Media & documents
10,079 rows from 2,211 repositories
File formats a browser will not simply render for you.
- PDF & office files3,211
- Images & graphics1,136
- Video & audio3,623
- Slides & presentations1,563
- Diagrams & charts744
What Media & documents skills agree on
103 skill files read, by 99 of the 124 authors on this shelf whose files we hold, 2026-09-06
Counted by distinct author, so one author publishing three of these counts once. Where a claim sits in fewer files than authors, that is said: a claim held by forty authors across three files is one file people copied, not forty people who agreed. Near-identical wordings are grouped and the other wordings are shown, so the grouping is yours to check.
What they tell the agent to do
- Define three to five content pillars7 of 99 in 5 filesalso worded as Build content around three to five pillars; Define three to five content pillars before scheduling
- Tag every finding as verified, medium, or assumed5 of 99 in 3 filesalso worded as Tag every finding as verified, medium, or assumed; Tag findings as verified, medium, or assumed
- Respond to comments within one hour5 of 99also worded as Reply to every comment within one hour; Respond to comments within four hours
- Adapt content format to each platform5 of 99also worded as Adapt content format to each platform's norms; Adapt format and tone to each platform
- Choose platforms where the audience already spends time4 of 99 in 2 files
- Cap promotional content at ten percent4 of 99 in 2 files
- Answer product questions within two hours4 of 99 in 2 files
- Acknowledge complaints publicly, resolve them privately4 of 99 in 2 files
- Batch-create posts to keep cadence consistent4 of 99 in 2 filesalso worded as Batch-create posts weekly to maintain cadence
- Fan out across free media sources in one query3 of 99 in 1 file
- Use Pexels or Pixabay for modern short clips3 of 99 in 1 file
- Extract historical shots from archival films3 of 99 in 1 file
- Clip the timestamped moment with ffmpeg3 of 99 in 1 file
- Cut archival films into shots with PySceneDetect3 of 99 in 1 file
- Pass --type gif to reach GIF sources3 of 99 in 1 file
What they tell it not to do
- Never copy-paste identical text across platforms6 of 99also worded as Don't post identical content on every platform; Never post identical content across all platforms
- Never feed trolls4 of 99 in 2 files
- 'Like if you agree' engagement bait4 of 99 in 2 filesalso worded as Using 'like if you agree' engagement bait
- Self-promotion in industry discussions4 of 99 in 2 filesalso worded as Self-promoting in industry discussions
- Do not publish without explicit user approval4 of 99 in 2 filesalso worded as Never auto-post or publish without approval
- Don't use this for generated media3 of 99 in 1 file
- Don't trust audio-judge for subjective qualities3 of 99 in 1 file
- Don't build the media router yet3 of 99 in 1 file
- Never request, print, or store credentials or tokens3 of 99 in 1 file
- Don't exceed two hashtags per tweet3 of 99also worded as do not exceed five LinkedIn hashtags
What they expect to be installed
- ffmpeg6 of 99 in 4 files
- curl4 of 99
- Buffer4 of 99
- WebSearch4 of 99
- Twitter/X3 of 99
- LinkedIn3 of 99
- webmedia.py3 of 99 in 1 file
- Twelve Labs Marengo3 of 99 in 1 file
- PySceneDetect3 of 99 in 1 file
- freesound-fetch.py3 of 99 in 1 file
What they ask it to produce
- Weekly content calendar8 of 99also worded as content calendar; Weekly content calendars
- Platform-specific growth plan4 of 99 in 2 files
- Community management plan with response framework4 of 99 in 2 files
- Four-week content calendar with topics and times4 of 99 in 2 filesalso worded as Four-week content calendar
- Audit with prioritized actions4 of 99 in 2 filesalso worded as Social media audit with prioritized actions
- Normalized JSON result list3 of 99 in 1 file
- Downloaded top-K media files3 of 99 in 1 file
- Attribution.json sidecar3 of 99 in 1 file
When Media & documents authors say to reach for one
The situations these authors wrote into their own files, counted out of the same 99 authors, with the skills that name each one
- User asks for a social media post11 of 99
- Social media posts
- Social media strategy
- Social media monitor
- and 1 more on this shelf
- Engagement rate below platform average5 of 99 in 3 files
- Social media manager
- and 5 more on this shelf
- User asks to add or upload an image5 of 99
- User asks for a LinkedIn post or thread5 of 99
- All content is promotional4 of 99 in 2 files
- Social media manager
- and 5 more on this shelf
- User wants social strategy, calendar, or audit4 of 99 in 2 files
- Social media manager
- and 5 more on this shelf
- Posting frequency below three per week4 of 99 in 2 files
- Social media manager
- and 5 more on this shelf
- Same format every post4 of 99 in 2 files
- Social media manager
- and 5 more on this shelf
How Media & documents skills are built
9,126 skill directories by 1,812 authors, read from their repositories’ own file trees 2026-08-05
The middle bundle among those shipping files is 4 files, 27.8 KB beside SKILL.md
Counted by distinct author, same as above, so one author publishing forty template copies counts once. SKILL.md itself is not counted as a file, so a single-file skill is one where that file is the whole skill.
