Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
This skill should be used when the user asks to “make a sale video,” “create a promo video,” “build a discount/percentage-off reveal,” “animate a was→now price with a strike-through,” “do a Black Friday / flash-sale / clearance video,” “make a promo-code reveal with a countdown,” or “batch a promo template across many products.” Covers the offer-announcement arc — discount reveal, price strike-through, promo code, urgency, product shot, CTA — and product+offer data → many videos.
ElevenLabs speech-to-text with Scribe models and forced alignment via inference.sh CLI. Models: Scribe v1/v2 (98%+ accuracy, 90+ languages). Capabilities: transcription, speaker diarization, audio event tagging, word-level timestamps, forced alignment, subtitle generation. Use for: meeting transcription, subtitles, podcast transcripts, lip-sync timing, karaoke. Triggers: elevenlabs stt, elevenlabs transcription, scribe, elevenlabs speech to text, forced alignment, word alignment, subtitle timing, diarization, speaker identification, audio event detection, eleven labs transcribe
ElevenLabs voice isolator - remove background noise and isolate vocals from audio via inference.sh CLI. Capabilities: noise removal, voice extraction, audio cleanup, background removal. Use for: podcast cleanup, interview audio, music vocals, noisy recordings, audio restoration. Triggers: voice isolator, noise removal, background removal, isolate voice, clean audio, remove background noise, audio cleanup, voice extraction, elevenlabs isolator, eleven labs noise, vocal isolation, denoise, audio restoration, voice separation
Builds figures that move or respond to the reader in three tiers: SMIL animations and slider widgets inside lessons, interactive mechanism figures that show the named parts of a real system with a computed verdict, and ordered dither bands in the course palette. Triggers: “animated figure,” “add a slider widget,” “interactive figure,” “show how this system works,” “make this diagram move,” “dither masthead,” “mechanism figure,” “figure fence.”
ElevenLabs voice changer - transform any voice to a different voice while preserving speech content and emotion via inference.sh CLI. Models: eleven_multilingual_sts_v2 (70+ languages), eleven_english_sts_v2. Capabilities: speech-to-speech, voice transformation, accent change, voice disguise. Use for: content creation, voice acting, privacy, dubbing, character voices. Triggers: voice changer, speech to speech, voice transformation, change voice, voice swap, voice conversion, voice disguise, eleven labs voice changer, elevenlabs sts, transform voice, ai voice changer, voice modifier
Atlas Cloud API integration skill — quickly call 300+ AI image generation, video generation, audio (TTS, music, speech-to-text), 3D generation, and LLM models through a unified API. Use this skill when the user needs to integrate AI image generation (e.g., Flux, Seedream, DALL-E), AI video generation (e.g., Kling, Sora, Seedance), call LLM APIs (OpenAI-compatible format), generate speech/TTS or music (e.g., Seed Audio, Suno), transcribe audio to text (ASR), or turn images/text into 3D assets into their project. Also covers model discovery and keyword search, uploading local images/media files, one-step quick generation, and configuring ATLASCLOUD_API_KEY. Even if the user doesn't explicitly mention Atlas Cloud, this skill should be considered whenever AI media generation API integration development is involved.
Use when adding or maintaining a direct Runway Dev model endpoint in an application, including image, video, audio, or task handling. Discover current model access and constraints when needed, follow the exact endpoint contract, and integrate through the official SDK. For configured model-agnostic routing, use runway-dev-model-routers instead.
Create polished audio content and save to Spotify. Produces episodes with TTS narration, a rich timeline (chapters plus in-player images, external links, and Spotify entity cards), and a cover image. Also use for raw media saves, show/episode management, and timeline navigation.
When you want to extract content from a video — YouTube, Loom, Vimeo, Riverside, Zoom recording, local MP4, X/IG video, anything yt-dlp supports. Three depth modes user picks per invocation — transcript (just words, fast/free), visual (transcript + ffmpeg frame extraction + Claude vision pass on key moments), multimodal (Gemini native video ingestion if $GEMINI_API_KEY set, else dense Claude vision). Uses local Whisper for transcription (MLX-Whisper on Apple Silicon, faster-whisper elsewhere), falls back to platform-provided transcripts when available (Loom, Riverside, YouTube auto-subs). Saves to ~/Documents/videos/<source>-<slug>-<date>/ and optionally captures summary to second-brain raw/ as call-/meeting-/note-. Triggers on "/watch-video <url>," "watch this video," "transcribe this loom," "analyze this video," "summarize this recording," "key moments from this," "what happened in this video." For a post's text and engagement, use social-fetch.
