, or understand why a competitor's Instagram is growing. Returns post frequency, content type mix, top-performing posts, hashtag strategy, and engagement benchmarks. Ideal for social media managers, brand strategists, and content marketing teams.
LangChain / LangGraph engineering pitfalls and verified fixes. Covers DeepAgents, structured output, OpenAI-compatible model integration (including Chinese provider adapters: DeepSeek, Qwen, GLM, etc.), middleware, streaming, multi-agent orchestration and other common development issues. Use when hitting unexpected behavior, making architecture decisions or integrating Chinese LLM providers during LangChain development
The annual moment-planning skill — map the few seasonal/cultural/commercial moments that genuinely fit your brand, gate them for fit + authenticity, tier by weight, and plan far in advance. Use when someone wants a seasonal/holiday content plan, a moment calendar, to plan Black Friday/holiday content, or to decide whether to post for a holiday/awareness day. The planned counterpart to trend-jacking's reactivity: silence on the wrong day beats noise on the wrong topic. Uses the DATES framework. Reads brand-profile + audience-research first. The agent builds the calendar, gates fit + authenticity, tiers, plans lead-time, feeds content-calendar. Big moments route to campaign-and-launch-planning + paid; the reactive half to trend-jacking. WoopSocial schedules ahead — it does not pick moments, judge authenticity, or run paid. Never join identity/cause moments without year-round standing; never fabricate. Distinct from trend-jacking, content-calendar, and campaign-and-launch-planning
Use when converting an AI-generated static HTML page (Stardust, Mobirise, Relume, Lovable, v0, Figma-derived, etc.) into an Edge Delivery Services page while preserving the original design and making content authorable in Document Authoring: triggers include "convert this page to EDS", "static-to-EDS overlay", "convert to EDS blocks", "next experimentation", "next run", "start run", or providing a source URL to make editable in DA. Covers two modes: page-level (overlay template with slot markers) and block-level (each section becomes an independent EDS block). For canonical EDS block-rewrite migrations use page-import instead
Expert guidance for systematic backtesting of trading strategies. Use when developing, testing, stress-testing, or validating quantitative trading strategies. Covers "beating ideas to death" methodology, parameter robustness testing, slippage modeling, bias prevention, and interpreting backtest results. Applicable when user asks about backtesting, strategy validation, robustness testing, avoiding overfitting, or systematic trading development.
Extracts and analyzes YouTube comments for audience research using apidojo's YouTube scraper on Apify. Triggers when the user asks to: extract YouTube comments for research, analyze what viewers say in YouTube comments, scrape comments from a YouTube video for sentiment analysis, find common questions in YouTube comments, research audience feedback from YouTube video comments, extract top comments from a YouTube channel for audience insights, or analyze viewer reactions from YouTube comment sections. Returns comment text, likes on comment, reply count, commenter username, and timestamp. Ideal for content creators, brand researchers, product teams, and audience insight analysts.
Send Feishu messages. Send messages (10 types, including text/post/interactive cards: text/post/image/file/audio/media/sticker/interactive/share_chat/share_user; system separators are not directly supported by the CLI and must be passed through with `feishu-cli api`), reply to messages, forward or merge-forward messages, mark messages as urgent, manage message bookmarks (flag add/list/cancel), and download message resources (images/files). Sending, replying, forwarding, and marking urgent default to App Token (Bot identity); message flag bookmarks require User Token (`im:feed.flag:read/write`); msg resource-download prefers User Token when logged in and falls back to App Token otherwise. Use when the user explicitly requests sending, replying to, forwarding, merge-forwarding, marking urgent, bookmarking, or downloading message images or files through Feishu IM/Bot messages. Use feishu-cli-mail for email; use the relevant skill for document comments or sharing permissions. Note: use the feishu-cli-chat skill for Reaction/Pin, getting message details, batch message retrieval, thread replies, message history, searching group chats, group chat management, and deleting messages (App Token by default for a Bot to retract its own messages; optional User Token lets an administrator retract others' messages). To send interactive cards, first use feishu-cli-card to build v2 JSON, then return to this skill and send with --msg-type interactive --content-file.
Installs NemoClaw, launches a sandbox, and runs the first agent prompt. Use when onboarding, installing, or launching a NemoClaw sandbox for the first time. Trigger keywords - nemoclaw quickstart, install nemoclaw openclaw sandbox, nemohermes quickstart, hermes agent nemoclaw, run hermes openshell sandbox, nemoclaw prerequisites, nemoclaw supported platforms, nemoclaw hardware software, nemoclaw windows wsl2 setup, nemoclaw install windows docker desktop.
An end-to-end worldbuilding and creation orchestrator for web novels and novels. Handles broad requests such as starting a novel from scratch, writing a novel in a particular genre, setting up the full writing process, or turning an idea into a finished book. Coordinates the full workflow: topic selection → outline → writing → review → polishing → export, with actionable acceptance gates at each stage. Chapter-level work is handled in parallel by sub-agents, each responsible for at most 3 chapters.
The transformation / before-after content format — structure a credible, honest, satisfying transformation (fitness, beauty, business results, skill progress, makeovers, client glow-ups, product before/after). Use when someone wants a before/after, a transformation post, a client-results reveal, a progress/journey story, or a makeover. Most powerful format AND most abused/distrusted — honesty is the edge; FTC enforcement is live. Uses the SHIFT framework. Reads brand-profile + social-proof-and-testimonials (consent + FTC substantiation) + short-form-video-script first. Agent structures + specs; human/tool produces the real media; WoopSocial publishes. Never stages/exaggerates the before, hides aids, cherry-picks, or fabricates a result; "results not typical" alone is insufficient — disclose the actual typical result; consent + YMYL required. Distinct from social-proof-and-testimonials, short-form-video- script, infographic-and-data-viz, and storytelling-and-narrative.
DBOS Python SDK (3.x) for building reliable, fault-tolerant applications with durable workflows. Use this skill when writing Python code with DBOS, creating workflows and steps, using queues, datasource transactions, or schedules, using DBOSClient from external applications, upgrading DBOS Python 2.x code to 3.x, or building applications that need to be resilient to failures.
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.