Video & audio
3,623 rows, by stacks then stars
782 of these skill files have been read, by 619 distinct authors, and what they tell an agent counted. What Video & audio authors agree on, and what they forbid
heygen-com/skills/heygen-translate Skill
392★ repoHeyGen AI agent skills — avatar creation and video production via the v3 Video Agent pipeline
stevenflanagan1/social-ai-team/skills/caption-writer Skill
no license184★ repoClaude Code skills for social media — a complete AI social team for SMBs. Brand setup, content calendar, captions, creative, and performance review.
Karanjot786/agent-skills-cli/.agent/skills/remotion-best-practices Skill
177★ repoUniversal CLI for Agent Skills. Access 200,000+ skills from SkillsMP and sync them to Cursor, Claude Code, GitHub Copilot, OpenAI Codex, and Antigravity.
smixs/visual-skills/video Skill
165★ repoAI film director skills for Claude agents: cinematic dramaturgy (Murch, blocking, montage) + exact prompt syntax for Seedance 2.5, Kling 3.0 Turbo/Omni, Veo 3.1, Nano Banana 2, GPT Image 2. Claude Code, Cursor, Windsurf, OpenCode
Cassette-Editor/oh-my-cassette/hermes/skills/cassette-video-edit Skill
140★ repo你的随身 AI 剪辑搭档 | Pocket AI co-editor for video montage — AI video editing plugin & MCP server for Claude Code, Codex, Hermes & OpenCode
genli-ai/market-research-skills/skills/local-vault Skill
59★ repoTurn Claude into a disciplined research analyst — verify facts against primary sources, brief any topic, draft flagship reports. Standalone or chained; runs across LLM terminals. | 把 Claude 变成讲纪律的研究分析师:核实事实、主题简报、旗舰研报,引用一手来源、绝不造数;可单用或串联,跨 LLM 终端。
avenoxai/avenoxskills/skills/avenox-roughcut Skill
35★ repoProduction agent skills for Claude Code, Cursor, and any SKILL.md harness — Codex fleets, video pipeline, monorepo review bundles, multi-chain explorer.
VoDaiLocz/kilo-kit-mcp/skills/ai-media/ai-multimodal Skill
24★ repoAn MCP server for safer coding agents: skill routing, C4 workflow gates, memory checks, and verification before completion.
social-media-skills/skills/skills/ai-music-and-sound Skill
22★ repo106 social media skills for AI agents - strategy, writing, video, design, platform growth, publishing, and analytics. Works with Claude, Cursor, OpenClaw, Hermes & 40+ agents.
hogan-tech/brand-loom/skills/caption Skill
22★ repoOpen-source marketing skills that run on any model — with a hosted brand-memory engine. No coding agent required.
chanjing-ai/chan-skills/skills/chanjing-avatar Skill
no license19★ repo蝉系openclaw 技能库,聚焦电商内容创作,提供实用的 AI 工具及技能包
PrunaAI/pruna-skills/skills/audio/music-2.5 Skill
17★ repoAgent skills and plugins to give your agents access to Pruna API and generation workflows.
jackspace/ClaudeSkillz/skills/ai-multimodal_mrgoonie Skill
16★ repoClaudeSkillz: For when you need skills, but lazier
kunitoki/sonic-skills/skills/audio-artifacts-debug Skill
15★ repoModular Markdown-based audio skills for AI agents and developers, covering signal processing, synthesis, effects, analysis, and spatial audio.
GoldLegendW80/llm-video-maker/skills/make-video Skill
15★ repoTurn one prompt into a finished MP4. An AI agent skill for Claude Code, Cursor, Codex & Windsurf that generates TikTok/Reels/Shorts, YouTube intros, startup hero loops & data explainers — with AI voiceover, captions, music & real assets. Deterministic HTML/GSAP render. Prompt-driven, Remotion-style.
WhiteTowerAI/cut-as-code/skills/video-add-content-cards Skill
10★ repoOpen-source agentic video editing skills — an AI-powered alternative to Opus Clip and CapCut
Phantomlau3674/ai-film-director-workbench/skills/ai-video-prompt-generator Skill
9★ repoAI电影导演工作台和提示词生成系统:素材生产、参考图职责、导演级长提示词与可验证生产流程
Lenny Rachitsky Podcast Transcripts MCP Server
la-rebelion/hapimcp/ai.com.mcp/lenny-rachitsky-podcast MCP server
9★ repoMCP server for structured access to Lenny Rachitsky podcast transcripts. For content creators.
apresmoi/jianglens/.codex/skills/jiang-agent-transcript-pass Skill
no license7★ repoAgentic Organization Research Project - Jiang Lens is an independent research and reading project built from Jiang Xueqin's lectures, interviews, and writing.
