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
XJTLUmedia/AI_answer_copier/io.github.XJTLUmedia/markdown-formatter MCP server
3★ repoAI Answer Copier — Convert Markdown to PDF, DOCX, HTML, LaTeX, CSV, JSON, XML, XLSX, RTF, PNG
beeswaxpat/ffmpeg-render-pro/io.github.beeswaxpat/ffmpeg-render-pro MCP server
3★ repoParallel video rendering tools: detect GPU encoders, render, color grade, merge audio, concat.
chicogong/ffvoice-engine/io.github.chicogong/ffvoice MCP server
3★ repoOffline speech-to-text & speaker diarization MCP server: transcribe audio on-device, no cloud
debu-sinha/excalidraw-mcp-server/io.github.debu-sinha/excalidraw MCP server
3★ repoSecurity-hardened Excalidraw MCP server with auth, rate limiting, and 14 tools
jwulff/whisper-mcp/io.github.jwulff/whisper-mcp MCP server
3★ repoLocal audio transcription using whisper.cpp. Transcribe with OpenAI Whisper models.
ludmila-omlopes/youtube-video-analyzer-mcp/io.github.ludmila-omlopes/youtube-video-analyzer MCP server
3★ repoMCP stdio server for analyzing YouTube videos with Google Gemini
Crazy-MT/video-subtitle Skill
2★AI-powered video subtitle pipeline — extract audio, transcribe with Whisper, translate, and burn subtitles into videos. One-click install for Claude Code, Codex, Cursor & more.
renalpelvisdeinocheirus70/ozor-skills/mnt/user-data/outputs/ozor-skills/skills/ozor-doc-to-video Skill
2★ repoBuild Ozor AI video prompts and skills for product launches, ads, explainers, and more
isatimur/presentation-md/packages/core Skill
2★ repoTurn rough notes into a polished, schema-validated slide deck in any AI agent (Claude Code, Cursor, Codex, Gemini CLI, Copilot) — then export native, editable PowerPoint, Keynote & Google Slides. Skill + MCP server.
YuYY2004/excel-skills/claude/skills/excel-date-to-text Skill
2★ repo18 Excel processing skills for Claude Code & Codex. XML direct ops for large files — 4-10x faster. Available in Chinese and English.
Matthewyin/CustomSkills/plugins/diagram-generator/skills/diagram-generator Skill
no license2★ repodrstarry/interactive-video-skill Skill
2★Turn docs, posts, and codebases into interactive walkthroughs — narrated animation, quizzes, and hands-on widgets.
helloyxs/generate-html-ppt Skill
2★A coding-agent skill for creating stunning, interactive HTML presentations — from scratch or by converting PowerPoint (`.pptx`) files.
rtfirst/music-analyzer Skill
2★AI Coding Agent Skill for comprehensive music analysis — genres, moods, instruments, BPM, key, lyrics & production description
zcker/xiaoyuzhou-podcast-skill Skill
no license2★自动下载小宇宙播客音频并生成完整转录文本的 Claude Code Skill。如果对你有用请 Sponsor，thanks bro!
PhSeCl/pdf-courseware-to-obsidian Skill
2★Claude Code skill: 将本地 PDF/PPT 课件批量整理为图文并茂的 Obsidian 复习笔记知识库
SkillMedev/creator-studio/skills/content-repurposing Skill
2★ repoSix skills for video and podcast creators who publish consistently and grow.
jnichor/creador_videos_ai Skill
2★Claude Code skill that turns any website URL into a 30s cinematic marketing video — drone tour, voice off, word-synced subtitles, square/vertical/horizontal. HTML + Python + FFmpeg.
Aidress skill find verified social media management agent
Aidress-ai/aidress-skill-find-verified-social-media-management-agent Skill
2★Find a Verified Social Media Management Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for content agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).
roeibh/marp-deck-architect Skill
2★Claude skill for building Marp presentations. 4 archetypes (Builder, Operator, Storyteller, Educator) that shape not just the theme - but how the deck gets written.