The shape
- SKILL.md is the whole skill406 of 1,812 authors, 3,172 of 9,126 skills
- files ship beside it1,406 of 1,812 authors, 5,954 of 9,126 skills
- executable scripts ship inside916 of 1,812 authors, 3,025 of 9,126 skills
The folders they converge on
- references/897 of 1,812 authors, 2,672 of 9,126 skills
- scripts/807 of 1,812 authors, 2,646 of 9,126 skills
- assets/291 of 1,812 authors, 691 of 9,126 skills
- agents/278 of 1,812 authors, 593 of 9,126 skills
- examples/176 of 1,812 authors, 274 of 9,126 skills
- templates/148 of 1,812 authors, 214 of 9,126 skills
GLips/Figma-Context-MCP/io.github.GLips/Figma-Context-MCP MCP server
in 1 stack15,643★ repoGive your coding agent access to your Figma data. Implement designs in any framework in one-shot.
eigent-ai/eigent/resources/example-skills/docx Skill
15,013★ repoEigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex
tt-a1i/archify/archify Skill
10,485★ repoAgent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
OpenSenseNova/SenseNova-Skills/skills/sn-da-excel-workflow Skill
4,914★ repoModular SenseNova skills for building AI-powered office assistants and productivity workflows
wuyoscar/GPT-Image2-Skill/skills/gpt-image Skill
4,246★ repoGPT Image 2 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing
Vincentwei1021/video-shotcraft Skill
4,130★AI video skill for Claude Code & Codex — cinematic product videos with Remotion: 106 shot recipe cards, 161 motion previews, a production-ready template
glincker/thesvg/skills/thesvg Skill
2,560★ repo6,400+ brand SVG icons for developers. Tree-shakeable, typed, open source. npm i thesvg
figma/mcp-server-guide/com.figma.mcp/mcp MCP server
no license1,875★ repoThe Figma MCP server brings Figma design context directly into your AI workflow.
plannotator/effective-html/skills/html-diagram Skill
1,633★ repoAgent skill for elegant and simple html plans, architecture diagrams, or whatever else you can think of.
JuneYaooo/gpt-image2-ppt-skills Skill
1,170★Clone any .pptx into your own deck — OpenAI gpt-image-2 mimics the layout, you supply the content. 10 bundled styles. | 把任何 .pptx 模板"抄"成你的 PPT：gpt-image-2 仿版式、你换内容，另含 10 套精选风格。Claude Code / OpenClaw skill.
0xsline/OpenChatCut/src/agent/skills/asset-import Skill
1,057★ repoLocal-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion-powered rendering.
shang-zhu/violin/.claude/skills/video-translator Skill
1,036★ repoOpen-source Video Translation Skill
axoviq-ai/synthadoc/synthadoc/skills/docx Skill
970★ repoSynthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-managed and self-improved without the use of any tools.
SylphxAI/pdf-reader-mcp/io.github.SylphxAI/pdf-reader-mcp MCP server
887★ repoEvidence-first PDF MCP. Agent Document Twin with citeable page+bbox evidence.
nexu-io/codex-slides/skills/codex-slides-browser Skill
804★ repo🎨 Open-source AI slide studio inside Codex: image-native decks, every slide a full visual canvas. ⚡ 10+ high-quality slides in ~4–5 minutes — Fast mode renders every page in parallel. 🔍 Watch the whole chain live: research → outline → style → render → edit → present → export PDF/PPTX. 🖥️ Browser-first · zero API keys · durable projects.
