Media Claude Skills
3 032 media skills from 496 authors. They create and process images, video and sound. Half of them fit into 1 962 tokens or less — that is what one costs your context window when the agent loads it. 771 ship runnable scripts rather than instructions alone. 30 of them cannot work without an MCP server, most often rube. We also found 347 copies of these same skills sitting in other people's repositories — counted once here, not 347 times.
3 032 unique 496 authors 13 updated this month 173 from vendors
Assemble a song-driven music-video ad from a config — a generated sung track carries the whole narration across N tableaux (one keyframe -> one i2v clip per lyric beat) with NO separate voiceover, captions synced to the song's OWN word timings (script-window, never Whisper) and the hook word landing on the chorus drop, closed on a PIL brand end card. This is the FREE deterministic assembly stage (clip cut-to-timeline + captions + end card + FFmpeg composite); the song, keyframes, and clips come from create-music-elevenlabs / create-image-fal / create-video-fal. Use for the song-driven-music-video format.
Assemble a split-screen creator ad from a config — a two-zone vertical composite where a supplied AI-creator lip-sync take fills the BOTTOM ~48% while real 16:9 product/demo clips run uncropped in the TOP ~52%, each top clip contain-fit with a darkened blurred cover-scale fill of the same clip (never black bars), a 3px brand-color divider between the zones, the creator slice cover-fit per the per-scene VO timing, scenes hard-concatenated with the body audio being the concatenated creator VO slices, an end card held on the last sharp frame ~3s, then the ASSEMBLED cut transcribed with local Whisper (not the raw VO — concat drops inter-scene silence) and word-level captions burned in the chosen style. This is the FREE deterministic assembly + caption stage (two-zone composite + blurred fill + divider + hard-concat + end card + captions); the VO comes from create-vo-elevenlabs, the anchor from create-image-gpt-image-fal, and the whole-VO lip-sync from a paid VEED Fabric 1.0 take (a no-atom upstream input). Use for the split-screen-creator format.
the UGC fix-loop toolkit — surgically re-render a bad window/beat of a single-take UGC master (stitch_replacement.py, pure FFmpeg) and GPT cross-model review a Seedance prompt before render (vet_seedance_prompt.py, routed through the openai-proxy). Fetch it into a one-shot UGC recipe so both scripts resolve on any machine and the vet call bills the Ads agent.
QC gate for a generated static ad image — verify the file opens, matches the requested dimensions, shows the correct product/subject (right shape, colour, label, logo), and has no garbled text or severe artifacts. Records pass/fail/needs-human in verification.md. Used as the final check in the static ad remix flow before shipping.
Assemble an expert/educator motion-graphic LISTICLE video ad from a config — a spoken authoritative voiceover carries a numbered listicle while N web-animated hyperframe beats (HTML plus the Web Animations API, one branded design system of alternating tiles, big hero numerals, and glass-pill callouts) are rendered frame-by-frame via Playwright and anchored to the VO's word-level timestamps, periodic color-graded B-roll windows give visual breath, and captions burn ONLY inside those B-roll windows (2-word chunks, ASS Format header carrying a Name field so none drop) with the VO mixed under a low music bed. This is the FREE deterministic assembly stage (Playwright beat render plus ffmpeg concat plus window-masked caption burn plus VO-and-music mix plus final composite) — the VO, the music bed, and the stock B-roll come from create-vo-elevenlabs, create-music-elevenlabs, and media-proxy. Use for the vo-anchored-motion-listicle format.
Assemble a short-form 'vignette' ad from clean product cutouts composited over a kinetic background video — birefnet cutout, then a cold-open text card + product carousel + annotated specimen-sheet end card, plus loudnorm + separate-pass music mux. FREE assembly (PIL + rsvg + FFmpeg); the recipe supplies the config and gates the paid BG/cutout/music calls to their own capabilities. Use for the vignette format.
Assemble a stop-motion hand-swatch-cycle product-demo ad from a config — a sequence of still PLATES (one hand swiping a single-barrel cosmetic across a cream skin-patch, the barrel + swatch changing per plate while the hand, background, crop, and lighting stay locked) is PNG→mp4 loop-encoded at each plate's own stop-motion hold (fast motion frames 150–250ms, per-shade ~380ms, hero beats 1100–1800ms), concat-demuxed with HARD cuts into a silent master, closed on a Playwright HTML-rendered branded end card (serif tagline + sans subtitle + real logo SVG over a hero BG, never AI-rendered text), and muxed with a pre-sourced music track playing under the end card with a fade tail (no VO). This is the FREE deterministic assembly stage (loop-encode + concat-demux + end-card render + music mux); the master-anchor plate, shade plates, and end-card BG come from create-image-gpt-image-fal and the track from create-music-elevenlabs. Use for the stopmotion-hand-swatch-cycle format.