PodcastAPI/skills/skills/podcast-api Skill
2★ repoSkills for teaching agents how to build with the Podcast API
zmazz/thinkcell Skill
2★Agent skill for creating, validating, and automating think-cell PowerPoint chart workflows.
vdk888/local-tts/skills/local-tts Skill
2★ repoLocal TTS plugin for Claude Code — 30 languages, voice design, voice cloning. Free, offline, powered by VoxCPM2.
casatwy/deyo-skill/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。
geekjourneyx/video-post Skill
2★Short-form video finishing skill for turning animation HTML and master MP4 files into delivery-ready variants with Bun and FFmpeg
zhoujiegg123-svg/official-docx-cn-skill/official-docx-cn Skill
2★ repo公文格式排版
ltppp/douyin-ingest/skills/douyin-content-ingest Skill
2★ repoDouyin/抖音 agent skills for Top-N viral video collection, speech-to-text transcripts, short-video script rewriting, and Word delivery.
ouyangevan/evidence-first-ai-video-skill/skills/evidence-first-ai-video Skill
2★ repoAI 科技口播与演示视频 Codex Skill：真实界面、官方素材、连续口播、分镜与逐镜头 QA | Evidence-first AI video workflow
twotwo/obsidian-skills/.skills/excalidraw-diagram Skill
2★ repo开箱即用的 Obsidian 仓库，集成设计常用的 Obsidian Skills
tinhtran24/maestro/.claude/skills/brandkit Skill
2★ repoMaestro is an open-source, multi-agent AI development framework written in Go. It orchestrates specialized AI coding agents across a deterministic software engineering workflow
Ghosteken/agent-harness/archive/skills-community/2slides-ppt-generator Skill
2★ repoProduction-grade engineering skills and specialist agent personas for AI coding assistants. Orchestrates the full SDLC, from spec to ship, with structured verification gates, anti-rationalization checks, and senior-level engineering discipline.
Stephen-studying/tech-route-maker Skill
2★Evidence-grounded editable technical route diagrams for research and engineering projects.
Hubujiu/fan-poker-teaching-skill Skill
2★An Agent Skill for turning any topic into a dependency-free interactive HTML lesson with a single-sided fan poker deck animation.
h46373824-tech/format-thesis-docx-skill/format-thesis-docx Skill
2★ repoCodex skill + Microsoft Word Add-in for AI-assisted thesis DOCX formatting: templates, cover metadata, page numbering, confirmations, and dynamic TOC.
mbanderas/maestro-agora/skills/agora Skill
2★ repoVerified truth, conducted into copy. Argument-first Agent Skill for buyer, investor, editorial, interface, outreach, and spoken copy.
PBNZ/watch-local/plugins/watch-local Skill
no license2★ repoClaude Code plugin that gives Claude a video input — fully local. /watch downloads, extracts frames, and transcribes with faster-whisper on a self-provisioned portable runtime (no Docker, no system installs). Auto-detects NVIDIA GPUs (NVDEC decode + CUDA whisper), CPU-only fallback. No cloud APIs.
narumiruna/kabigon/skills/kabigon Skill
2★ repoA multi-source URL content loader that extracts text from social posts, videos, PDFs, and web pages via a simple CLI and Python API.
shaom/infocard-video-skills/skills/remotion-video-workflow Skill
2★ repoReusable Remotion agent skills for infocard structured short-form video production.
alfredang/skills/ai-avatar-video Skill
no license2★ repoClaude Code skills: auto-detect & start any app, README generator, Docker Hub push, LinkedIn posts, NotebookLM slides, secret scanner, mobile responsiveness testing | Install with npx skills add
FrankL1u/liusir-skills/skills/ls-multi-collector Skill
no license2★ repoAI agent skills for WeChat article writing, publishing, and workflow automation.
wokaka209/markdown_everything/SKILL/markdown-everything Skill
2★ repoAI agent skill
Creating canvas video animations
siegerts/skill-canvas-video/creating-canvas-video-animations Skill
2★ repoAgent skill for creating animated videos using HTML5 Canvas and JavaScript, exportable to MP4.
shiyunbo/hd-video-downloader Skill
no license2★A powerful HD video downloader skill that supports YouTube, Bilibili, TikTok, and 1000+ more platforms. Optimized for compatability and speed.
notfolder/isdd/.agents/skills/mermaid-syntax-skill Skill
no license2★ repoisdd（Interview-driven Spec-driven Development）はインタビュー駆動で仕様を確定して、要件・設計・ソースをIDで一貫追跡しながら、開発を進める手法です。
siegerts/agent-transcript/skills/agent-transcript Skill
2★ repoAgent Skill - Find and export chat session transcripts from coding agents.
