majiayu000/claude-skill-registry-data/multiformat-to-md

Claude Code and agent skill by majiayu000/claude-skill-registry-data

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Tainted

Author "majiayu000" has blocked skill(s)

Convert source files into Markdown for LLM ingestion. Use this skill for PDF/Word/images (.pdf/.docx/.doc/.png/.jpg/.jpeg) and audio/video transcription (.mp3/.mp4).

Install

npx vskill@latest install majiayu000/claude-skill-registry-data/multiformat-to-md

SKILL.md

Multiformat To Markdown

Script Architecture

  • scripts/multiformat_gateway.py
  • Shared/common layer for this skill.
  • Provides shared helpers (ProgressPrinter, resolve_inputs, markdown builder/writer).
  • Provides runtime bridge API convert_file_to_markdown_via_skill for utils/agents/dataloaders.py.
  • scripts/docs_images2md.py
  • Handles document/image conversion only.
  • Includes doc/image-specific extraction functions (PDF/DOCX/DOC/OCR).
  • scripts/media2md.py
  • Handles media transcription only.
  • Includes media-specific functions (audio/video transcription + optional LLM rewrite).

Usage

Document/image to markdown:

powershell
python skills/multiformat-to-md/scripts/docs_images2md.py `
  --input "E:/data/raw_docs" `
  --output "E:/data/md_output"

Media to markdown:

powershell
python skills/multiformat-to-md/scripts/media2md.py `
  --input "E:/data/raw_media" `
  --output "E:/data/md_output" `
  --whisper-model "base"

Enable LLM rewrite for media:

powershell
python skills/multiformat-to-md/scripts/media2md.py `
  --input "E:/data/raw_media" `
  --output "E:/data/md_output" `
  --whisper-model "base" `
  --rewrite-with-llm

Dependencies

powershell
pip install pypdf python-docx pillow pytesseract openai-whisper faster-whisper pypdfium2 pymupdf requests

System tools when needed:

  • ffmpeg for .mp4
  • tesseract-ocr for OCR
  • antiword for .doc fallback

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/majiayu000/claude-skill-registry-data/multiformat-to-md/badge)](https://verified-skill.com/skills/majiayu000/claude-skill-registry-data/multiformat-to-md)

Something wrong with this skill or its page? Tell us.