Media & documents
10,079 rows, by stacks then stars
103 of these skill files have been read, by 99 distinct authors, and what they tell an agent counted. What Media & documents authors agree on, and what they forbid
oubakiou/skills/skills/dataviz-svg Skill
1★ repoAI agent skills
rishi058/LLM-powered-Video-Editor/videoeditor/.github/skills/remotion-skills Skill
no license1★ repoAgentic AI based VideoEditor. Edits video by using prompts only.
alavten/svg-create Skill
no license1★danielgwilson/luxin Skill
1★Zero-setup creative media for agents. Generate & edit images, generate video & audio, create 3D, with no API key, no OAuth, durable hosted URLs, recoverable jobs, and cost receipts.
stevederico/video-understanding Skill
1★Agent skill that turns any video into full AI understanding — extracts timestamped frames + local-whisper SRT transcript, then the agent correlates visuals and speech into an understanding.md
yzp100911/skillgate-agent/cclaw/data/codex-home/skills/.system/imagegen Skill
1★ reposkillgate-agent - AI多模型网关与智能代理框架, 支持MiniMax/DeepSeek等主流模型, 集成MCP工具调用与技能系统。skillgate-agent - AI multi-model gateway & intelligent agent framework, supporting MiniMax/DeepSeek, MCP tools & skill system。
RanaCM/marpsmith/skills/deck-a11y-audit Skill
1★ repoMarpsmith - agent skills for building Marp decks
purpose1004/dark-tech-report-generator Skill
1★Generate editable dark-tech-style PowerPoint (.pptx) reports from a simple JSON — i18n, themes, generic blocks. Works as a CLI or agent skill.
AzalDaniel/FigForge/skills/figma-to-email-html Skill
1★ repocskwork/superoffice-skills Skill
1★Korean business-document skill (docx/pptx/xlsx/hwpx/pdf) with company branding, deterministic office-gate + OfficeCLI render verification - /superoffice for 팀장·경영자
jeremyknows/prosody-lens Skill
1★Local-first prosody analysis skill for voice memos and speech recordings
Dunteng/watch-video-skill Skill
1★Evidence-first video understanding skill for Codex: yt-dlp, Douyin SSR fallback, local whisper.cpp, keyframes, OCR, and grounded reports.
j0m0k0/jellyfin-skills/skills/organize-jellyfin-media Skill
1★ repoAgent Skills for Jellyfin media libraries, naming conventions, metadata IDs, and library maintenance
raydocs/fusion-deck Skill
1★A Claude Code skill that spends extra models only when the risk earns it. One hard question goes to Claude + GPT + Gemini blind and in parallel; Claude judges, and the panel that actually ran is disclosed. Plus plan / context / review / orchestrate / handoff workflows. Runs on the CLI subscriptions already on your machine.
lucyfengcl-art/video-prep/skills/video-prep Skill
1★ repoClean up raw video clips before editing: cut silence, transcribe subtitles (any language, Mandarin default), normalize speed, stitch in order. Ships as a Claude Code plugin + CLI for Codex.
iamurali/system-design-skill/skills/excalidraw-diagram Skill
1★ repoOpen Agent Skill for PE-grade system design interview prep. Generates 10 artifacts per problem with quality gates, cross-file checks, and a Python validator. Works with Cursor, Codex, Claude Code, Copilot, and Gemini CLI.
jingua1234/docx-from-template Skill
1★Universal Agent Skill for Claude Code, Codex, and Cursor: generate delivery Word/Excel docs by mirroring a template structure
Xerneas216/ProCraft/skills/procraft Skill
1★ repoCraft reliable prompts for everyday tasks, tool agents, and software work.
zhiming33416/top-cs-paper-skills/skills/top-cs-figure Skill
1★ repoEvidence-grounded Codex skills for writing, polishing, reviewing, reviewer responses, and figures for top CS conferences.
iurysza/agent-skills/skills/audio-transcribe Skill
1★ repoShareable skills for clankers
huxlife/handdrawn-wisdom-video/skills/handdrawn-wisdom-video Skill
1★ repoAn open-source Codex skill for creating English hand-drawn wisdom videos from fables, Chinese idioms, historical anecdotes, and the Thirty-Six Stratagems.