Gabberflast/academic-pptx-skill Skill
760★A Claude Skill for creating academic presentations (conference talks, seminar slides, thesis defenses, grant briefings). Enforces action titles, structured argument, exhibit discipline, citation standards, and communication-first design. Works alongside Anthropic's built-in PPTX skill.
sparklabx/drawio-ai-kit/skills/drawio-aws Skill
626★ repoTeach your AI to draw correct, beautiful draw.io diagrams — declarative layout engine, ground-truth stencils, structural validator, vision self-check. AWS · Azure · GCP · Databricks · BPMN. Zero dependencies.
hustcc/mcp-mermaid/ai.smithery/hustcc-mcp-mermaid MCP server
621★ repoGenerate dynamic Mermaid diagrams and charts with AI assistance. Customize styles and export diagr…
ronak-create/FableCut/io.github.ronak-create/fablecut MCP server
588★ repoZero-dependency browser video editor AI agents drive via a JSON timeline over MCP; ffmpeg export.
linzzzzzz/openclip/.claude/skills/video-clip-extractor Skill
547★ repoOpenClip - AI-powered highlight extraction for long videos (AI 驱动的长视频精彩时刻提取工具)
sbroenne/mcp-server-excel/io.github.sbroenne/mcp-server-excel MCP server
532★ repoExcel automation for AI - Sheets, Power Query, DAX, VBA, Tables, Ranges and more. Windows only.
ZeroPointRepo/youtube-skills/clawhub/captions Skill
518★ repoYouTube Transcript API skills for AI agents. Get transcripts, search videos, browse channels. Works with OpenClaw, Hermes-Agent, Claude Code, Cursor, Windsurf.
MartinDelophy/ai-video-editor/skills/edit-timeline-studio Skill
490★ repoLocal-first browser AI video editor with ONNX voiceovers, Whisper captions, talking avatars, and multi-track MP4/WebM export.
jkawamoto/mcp-youtube-transcript/io.github.jkawamoto/mcp-youtube-transcript MCP server
463★ repoAn MCP server retrieving transcripts of YouTube videos
worldwonderer/video-recap-skills/skills/video-assemble Skill
447★ repoClip any video into a narration recap with claude code skill｜用 claude code skill 把任何视频剪辑成中文解说视频，支持剪映导出
Jaycheng1103/chatgpt-video-editing-skills/skills/chatgpt-short-video-editor Skill
417★ repo用 ChatGPT／Codex 安裝 AI 剪輯環境，並依八大步驟完成可驗證的短影音剪輯。
yanhua1010/self-media-content-workflow/skills/self-media-content-analytics Skill
365★ repo通用、模块化的自媒体内容生产与经营 Skills / A modular, tool-agnostic self-media content skill suite
MemTensor/skills-vote/examples/evaluate_skills/pdf Skill
295★ repoSkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
burningion/video-editing-mcp/io.github.burningion/video-editing-mcp MCP server
no license285★ repoMCP Server for Video Jungle - Analyze, Search, Generate, and Edit Videos
modu-ai/cowork-plugins/moai-bi/skills/executive-summary Skill
268★ repo모두의 AI (MoAI) — Claude Cowork & Claude Code 한국 실무 도메인 AI 하네스·플러그인 마켓플레이스. 사업계획서·세무·법률·HR·마케팅·커머스·BI·콘텐츠 도메인 스킬·에이전트·워크플로우. Korean B2B + office docs (HWPX/DOCX/XLSX/PPTX/PDF) + AI media (image/video/voice). AI-slop 검수 + humanize-korean 내장.
taisly/agent/io.github.taisly/agent MCP server
264★ repoPublish videos to TikTok, Reels, Shorts, X, and Facebook through Taisly.
bowenliang123/markdown-exporter Skill
261★An Agent Skill and Dify plugin to transform Markdown to files of DOCX, PPTX, XLSX, PNG, PDF, Mermaid, HTML, MD, CSV, JSON, XML.
sonpiaz/watch-cli/io.github.sonpiaz/watch-cli MCP server
248★ repoHand any social video to your AI agent — frames + transcript bundled. MCP server for watch-cli.
leemysw/feishu-docx/.skills/feishu-docx Skill
247★ repo🚀 Feishu/Lark Docs、Sheet、Bitable <-> Markdown | AI Agent-friendly knowledge base exporter and writer with OAuth 2.0, CLI, TUI & Claude Skills support - 飞书文档 <写入/导出> Markdown | AI Agent 友好型导出-写入工具
TranHoaiHung/figma-ui-mcp/io.github.TranHoaiHung/figma-ui-mcp MCP server
221★ repoBidirectional Figma MCP — AI draws UI on Figma canvas, reads designs back
Misaka-Mikoto-Tech/agent-skills/skills/bilibili-page-reader Skill
220★ repoReusable AI agent skills for Codex, including a PowerShell skill for safe Windows command invocation and optional MCP utilities.
hubeiqiao/apple-bento-grid Skill
213★Agent skill that generates Apple-inspired bento grid presentation cards. For Claude Code, Codex, and any AI coding agent.