Create a clean, vertical editorial artwork that preserves an uploaded photograph as the original image and pairs it with a restrained, photo-derived abstract memory panel and poetic English title. Use when asked to transform a photo into an abstract editorial diptych, photo-plus-abstraction composition, visual memory panel, or minimalist archival poster without redrawing or stylizing the source photo.
ByteDance AI video creation tool. Supports comic drama, short drama and film creation, automating the entire process from script to finished cut. Trigger words: comic drama, short drama, film, anime video, manga video, story video, short video creation, comic drama generation, animation production, drama video, byted-drama
Use this skill when the user asks to "make a math animation", "animate an equation", "use Manim", "make a 3Blue1Brown-style video", "plot or animate a graph/function", "visualize a math/physics/CS concept", "morph one formula into another", "animate a geometric proof", or "render a math explainer". Covers Manim Community Edition — Scenes, Mobjects, animations, LaTeX/MathTex, graphs, updaters/ValueTracker, 3D, and rendering to MP4/GIF via the CLI.
YouTube video search, video download, and subtitle download tool. Uses YouTube Data API v3 for advanced search and yt-dlp to download videos, audio, and subtitles. Core capabilities: site-wide keyword search, channel browsing, sorting by time/views/relevance, video download, audio extraction (MP3), subtitle download (Chinese and English), and video details. Trigger scenarios (use this skill for any YouTube-related task): search, e.g. "search YouTube", "find YouTube videos", "latest videos from [channel name]", "[person name] on YouTube"; channel browsing, e.g. "browse channels", "see the latest videos from [channel name]", "[person name]'s recent videos", "video list of [channel name]"; video download, e.g. "download this video", "download YouTube video", "save the video"; audio download, e.g. "extract audio", "download audio", "convert YouTube to MP3", "audio only"; subtitle download, e.g. "download subtitles", "extract subtitles", "get subtitles", "Chinese subtitles", "English subtitles", "extract text", "video to text"; video info, e.g. "video details", "video info", "how long is this video". Keyword matching: trigger this skill whenever the user message contains "YouTube", "oil pipe" (YouTube slang), "YT", or "yt" together with action words like search, download, subtitles, channel, or video.
The Instagram Reels publishing-mechanics skill — distinct from reels-script (the script), instagram-seo (the keyword caption), and platform-specs-and-validation (cross-platform validation). Use when someone has a finished Reel and needs to publish it correctly: specs, cover, safe zone, publish settings. It gets the Reel out the way Instagram displays it: 9:16 spec-clean video, the safe zone that survives the feed and profile-grid crops, a custom grid-safe cover (chosen before publish, can't edit after), the keyword caption, and audio. Uses the FRAME framework. Reads brand-profile + the Reel asset first. The agent specs the publish settings, cover brief, and specs/safe-zone checklist, and advises audio/tags. WoopSocial publishes postType REEL + video + caption + cover on a schedule; trending audio, Share-to-Feed, tags, and Reel Insights stay native/in-app; the video/cover come from other tools. Remove other-platform watermarks; metrics never fabricated.
Generates high-quality images for WeChat public account articles. Supports cover images (2.35:1), inline illustrations (16:9/4:3), and infographics. Offers two paths: AI generation (visually creative) and HTML rendering (text-accurate). Use this skill when the user mentions "公众号配图" (public account images), "公众号封面" (public account cover), "文章配图" (article images), "正文插图" (inline illustrations), or "公众号图片" (public account pictures).
Diagnose world-level story problems. This skill should be used when settings feel thin, institutions feel designed rather than evolved, economies don't make sense, or non-human species feel like humans in costume. Keywords: worldbuilding, setting, world, institutions, economy, culture, species, consequences.
Generates high-quality images for Xiaohongshu notes. AI generation (Gemini) by default, with HTML as a fallback only for exact data tables. Use this skill when the user mentions "Xiaohongshu image", "Xiaohongshu cover", "Xiaohongshu picture", "make a Xiaohongshu image" or "note image".
Colloquial polish for video scripts, removing overly formal wording so the script sounds natural when spoken. Use when the user mentions "口语化" (colloquial), "太书面了" (too written/formal), "像说话一样" (like spoken speech), or "脚本审校" (script review).