Render a designed 'value prop' video from a config — 3-5 noun-phrase benefit claims (<=4 words each) revealed sequentially over per-SKU product visuals, one crisp editorial frame per claim (hook sticker -> N claim beats -> brand end card). Deterministic PIL/HTML beat renderer frame-stepped via Playwright and encoded with FFmpeg, sound-off legible, hard cuts, uniform pacing. FREE (no paid calls); music is added separately (create-music-elevenlabs). Use for the value-prop format.
Generate a single 4-15s vertical video clip with ByteDance Seedance 2.0 reference-to-video via fal.ai. Multi-image reference (avatar + product + setting), native lip-synced VO + ambient audio (generate-audio on by default), internal multi-cut handling within one render. Routes through the GooseWorks FAL proxy (bills the Ads agent). The default clip atom for AI-creator UGC ads built on the NB2 + Seedance architecture. Validated on beauty-by-earth/video-01.
Recreate a static graphic ad (Pinterest pin, IG/FB feed image, poster) from a reference image, swapping in a new brand's product and new copy while keeping the reference's layout, composition, and visual energy. ALWAYS generated with GPT Image 2 in edit-the-reference mode (fal-ai/gpt-image-1/edit-image, a billed FAL generation); the HTML/goose-graphics overlay is only an optional text-finishing step, never the generator. The static-graphics counterpart to the video remix-ad skill; this is what the app calls when a user picks a reference ad and wants it for their own product.
Mandatory pre-publish review gate for a UGC video render. Transcribes the finished render's AUDIO with Whisper and word-diffs it against the approved spoken script, then gates set_final_render — blocking a render whose generated audio mis-voices a word (e.g. the approved "human-vetted" spoken as "human witted"), drops an approved phrase, or comes back silent. Runnable, gating counterpart to content-goose's review-transcript-integrity atom. Every ugc-video-formats recipe runs this after render and BEFORE set_final_render.
Render pixel-accurate Apple Notes (iPhone, light mode) screenshot mockups from a JSON note spec. Outputs HTML + PNG at the iPhone 16/15 Pro native 1180×2556. Supports paragraphs, images, checklists, dividers, autocorrect underline, smart quotes, and an optional iOS keyboard chrome overlay used by the parent video-ad molecule.
Render pixel-accurate ChatGPT mobile (iOS) screen mockups in light mode from a thread JSON. Supports user text bubbles, user image attachments, assistant markdown prose, citation chips, the OpenAI spiral logo, the Apps-SDK GPT chip in the composer, and three header styles (model-tag, plain title, "Get Plus"). Fixed 9:16 viewport. Outputs HTML + PNG.
Canonical short-form-ad audio mix in one FFmpeg pass. VO loudnorm + 3.0× per-clip + 2.0× mix, music 0.13 base + apad+afade, sidechain compress 20:1 @ 0.01, climax line +20%, optional video-to-music duration sync. Replaces the reactive multi-round tuning that cost v03 6+ passes.
Render pixel-accurate iMessage screenshot mockups (DM or group) from a thread JSON. Supports minimal, with-keyboard, and full iPhone 15 Pro frame variants. Outputs HTML + PNG.
Render a static iOS QWERTY keyboard as inline HTML+CSS sized for the 750-wide 9:16 stage. Includes the 3-suggestion bar, alpha keys, shift/backspace, 123/emoji/space/return row, and the bottom globe+mic strip. No animation logic — slide up/down is the molecule's job (CSS transform on the .keyboard root).
stitch video segments with ffmpeg concat, xfade, overlay, audio mux, and export settings.
Watch a rendered video (whole file or specific ranges) at a chosen fidelity and emit a timestamp-keyed observation report. Observation only — no edits, no verdicts.
> Analyze a company's published content to extract their brand voice, writing style, and tone guidelines. Reads 10-20 of their best content pieces and produces a brand voice profile covering tone, vocabulary level, sentence structure, formatting patterns, CTAs, and target persona. Useful before writing outreach, content, or campaigns that should match a client's existing voice.
> Generate a personal voice guide for X (Twitter) and/or LinkedIn by scanning a user's past posts and iteratively refining with sample-and-feedback loops. Produces a structured markdown voice guide that sibling skills (create-x-content, create-linkedin-content) consume to draft in-voice posts. Different from brand-voice-extractor, which analyses company blogs/landing pages — this skill is for personal social voice.