Stephen-creater/github-research-podcast/skills/github-research-podcast Skill
1★ repoResearch GitHub repositories and turn verified findings into Chinese podcast episodes with an installable Agent Skill.
zccyes/summarize-learning-videos Skill
1★Turn Bilibili and YouTube learning videos into detailed, timestamped Obsidian study notes with a mandatory quality gate.
madeyexz/annotate-screenshots/skills/annotate-screenshots Skill
1★ reposcreenshots annotation skill for coding agents
phamthanhnghia/remotion-agent-skills/skills/hyperframes-to-remotion 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.
ychampion/morph-public/experiments/morph-animation/plugin-template/skills/morph-animation Skill
1★ repoMorph is the intelligence layer between sales and engineering—turn real product flows into buyer-ready videos, interactive demos, and Story Packs with your coding agent.
Paper and book to visual learning
YIYANG-hakimide/paper-and-book-to-visual-learning Skill
1★Turn papers, books, and reports into visual learning albums, editable PPTs, and interactive bilingual readers.
yonathanarbel/legal-ai-skills/bluebook-review Skill
1★ repoAgent skills and deterministic tools for legal scholarship workflows
k-telux/SciReviewWriter/i18n/ja Skill
1★ repoEvidence-gated Agent Skill for mechanism-first, citation-traceable scientific reviews with LaTeX, rendered-page QA, and multilingual rules.
igapyon/miku-media-proc-skills/skills/miku-media-proc Skill
1★ repoRepository-local Codex skill package for media processing workflows, including video, audio, image, subtitle, metadata, and batch media preparation tasks.
dzivkovi/agent-skills-on-databricks/skills/branded-pptx Skill
1★ repoBring your Claude Code skill unchanged and run it as a governed Databricks job. Publish once to a Unity Catalog volume, reuse from any job, chain skills into a pipeline (markdown in, branded PowerPoint out). No external API key. Runs on Free Edition.
haixinnn05/classcorpus Skill
1★Local-first Agent Skill for citation-aware lecture search, Q&A, flashcards, and study guides.
xiaopixuan/skills-public/skills/drawio-diagram-skill Skill
1★ repoPublic Codex skills, including skill-design-review and drawio-diagram-skill.
SocialYjj/literature-fetch Skill
no license1★按题目/DOI 查找·查阅·正版下载学术文献 PDF 的 Agent Skill (Claude Code / Codex) · Search, read & download academic paper PDFs by title/DOI
nguyenthdat/opencode-starter/skills/docx Skill
1★ repoOpinionated OpenCode configuration with reusable agents, document skills, MCP integrations, custom tooling, and cross-platform workstation bootstrap.
Kiratuu/Video-Wrapper-Skills Skill
no license1★🎬 Enhance interview and podcast videos with stylish visuals using AI-generated effects for a professional touch.
dovudja9209/civitai-gen-skill/civitai-gen Skill
1★ repoGenerate images, video, and audio using Civitai's Workflow API through a dependency-free Node.js agent skill compatible with standard agent runtimes.
khu88/ResearchFigureSkill/skills/research-figure Skill
1★ repoEvidence-locked scientific visual compiler for auditable research figures
cinquewoo/Halliday-SFL-analysis-skill/plugins/halliday-sfl-analysis-skill/skills/halliday-sfl-analyst Skill
no license1★ repoHallidayan SFL analysis for English and Chinese—with grammatical-metaphor diagnostics, congruent alternatives, and page-verified citations.
pptxz/ppt-collaboration-assistant Skill
1★All-in-one cost-aware PPT Skill for Codex and other AI agents
Retro-Diffusion/retro-diffusion-mcp/ai.retrodiffusion/pixel-art MCP server
1★ repoGenerate authentic pixel art - sprites, animations, and tilesets - from any MCP client
superdocsapp/superdocs-plugin/app.superdocs/superdocs MCP server
1★ repoAI document editing for agents: draft, edit, export .docx/PDF. 37 MCP tools; agent self-signup.