Give your agent the ability to speak to you real-time. Talk to your Claude! Local TTS, text-to-speech, voice synthesis, audio generation with voice cloning on Apple Silicon. Use for reading articles aloud, audiobook narration, or voice responses. Runs entirely on-device via MLX - private, no API keys.
Entry command that naturally polishes Korean text written by AI. Runs the humanize-korean pipeline along the path set by the shim's route_hint (light 1 call · standard 2 calls · heavy 3+ calls), and pins heavy when `--strict` is given. Trigger — "/humanize".
Use when the user asks for stagefight or a task matching the examples below. Generate a viral "fan-filmed staged fight" clip — POV phone footage of two costumed performers having a choreographed cosplay battle on an elaborate themed stage at a live outdoor event, with a believable live-stage effect (smoke / colored fire / water geyser) and a crowd in the foreground filming. A gpt-image-2 stage still → image-to-video (Seedance, ~10s, 16:9). The advertiser-safe "theatrical performance" framing is what gets fight content past moderation. Triggers: "/stagefight", "make a staged fight video", "fan-filmed cosplay fight", "ninja/samurai stage battle", "that staged fight trend". Requires the pika MCP.
Use when the user asks for gameday or a task matching the examples below. Put a fan into the game. The user uploads one photo of themselves and names their favorite team; generate a 6-photo matchday-superfan carousel — six separate images of that same person at the game in their team's kit. Triggers: "/gameday", "make me an [team] superfan", "put me at the game", "gameday carousel". Requires the Pika MCP.
The idea-system craft — never run out of content ideas by running a system instead of waiting for inspiration. Use when someone is out of ideas, stares at a blank calendar, asks where good ideas come from, wants an idea bank/backlog, feels their AI-generated ideas sound like everyone else's, or thinks their niche is "boring." Uses the SPARK framework. Reads brand-profile + social-strategy + content-pillars + audience-research first. The audience is the idea engine (comments/DMs/FAQs clustered into themes); AI expands real signals, it doesn't discover them; systems beat muses; trends are a timing filter, not a source. The agent clusters/expands/scores; the HUMAN supplies proprietary signals and decides; WoopSocial publishes the content, not ideas. Never rewords competitor posts, invents audience questions, or fabricates probe results. Distinct from social-strategy/content-pillars, audience-research, cross-platform-repurposing/ content-recycling, and the format skills
Apply actions and animations to sections of a video/audio with auto-editor — change speed, duck or fade volume, de-ess, zoom/Ken Burns, rotate/spin, draw boxes, overlay logos or picture-in-picture, and animate any of these with ramps and easing. Use when someone wants creative effects or per-section behavior rather than plain silence-cutting.
Master Syncfusion React Image Editor for comprehensive image editing. Use this when users need to edit images, add annotations, apply filters, manage layers, or implement image editing features. Supports multiple formats (PNG, JPEG, SVG, WEBP, BMP), annotations (text, shapes, freehand, images), effects (filters, finetune), and accessibility features.
Comprehensive toolkit for detecting and eliminating "AI slop" - generic, low-quality AI-generated patterns in natural language, code, and design. Use when reviewing or improving content quality, preventing generic AI patterns, cleaning up existing content, or enforcing quality standards in writing, code, or design work.
A speaking and presentation coach. Based on the How to Speak methodology of Patrick Winston (MIT AI professor), it helps prepare talks for in-person training, tech sharing sessions, and tutorial videos on Bilibili. Use this skill when the user mentions "presentation", "sharing", "training", "lecturing", "PPT talk", "opening", "ending", "how to speak", or "speech structure".
Use when connecting an AI agent to Scenario (scenario.com) through MCP, or when a task involves generating images, video, 3D, audio, sprites, textures, or game assets. Also when picking a Scenario model, running a LoRA, refining a generation prompt, uploading reference images, waiting on generation jobs, checking credits or quota, hitting Scenario auth, scope, or Forbidden errors, or setting up mcp.scenario.com in Claude Code, Cursor, VSCode, or another agent.
This skill should be used when the user asks to "validate", "reindex", "repair registries", "check links", "run the continuity, pacing, clue, voice, or name checks", "count words", "summarize a story project", "import an existing manuscript", "export a manuscript", "run a build", "generate a diagram", "record revision-pass status with `story passes`", "run the story CLI", or wants deterministic maintenance on a Story Skills markdown project. It runs the CLI and reads its output; NOT for judging a finding or revising the story to fix it (use revision-continuity for continuity errors and revision passes, plot-structure for pacing, voice-style for voices and prose, genre-craft for clues and fair play), or for sharing a review copy with readers (use feedback-triage).