1-SKILL/jiaoben Skill
no license2★短视频脚本工坊 — 5分钟出完整脚本,产能提升5倍,完播率翻倍
keepYaoung/artifact-organizer/plugins/artifact-organizer/skills/artifact-organizer Skill
2★ repoAgent skill that turns semantic JSON into self-contained, themed HTML — then stacks your artifacts into one persistent, restyleable dashboard. Zero dependencies, opens offline.
Alibaba quark transoffice qoder
alibaba-quark-scanking/alibaba-quark-transoffice-qoder Skill
2★夸克扫描王-文档格式转换工具（Qoder专用版本）。将图片、截图或扫描件转换为可编辑的 Word、Excel 或 PDF 文件，支持版式还原。由夸克扫描王 API 提供支持。
alibaba-quark-scanking/alibaba-quark-scan-qoder Skill
2★夸克扫描王-文件扫描工具（Qoder专用版本）。当用户需要对图片、截图进行画质优化、瑕疵去除或视觉增强时使用此技能，包括画质增强、证件照优化、考试试卷增强、合同增强等场景。智能去除手写笔迹、水印、阴影、摩尔纹、底色等干扰元素。支持图像裁剪与矫正、素描效果转换、线稿提取等，输出优化后的高清图片。本技能由夸克扫描王提供支持。即使用户没有明确提到“增强”或“处理”，只要用户的需求涉及提升图片清晰度、清理干扰元素或优化图像质量，也应触发此技能。不适用于文字提取/识别、文档转换 (Word/Excel/PDF)、AI 图像生成、证件照制作
bybaochaule/pdf-image-converter Skill
no license2★This Agent Skill converts PDF pages into PNG, JPEG, or JPG image files. It is designed for page rendering, preview generation, and batch PDF-to-image conversion.
zjczg/listen-to-content/skills/listen-to-content Skill
2★ repoGenerate, cache, play, and control DashScope speech on macOS with Codex and OpenCode Skills.
rossyao2022/editable-html-slides Skill
2★Zero-dependency in-browser WYSIWYG editor you can bolt onto any HTML slide deck — inline text edit, add images, drag/resize, undo/redo, slide reorder, autosave & export. Pairs with html-ppt/reveal decks.
hyt315/notebook-video Skill
2★Visual-director Agent Skill for 2K Chinese Remotion videos with original imagery, animated text and automated QA.
mrloldev/artificial-analysis-skill Skill
2★Agent skill that picks the right AI model using live benchmarks from artificialanalysis.ai. Works with Claude Code, Cursor, Codex, and any skills.sh-compatible agent.
run-llama/llamaparse-agent-plugins/plugins/liteparse/skills/liteparse Skill
2★ repoClaude Code/Codex plugins for LlamaParse, LiteParse and LlamaParse MCP
m1crodevil/hermes-video-rs/skill/watch2 Skill
2★ repoRust-powered video analysis skill for Hermes Agent — transcript-first with scene detection
Docx batch variable replacement
kuliantnt/docx-batch-variable-replacement Skill
2★Codex/agent skill for batch replacing variables in DOCX templates with safety checks and reports.
sfrangulov/skills/book-to-skills Skill
2★ repoAgent skills installable via skills.sh
Ai startup due diligence skill
PiroteQueen/ai-startup-due-diligence-skill Skill
2★Open-source Agent Skill for AI startup due diligence: evidence ledger, Q&A gap list, OnePage, IC memo, risk register, VC-fit analysis
drakulavich/iago/iago Skill
2★ repo🦜 Greptile-style Mermaid diagrams for AI code reviews — drawn by your own agent. A Claude Code / Codex / Copilot / Gemini skill; run /iago after /review.