Openclaw Product Branding Skill
X-RayLuan/awesome-ceo-stack/ceo-skill/Openclaw-Product-Branding-Skill Skill
no license7★ repoAn awesome, curated stack of Claude / OpenClaw agent skills for founders & CEOs — strategy, knowledge base, decks, K-12 coaching, and a full local AI promo-video pipeline. Works with Claude Code, Codex & OpenClaw.
chenyuxiaojin/video-agent-skills/video-agent-editor Skill
7★ repoMulti-agent Claude Code skills that turn a topic into a DaVinci/CapCut-ready video timeline — research to publish.
Mintii-Labs/ozor-skills/skills/ozor-changelog-to-video Skill
6★ repoParthGanatra/agent-skills/youtube-summary Skill
5★ repoClaude Code agent skills. Includes youtube-summary: a YouTube video summarizer that writes structured notes (TL;DR, takeaways, chapters) with optional slide extraction.
smeseik-ai/arabic-content-studio/skills/arabic-content-producer Skill
no license5★ repoProfessional Claude Skills for Arabic content teams — production, culture, SEO, brand voice, logo design a community initiative by Viral
huhx0015/AndroidBooster/claude/skills/androidbooster-audio Skill
no license5★ repoAndroid Booster: An Android starter project that provides a modular foundation for building production-ready apps. It offers multiple architecture patterns (MVI, MVVM, MVP, VIPER) with shared base classes, so you can choose the approach that fits each feature.
benelser/docent/packages/agent/skills/docent-doctor Skill
5★ repoPoint it at anything — a codebase, a PR, an essay, a paper, a URL — and get back a narrated, animated film that argues for what it explains. A closed grammar of explanation rendered by a coding agent, judged before it ships.
BusyBee3333/animated-explainer-skills/skills/explainer-studio Skill
4★ repoBuild Kurzgesagt-quality animated explainer videos as one self-contained HTML file — GSAP choreography patterns, YouTube-retention method, overlap auditor, ElevenLabs VO pipeline. Claude Code skills + standalone tools. MIT.
mike007jd/game-superpowers/publish/clawhub/gsp-audio-feedback-audit Skill
4★ repoSkills-first game development superpowers for Claude Code and Codex: build, audit, polish, and productionize game projects with reusable Agent Skills.
prvthmpcypher/skills-gamedev/skills/game-audio-engineer Skill
3★ repo22 Claude skills for game developers. Unity, Unreal, Godot, Roblox, level design, narrative design, and shader authoring
chenyuxiaojin/cyxj-remotion-starter/.claude/skills/cyxj-remotion-overlay Skill
3★ repo用 Claude Code 指挥 Remotion 出视频的工作台脚手架:三层架构 + hooks 守规矩 + skills 编排流程 | by 陈与小金
handsomeng/Hskill-chatcut/skills/publish-video-three-platforms Skill
3★ repoReusable Agent Skills for ChatCut talking-head editing and AI-driven publishing to Xiaohongshu, Douyin, and WeChat Channels
m-binimran/creator-pack/skills/caption-hashtags Skill
3★ repoClaude Code pack for Instagram & Facebook content creators: FTC/Meta disclosure, copyright, brand-safety & no-fabricated-stats guardrails + skills for Reels/carousels/Stories/captions/repurposing/sponsorships, loops & review agents. Not legal advice.
renalpelvisdeinocheirus70/ozor-skills/skills/ozor-changelog-to-video Skill
2★ repoBuild Ozor AI video prompts and skills for product launches, ads, explainers, and more
Daftai extracting video subtitles
daftAI2026/daftAI-skills/skills/daftai-extracting-video-subtitles Skill
no license2★ repocasatwy/deyo-skill/plugins/deyo/skills/deyo Skill
no license2★ repo可用于 AI Agent 的 deyo skill,用于小宇宙、B站、小红书、抖音、Youtube的视频文案转写。
ltppp/douyin-ingest/skills/douyin-script-rewriter Skill
2★ repoDouyin/抖音 agent skills for Top-N viral video collection, speech-to-text transcripts, short-video script rewriting, and Word delivery.
RightBlogger/bloggingskills/skills/article Skill
2★ repoAgent skills that write blog content that ranks and doesn't read like AI.