Build identity-preserving character generation workflows and pipelines in ComfyUI. Selects the optimal identity method (InfiniteYou, FLUX Kontext, PuLID, InstantID, IP-Adapter) based on use case requirements. Handles face preservation, likeness transfer, cross-domain conversion (3D to photo), multi-reference consistency, iterative character editing, and character variation generation. Triggers on requests to generate consistent characters, preserve identity across images, create face-swapping workflows, or convert 3D renders to photorealistic portraits. Does NOT cover general image generation without identity preservation, model training/LoRA fine-tuning, animation, technical explanations, or workflow debugging.
Deconstruct and analyze video ad creatives for marketing insights. Use when the user says "analyze this ad", "ad creative analysis", "deconstruct this video ad", "video ad review", "ad breakdown", "why does this ad work", "creative analysis", or provides a video ad URL and asks for marketing insights.
The on-camera delivery craft — helping a real human film themselves talking to a lens and look like themselves doing it. Use when someone wants a "talking head video" or "piece to camera," says "film myself" or "I look stiff on camera," asks about a teleprompter, framing, lighting, audio, or retakes, or wants to batch-film videos. Uses the TAKES framework. Phone-first: gear is almost never the bottleneck. Reads brand-profile + voice-builder first; takes its script from short-form-video-script (that writes it, this delivers it). The agent coaches setup + delivery, formats prompter/beat-map scripts, and plans batch days; the HUMAN films and picks the take (the agent cannot see footage); WoopSocial publishes the finished file. Camera-shy? Route honestly to heygen/synthesia or faceless formats. Never fabricates "that take looks great." Distinct from scripting-and-storyboarding (the shoot plan), heygen/synthesia (avatars), and captions-and-clipping/capcut/descript (the edit).
Use when the user asks to create a demo video, product walkthrough, feature showcase, animated presentation, marketing video, or GIF from screenshots or scene descriptions. Orchestrates playwright, ffmpeg, and edge-tts MCPs to produce polished video content.
Use when asked to make a launch video, product film, motion design piece, UI motion reel, Dribbble-style UI animation or animated brand/logo sting—anything rendered to MP4 from HTML with a cursor, morphing UI, springs, beat-synced music and SFX. Carries Chan's full creative direction (one shape never cut, blur content swaps, springs, real data, logo slams, no creative limits) and the proven build/render pipeline (pure seek(t), closed-form springs, Playwright subframes, ffmpeg tmix, numpy beat grid).
Detect and rewrite AI-like Chinese text with a practical workflow for scoring, humanization, academic AIGC reduction, and style conversion. Use when the user asks to 去AI味, 降AIGC, 去除AI痕迹, 论文降重, 知网检测, 维普检测, humanize chinese, detect AI text, or make Chinese text sound more natural.
The writing-craft skill — style and tone as applied technique: rhythm, specificity, tone modulation, and the edit passes that make writing read as human. Use when someone's posts "sound like ChatGPT," a draft needs a style edit, they ask how to write differently per platform or moment without losing the brand voice, writing is grammatically perfect but exhausting, a manager wants em dashes banned or detector scores chased, or any AI-assisted draft needs its mandatory quality pass. Uses the STYLE framework. Reads voice-builder + brand-profile + the format skill first. Tells must be read as a cluster with judgment — no single marker proves AI, and detectors misflag real writers; the winning move is substance so owned the question never arises. Voice is identity; tone is register. The agent drafts; the HUMAN supplies lived specifics and final say; never invents anecdotes or staged typos. Distinct from voice-builder, hook-writer, the format skills, and content-research-and-sourcing.
The growth engine for YouTube long-form video in 2026. Use when someone asks to "grow my YouTube channel," "get more views on my videos," "plan/script a YouTube video," "improve my CTR or retention," "why did my video flop," or wants a long-form strategy. Produces packaging concepts + scripts; the human films/edits/designs the thumbnail; publishing routes through scheduling-and-queue -> WoopSocial; analytics and session features live in YouTube Studio. The opposite engine from, and sibling to, youtube-shorts.
Write dense storyboard-grid prompts for short-form image or previsualization workflows. Use this when a generation task needs a 6-9 panel grid with hook logic, visible actions, product timing, and negative constraints before image or video generation.