Maintain a brand kit — the canonical brand context an ad or content pipeline reads (positioning, audience, voice, standing instructions, brand-type, value-props, colors), plus manage the product list and attach product photos. Use when someone says "update my brand kit", "set my brand voice/audience", "add a product to my brand", or hands you a folder of product shots to attach. Platform-agnostic: it teaches the field model, partial-update/clear semantics, override behavior, caps and validation, and the hero-image and product-matching rules — independent of any specific backend.
> Draft voice-tuned LinkedIn post variants from a free-form brief. Reads a personal voice guide (generated via generate-voice-guide), produces 2–5 variants with distinct framings, applies LinkedIn-specific defaults (arrow bullets, "why this matters" beat, 150–500 words), and self-checks against the voice guide's banned phrases before returning.
> Draft voice-tuned X (Twitter) post variants from a free-form brief. Reads a personal voice guide (generated via generate-voice-guide), produces 2–5 variants with distinct framings (simple-howto, problem-first, hype, mechanism-breakdown, etc.), and self-checks against the voice guide's banned phrases before returning.
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
Create LinkedIn carousel posts as high-quality PNG images. Design informational multi-slide posts like "5 AI GTM workflows" with consistent styling, then automatically screenshot each slide at LinkedIn's optimal 1080x1080px format.
Create FigJam/Miro-style workflow diagrams as high-quality PNG images from plain-text workflow descriptions. Renders beautiful HTML diagrams with connected nodes, arrows, and labels, then screenshots them for sharing.
Best practices for Remotion - Video creation in React
Create polished terminal GIF recordings using VHS (Video Hardware Software) by Charmbracelet. Use when asked to create terminal demos, CLI gifs, command-line recordings, or animated terminal screenshots for documentation, READMEs, or marketing.
> Creates a new graphics format spec (custom canvas dimensions + content rules) and publishes it to the Gooseworks library so any agent can render against it. Use when the existing community formats (carousel, story, infographic, slides, poster, chart, tweet, plus community additions) don't fit the user's canvas — e.g., LinkedIn banner 1584×396, story cover 1080×1920, event flyer 8.5×11in. Mirrors goose-graphics-create-style but for formats.
> End-to-end skill that turns a single reference image into a published Gooseworks style — analyzes the image, drafts the slim style spec, renders a hero example plus 2-3 additional formats via Playwright, writes the `gooseworks-style.json` manifest, and publishes via `npx gooseworks styles publish` so other agents can discover it. Mirrors goose-graphics-create-format but for styles.
Generates Instagram Reels where product image cuts are synced to audio beats. Accepts audio as a local file, URL, or search query. Uses librosa for beat detection, FFmpeg Ken Burns for scene animation, and Pillow for text overlays. No AI video generation — fully free, fast, and scalable.
Generates Instagram-ready product reels from any e-commerce product page URL. Scrapes product images, classifies by type, generates AI-animated clips via Higgsfield API, creates text overlays with style presets, and composes a 15-20 second reel with music. Supports model-based and product-only reels.
Creates talking head videos from any source material (docs, changelogs, blog posts, notes, transcripts). Produces multi-scene videos with avatar narration over screenshots/images using HeyGen v2 API. Supports Quick Shot and Full Producer modes.
Repurposes long-form video (podcasts, interviews, talks) into short-form vertical clips for Instagram Reels, TikTok, and YouTube Shorts. Handles transcription, moment selection, clip extraction, speaker-tracked reframing (16:9 to 9:16), and animated captions.
Takes an existing screen recording or demo video and adds professional zoom/pan effects synchronized to the narration. Uses transcript-driven zoom targeting and Remotion for rendering. Optionally replaces audio with a soundtrack.
AI video conversations - create real-time video calls with AI personas
Analyze images with AI - extract text, describe content, detect objects
Fetch YouTube transcripts via APIFY API. Works from cloud IPs (Hetzner, AWS, etc.) by bypassing YouTube's bot detection. Free tier includes $5/month credits (~714 videos). No credit card required.
Fetch and read transcripts from YouTube videos. Use when you need to summarize a video, answer questions about its content, or extract information from it.