Speech AI - Pronunciation, STT & TTS
fasuizu-br/speech-ai-examples/io.github.fasuizu-br/speech-ai MCP server
2★ repoPronunciation scoring, speech-to-text, and text-to-speech for language learning
PiotrLason/video-to-code-skill/skills/setup-video-to-code-skill Skill
1★ repoInputs the content of any video into Claude Code prompt / context window as a multimodal bundle of voice transcription and data summary, time synced with keyframes - screenshots of key moments from the video so it can be used for all further requests related to that content.
bob5-tensorslab/skills/skills/tl-video Skill
no license1★ repoTensorLab Skills are AI task definitions for Claude Code, focusing on multimedia generation and processing using TensorsLab's AI models. It provides comprehensive capabilities including text-to-image and image-to-image generation, advanced image editing (avatar generation, watermark removal, object erasure, face replacement), as well as text-to-vid
ecliptic-ai/skills/plugins/ecliptic/skills/beat-sync-video-editing Skill
no license1★ repoAI-augmented video splicing framework for Agents
Gaoqian xuejie podcast outline
carpo9984/GQXJ/skills/gaoqian-xuejie-podcast-outline Skill
no license1★ repo搞钱学姐团队播客工作流:大纲、逐字稿剪辑、标题、宣发、ShowNote 与视觉风格 Skills
scumunna/programmatic-skills/skills/amazon-dsp-account-structure Skill
1★ repoAgent skills for programmatic trading, analytics, and account operations. DV360 first, multi-DSP and multi-runtime (Claude Code and Codex).
ZeusSheen/ppro-agent-bridge Skill
no license1★Transcript-driven, closed-loop AI editing bridge for Adobe Premiere Pro, built on official UXP APIs
Harduex/agentic-notebook/skills/agentic-notebook Skill
1★ repoSource-grounded, NotebookLM-style research notebook over any local folder of documents — grounded Q&A with verifiable citations, plus study guides, briefing docs, mind maps, podcast scripts and more.
gabros20/ai-skill/.agents/skills/remotion-best-practices Skill
1★ repoAgent skill for AI Systems — build model-powered behavior: agents, retrieval, evals, and guardrails
portel-dev/skills/skills/vertical-video-design Skill
no license1★ repoOfficial skills repository for Portel Photon
kiakun-collab/kiakun-skills/skills/bilibili-video-summary Skill
no license1★ repoKiakun 的 AI Agent Skills 集合(Claude Code / OpenClaw / 通用 SKILL.md):HTML→可编辑 PPTX、图片型 PPT 重构、GPT Image 2 出图、小红书/B站自动化、文件夹向量知识库、游戏 UI 与玩家互动设计等 10+ 技能。
lunchpaillola/pipa-skills/skills/pipa-audio-brief Skill
1★ repoOperational skills for the agents people already use.
Xuepoo/agent-lx-music-skills/audio-analysis Skill
no license1★ repoModular AI Agent Skills for agent-lx-music (alx) CLI, compatible with Hermes, OpenClaw, Codex, and npx skills
celeryhq/simplified-ai/skills/content-repurposer Skill
1★ repothiagoxikota/ai-collective-content-lab/.claude/skills/criar-video Skill
1★ repoWhite-label content tooling for The AI Collective chapters. Instagram posts, carousels and reels in the brand identity, from Claude Code. Posts need no API key (local render). Built by the Florianópolis chapter.
johnsonbuilds/awesome-hermes-skills/creative/wavespeed Skill
no license1★ repoCommunity-curated Hermes Agent skills, workflows, and reusable task automation recipes.
puntorigen/avatar-skills/audio-theater Skill
1★ repoCloud-based agent skills for creating AI avatar talking-head videos and short-form reels (skills.sh format)
phamthanhnghia/remotion-agent-skills/skills/remotion-animation Skill
no license1★ repoProgrammatic video creation agent skills suite for Remotion, modeled on HyperFrames architecture. Build explainers, product launches, motion graphics, captions, and data viz with AI.
sakydev/claude/skills/ffmpeg Skill
no license0★ repoClaude skills, scripts and configs for everyday use
oh-summy/skills/skills/agnes-generate-video Skill
0★ repoCross-agent AI skills for Claude, Codex, OpenCode, Kimi Code, and more. Install all at once or pick only what you need.
grooverLab/stash/skills/video-backend Skill
0★ repoPer-project skill manager for Claude Code. Organize hundreds of skills into domain profiles, load only what each session needs. Stops context bloat. Zero-dep bash TUI.
geopti/gemini-api-claude-skills/skills/gemini-api-guides Skill
0★ repoClaude skills from the Google's Gemini API Docs
craft-studio-marketplace/skills/skills/markitdown Skill
0★ repo