Creates jaw-dropping, production-ready frontend interfaces AND delivers perfectly matched real photos (Unsplash/Pexels direct links) OR flawless custom image-generation prompts for hero images, backgrounds, and illustrations. Zero AI slop, zero fake URLs.
Use as the foundation and router for any image a post needs — turn a social need into a clear image brief, describe it with model-agnostic prompt craft, and route to the right tool. Run when the user says “I need a visual/image for this post,” “what image should I use,” “make a graphic,” “help me prompt an image,” or is unsure which image tool/model to use. Reads brand-profile for the visual brand. Teaches the image brief, the universal anatomy of a strong prompt in natural language, and a tool router (typographic -> ideogram/nano-banana; photoreal -> nano-banana/flux; surreal -> Midjourney; editing -> nano-banana/flux; vector -> Recraft; video -> veo-3). Includes a “should this even be AI-generated?” gate (a real photo, screenshot, or chart often beats generic AI), accessibility, and honest scope (disclose AI, never real identifiable people or copyrighted IP, verify text/data). Hands off to the tool-specific mini-skills; WoopSocial publishes via Media and doesn't generate images.
The AI narration / voiceover mini-skill (ElevenLabs-led). Use when someone wants an "AI voiceover," "narration," "text-to-speech for a video," "voice for my Reel/Short/explainer," "clone my voice," or to "dub a video into other languages." Picks the voice and model, writes for the ear, and directs the delivery; ElevenLabs generates the audio, the human mixes/reviews, WoopSocial schedules/publishes. Sits below the ai-video router, sibling to veo-3 and heygen. Consented voices only; disclose AI voice in ads/political.
Automatically generate illustrations based on document content. AI analyzes the document structure, summarizes the core points, and generates illustrations in a specific style for each topic. Supports cover image generation and custom image ratios. Use cases: when a user needs illustrations for a document, article, or note. Keywords: illustration, generate images, document images
Generate, remix, extend, edit, and analyze AI music (Mureka). Triggers on: "音乐", "music", "生成音乐", "generate music", "翻唱", "cover", "混音", "remix", "续写", "extend", "纯音乐", "instrumental", "配乐", "soundtrack", "分轨", "stem", "识别歌词", "recognize lyrics", "作曲", "compose", "create a song", "做一首歌"
Redoes the most recent humanizing result a second time — with the option to adjust specific categories, paragraphs, and intensity. Re-runs humanize-korean strict humanizing (Phase B) on the existing run_id to handle remaining findings. Trigger — "/humanize-redo".
Use the genmedia CLI to search, inspect, run, and manage 1200+ fal.ai model endpoints. Trigger when the user mentions "genmedia", "fal CLI", or asks to "search models", "run a model", "fetch schema", "check pricing", "upload to fal", "queue async job", "track request", or any direct interaction with the fal.ai endpoint catalog. This is the foundational skill. Every other fal.ai-related skill in this repo executes its work through genmedia commands. Use `--json` whenever the output will be parsed by an agent.
Generate 4-30 second cinematic video with ByteDance Seedance 2.5 through fal.ai, Volcengine Ark, Runway, or ComfyUI Partner Nodes. Use for long single generations, synchronized audio, and large multimodal reference sets (up to 30 images, 10 videos, and 10 audio clips). Also covers the 2.5 prompt contract: section order, multi-shot "Hard cut" breakdown, named locks for continuity across cuts, the asset and character-sheet method, voice conditioning, and iteration discipline
Use to write great prompts for Google Veo (Veo 3.1) to generate or animate video for social media — the video-prompt-craft mini-skill, the video counterpart to nano-banana. Run when the user wants a Veo / AI video prompt, a short video clip for a post (b-roll, product-in-motion, hook visual, spokesperson/UGC clip, ad), to animate a still image into video, or a vertical Reel/TikTok/Short clip. Reads brand-profile for brand style. Veo’s standout is native synchronized audio in one pass, plus image-to-video and native 9:16 vertical. Teaches the prompt anatomy, audio prompting, the image-to-video pipeline, and the 8-second constraint + extension/stitching. Honest: iterate cheap then finalize, disclose AI video (SynthID watermark), never generate real identifiable people or copyrighted IP. This is the prompt-craft layer — the API/connection and the generate -> upload to WoopSocial Media -> attach flow live in tools/integrations/veo.md; the consuming pack is reels-script’s veo-prompt-pack
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.