WoopSocial/mcp/com.woopsocial/mcp MCP server
no license1★ repoPost to social media (Facebook, Instagram, LinkedIn, Pinterest, YouTube, TikTok, X/Twitter and more)
CSOAI-ORG/voice-audio-mcp/io.github.CSOAI-ORG/voice-audio-mcp MCP server
no license1★ repoVoice Audio MCP server. Tools: text to speech, list voices, transcribe. Built by MEOK AI Labs.
EigenCharlie/pdf-toolkit-mcp/io.github.EigenCharlie/pdf-toolkit-mcp MCP server
1★ repoUnofficial PDF toolkit (merge/split/compress/OCR/convert/watermark/protect/...) via iLoveAPI.
engr-faizanali/text-to-speech-mcp/io.github.Engr-FaizanAli/text-to-speech MCP server
1★ repoOpen-source local Windows text-to-speech through SAPI; no API key or cloud service required.
EmiyaKatuz/crispasr-agent-transcriber/io.github.EmiyaKatuz/crispasr-agent-transcriber MCP server
1★ repoTranscribe and understand local audio/video with CrispASR and local models only.
KitDevUA/video-vision-mcp/io.github.KitDevUA/video-vision-mcp MCP server
1★ repoAnalyze any video (local file or URL) into frames + transcript for Claude Code
MkTurner74/botverse-mcp/io.github.MkTurner74/botverse MCP server
1★ repoTranscode video, convert docs & transcribe audio for AI agents. Free $1 trial, no card.
RayAKaan/OcularAudio-MCP/io.github.RayAKaan/ocular-audio-mcp MCP server
1★ repoMCP server for video transcripts, screenshots, and OCR on YouTube and web videos.
Shan-Zhu/shuck-convert/io.github.Shan-Zhu/shuck-convert MCP server
1★ repoConvert between document formats — DOCX/PDF to Markdown, Markdown to DOCX.
SocialAPIsHub/mcp-server/io.github.SocialAPIsHub/social-media-api MCP server
1★ repoUnified social media API for AI agents. Access Facebook, Instagram, TikTok, and more.
Xvvln/pdf-reader-mcp/io.github.Xvvln/pdf-reader-mcp MCP server
1★ repoMCP server for extracting text, images, tables, links, annotations, and metadata from PDF files.
alichherawalla/video-overlay-kit/io.github.alichherawalla/video-overlay-kit MCP server
1★ repoAnimated b-roll overlays for short-form video. Paste a script, get an mp4. Free, MIT, local.
avotsai/avots-mcp/io.github.avotsai/avots-mcp MCP server
1★ repoImage, video, audio, face-swap, talking avatars and chat across 300+ AI models, one balance.
ayo-nci/bulkrender-mcp/io.github.ayo-nci/bulkrender MCP server
no license1★ repoGenerate DOCX and PDF documents from AI assistants using BulkRender templates.
beepboop2025/pdf-suite-mcp/io.github.beepboop2025/pdf-suite-mcp MCP server
1★ repo37 tools to read, create, merge, split, watermark, fill, redact & search PDFs. Local, no API key.
beepboop2025/pdf-toolkit-mcp/io.github.beepboop2025/pdf-toolkit-mcp MCP server
1★ repo37 tools to read, create, merge, split, watermark, fill, redact & search PDFs. Local, no API key.
compassalessandrolorenz/Figma-Context-MCP-AIR/io.github.compassalessandrolorenz/Figma-Context-MCP-AIR MCP server
1★ repoFigma MCP server for AI agents. 9 tools: design context, variables, screenshots, and FigJam.
conorbronsdon/podcastindex-mcp/io.github.conorbronsdon/podcastindex-mcp MCP server
1★ repoSearch the Podcast Index: podcasts, episodes, person appearances, trending, feed health.