KaguraNanaga/document-format-skills Skill
211★Professional Word document formatting toolkit for Chinese documents
EveryInc/hands-on-deck/skills/hands-on-deck Skill
203★ repoAgent-native PowerPoint manipulation — one CLI lets AI agents inspect, edit, create, and verify .pptx files through atomic JSON patches. Packaged as an Agent Skill.
dean9703111/ai-agent-skill-for-video-workflow/.agent/skills/audio-to-srt Skill
no license203★ repo這是一個專為影片字幕處理設計的 AI Agent Skills 集合，提供從音訊轉字幕、優化字幕、設計字卡到生成社群媒體摘要的完整工作流程。
hiyeshu/codeck/skills/codeck-design Skill
202★ repoNo Keynote. No dragging. No font sizes.
SkyworkAI/Skywork-Skills/skywork-design Skill
199★ repoSkywork Agent Skills for AI office suites, including AI PPT, AI Document, AI Excel, AI Image, AI Search/DeepResearch and AI Music. These skills can be used by any skills-compatible agent, including Claude Code, Codex CLI and OpenClaw.
opendatalab/MinerU-Ecosystem/io.github.opendatalab/mineru-open-mcp MCP server
188★ repoParse PDFs, images, doc, docx, ppt, pptx, xls, xlsx, html into Markdown using MinerU API.
Agents365-ai/excalidraw-skill/skills/excalidraw-skill Skill
186★ repoHand-drawn Excalidraw diagrams from natural language. 5 patterns, 8-color semantic palette, Kroki API or local CLI. PNG/SVG, multi-agent.
Agents365-ai/mermaid-skill/skills/mermaid-skill Skill
170★ repoMermaid diagrams (.mmd) from natural language with validation loop. 11+ types, multi-backend (mmdc / Kroki), PNG/SVG/PDF, multi-agent.
smixs/visual-skills/image 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
dog-qiuqiu/invincat/invincat_cli/built_in_skills/docx Skill
153★ repoA native Python agent CLI built on DeepAgents CLI, featuring an independent memory Agent that captures learnings after each task and delivers efficient AI coding assistance through hierarchical memory management.
csthink/dashmotion/skills/dashmotion Skill
150★ repoAnimated technical diagrams from plain English or Mermaid — a Claude skill, self-contained HTML/SVG.
roomi-fields/notebooklm-mcp/io.github.roomi-fields/notebooklm-mcp MCP server
147★ repoAutomate Google NotebookLM — Q&A with citations, audio, video, content generation
appautomaton/document-SKILLs/docx Skill
143★ repoClaude Code and Codex SKILLs for PDF, Excel, Word, and PowerPoint manipulation — extraction, forms, formulas, tracked changes, adapted from Anthropic skills.
BV-Venky/excalidraw-architect-mcp/io.github.BV-Venky/excalidraw-architect-mcp MCP server
142★ repoGenerate beautiful Excalidraw architecture diagrams with auto-layout and component styling
pattern-ai-labs/agentcall Skill
141★AgentCall lets AI Agents join meetings with voice, video & screen-share to build together. Supports Google Meet, Teams, Zoom (Beta)
Cassette-Editor/oh-my-cassette/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
Alisa0808/vibe-creating-skill/skills/vibe-creating-prompt Skill
no license133★ repoOpen-source, bilingual AI video-prompt skill — rewrite ideas into model-ready text-to-video prompts. A portable Agent Skill (Claude Code, Codex, OpenClaw, Hermes); generate via Atlas Cloud — Seedance 2.0, Kling, Veo, Hailuo, Wan, Vidu, Gemini Omni, Grok Imagine.
xlbaoxl/interactive-map-builder Skill
121★Build polished interactive maps and report-ready figures from spatial data with AI agents.
ShZhao27208/Aut_Sci_ppt Skill
115★Aut_Sci_PPt is an automated agent designed to convert academic papers (PDF) or structured text into professional, presentation-ready PowerPoint files (.pptx). It is specifically optimized for graduate defense, academic seminars, and research proposals.
runesleo/claude-video-kit/skills/video-explainer Skill
113★ repoAgent Skill + Remotion pipeline: brief/script → review receipt → narrated 9:16 explainer. RC: video-explainer skill.
KyaniteLabs/kinocut/io.github.KyaniteLabs/kinocut MCP server
113★ repoGuardrailed video editing for AI agents: FFmpeg, captions, effects, Hyperframes, and receipts.
infranodus/skills/infranodus-cli Skill
no license107★ repoSkills to augment LLM thinking process, integrated with InfraNodus insight generation tool
ComPDFKit/compdf-skills/skills/pdf-editor-compdf Skill
no license105★ repoComPDF Skills are AI-agent-ready PDF processing skills for Claude Code, Cursor, Copilot, OpenCode, and 39+ coding agents to convert, edit, split, insert, compare, compress PDFs, and more.