Use this skill for Node.js backend AI via @cloudbase/node-sdk (>=3.16.0) — cloud functions, CloudRun, Express, Koa, NestJS, serverless APIs, scheduled jobs, LLM proxies. Only SDK supporting image generation (ai.createImageModel + generateImage). Text models via ai.createModel with groups cloudbase, hunyuan-exp, or custom-*. Model IDs (deepseek-v4-flash, deepseek-v3.2, hunyuan-2.0-instruct-20251111, glm-5, kimi-k2.6) go in the model field of generateText/streamText. MUST run two-step preflight before code — see body. Keywords: backend, 云函数, 云托管, serverless, LLM proxy, agent orchestration, generateText, streamText, generateImage, createModel, hunyuan-image, Token Credits, TokenHub, Hunyuan, DeepSeek, GLM, Kimi, MiniMax. NOT for browser/Web (use ai-model-web) or Mini Program (use ai-model-wechat).
Use this skill when a browser/Web app (React, Vue, Angular, Next, Nuxt, static sites, SPAs, dashboards, AI chat UI) needs AI models via @cloudbase/js-sdk. Default routing for page/页面/Web/前端/frontend/网页/H5 AI — call directly from browser, do NOT propose a Node.js proxy. Covers generateText and streamText. Models via ai.createModel with groups cloudbase, hunyuan-exp, or custom-*. Model IDs (deepseek-v4-flash, deepseek-v3.2, hunyuan-2.0-instruct-20251111, glm-5, kimi-k2.6) go in the model field. MUST run two-step preflight before code — see body. Keywords: 页面, Web, 前端, React, Vue, Next, Nuxt, SPA, AI chat UI, generateText, streamText, createModel, hunyuan-exp, Token Credits, TokenHub, Hunyuan, DeepSeek, GLM, Kimi, MiniMax. NOT for Node.js backend (use ai-model-nodejs), Mini Program (use ai-model-wechat), or image generation (Node SDK only).
Use this skill for WeChat Mini Program AI via wx.cloud.extend.AI (小程序, 企业微信小程序, wx.cloud apps). Features generateText and streamText with callbacks (onText, onEvent, onFinish). Models via wx.cloud.extend.AI.createModel with groups hunyuan-exp (小程序成长计划), cloudbase (main managed), or custom-*. Model IDs (deepseek-v4-flash, deepseek-v3.2, hunyuan-2.0-instruct-20251111, glm-5, kimi-k2.6) go in the data wrapper model field. API differs from JS/Node SDK — streamText needs data wrapper, generateText returns raw response. MUST run two-step preflight before code — see body. Keywords: Mini Program AI, wx.cloud.extend.AI, 小程序成长计划, ai_miniprogram_inspire_plan, Token Credits 资源包, generateText, streamText, createModel, hunyuan-exp, TokenHub, Hunyuan, DeepSeek, GLM, Kimi, MiniMax. NOT for browser/Web (use ai-model-web), Node.js backend (use ai-model-nodejs), or image generation (use ai-model-nodejs).
Dub a video into another language and generate subtitles using the default Together + Cartesia stack. Trigger when the user wants to translate / dub / voice-over a video file, or generate subtitles for it. Handles `.mp4` / `.mkv` / `.webm`. Installs as the `violin` CLI (and `violin-api` for the FastAPI server) via `uv tool install`. For alternative models (OpenAI / ElevenLabs) or custom configs, point the user to the repo: https://github.com/shang-zhu/violin.
| Transforms vague video ideas into detailed scene-by-scene plans (scenes.md). Conducts research, asks clarifying questions about audience/scope/focus, and outputs comprehensive scene specifications ready for implementation with ManimCE or ManimGL. Use this BEFORE writing any Manim code. This skill plans the video; use manimce-best-practices or manimgl-best-practices for implementation.
| Best practices for ManimGL (Grant Sanderson's 3Blue1Brown version) - OpenGL-based animation engine with interactive development. Covers InteractiveScene, Tex with t2c, camera frame control, interactive mode (-se flag), 3D rendering, and checkpoint_paste() workflow. NOT for Manim Community Edition (which uses `manim` imports and `manim` CLI).
Best practices for Remotion - Video creation in React
Use when the user gives a topic and wants an automated video podcast created, or asks to learn visual design patterns from a reference video/image. Produces 4K video via research → script → TTS → Remotion → MP4 + BGM.
> Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage", a narrated explainer or short ad built from AI-generated collage posters, a scrapbook-style tribute, or wants to turn a topic / product / person into a punchy narrated collage video — even if they don't say the word "Vox". Also use when reproducing Stav Zilber / rom1trs / Higgsfield-style collage ad workflows. photo of a person/product anchored into the collage (C-roll mode). explainer", "make a collage ad", "turn this topic into a collage video", "turn my photo/this product shot into a collage video".