agentmods.dev

MinerU-MCP: Skill for Claude Code

.claude/skills/convert-to-markdown/SKILL.md

convert-to-markdown is a skill for Claude Code from AvatarGanymede/MinerU-MCP. It costs 147 tokens per session (1,070 once invoked), scanned A, original, MIT.

A document-conversion workflow that extracts text, tables, and formulas from PDFs, office files, images, and web pages into Markdown.

In plain words
What is it for?
Converting local files or URLs, including PDFs, DOC/DOCX files, presentations, images, and HTML, into Markdown.
Why use it?
It turns documents into editable, searchable text without requiring manual copying or formatting.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is AvatarGanymede/MinerU-MCP's own configuration. It tells Claude Code how to work on MinerU-MCP itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything MinerU-MCP configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is unzip -o ./temp/report.zip -d ./temp/report.

not rated 5repo 6mo ago A scan 147 tokens original MIT
View source ↗ AvatarGanymede/MinerU-MCP
Reuse

Borrowing it

Nothing to install: this file belongs to AvatarGanymede/MinerU-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/AvatarGanymede/MinerU-MCP/main/.claude/skills/convert-to-markdown/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/AvatarGanymede/MinerU-MCP

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for convert-to-markdown

README.md
[![agentmods](https://agentmods.dev/badge/skills/avatarganymede/mineru-mcp/convert-to-markdown/github.svg)](https://agentmods.dev/skills/avatarganymede/mineru-mcp/convert-to-markdown)
Your own site
<a href="https://agentmods.dev/skills/avatarganymede/mineru-mcp/convert-to-markdown"><img src="https://agentmods.dev/badge/skills/avatarganymede/mineru-mcp/convert-to-markdown/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for convert-to-markdown

Your own site · 80×15
<a href="https://agentmods.dev/skills/avatarganymede/mineru-mcp/convert-to-markdown"><img src="https://agentmods.dev/badge/skills/avatarganymede/mineru-mcp/convert-to-markdown.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 147 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,070 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00147 $0.01070
Opus 5 $0.00073 $0.00535
Sonnet 5 $0.00029 $0.00214
Haiku 4.5 $0.00015 $0.00107

Measured 12d ago against content hash 52b501a66ff9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

convert-to-markdown scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/convert-to-markdown/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Document to Markdown Conversion

Convert documents to Markdown using the mineru-converter MCP tools. Supports URLs and local file paths. The server auto-detects file type and configures optimal settings (model, OCR, etc.).

MCP Tools Reference

Primary tool — use this by default

  • convert_to_markdown — Complete workflow: submit → poll → download. Parameters:
    • url (required): URL or local file path
    • output_path (required): local path to save the result zip (e.g., ./temp/report.zip)
    • model_version (optional, default "vlm"): auto-detected; "MinerU-HTML" for HTML files
    • max_wait_seconds (optional, default 300): increase for large documents (e.g., 600 for 100+ page PDFs)
    • poll_interval (optional, default 10)
    • convert_pdf_to_markdown is an identical alias

Step-by-step tools — use when finer control is needed

  1. create_parse_task — Submit a parsing task. Extra parameters:

    • is_ocr (default false): force OCR on; auto-enabled for images
    • enable_formula (default true): formula recognition
    • enable_table (default true): table recognition
    • Returns task_id (URL input) or batch_id (local file input)

  2. get_task_status — Poll task progress. Pass task_id or batch_id.

  3. download_result — Download the result zip. Parameters: zip_url, output_path.

Use step-by-step tools when the user needs to: disable formula/table recognition, force OCR, submit multiple tasks in parallel, or check a previously submitted task.

Workflow

1. Determine output path

  • If the user provided an output path, use it (ensure it ends in .zip).
  • Otherwise, derive from the filename: ./temp/<filename_without_ext>.zip
    • URL example: https://example.com/report.pdf → ./temp/report.zip
    • Local example: C:\docs\slides.pptx → ./temp/slides.zip

2. Call convert_to_markdown

Pass url (the URL or local file path as-is) and output_path. The server handles:

  • Local file upload via batch API automatically
  • HTML → MinerU-HTML model, images → OCR enabled
  • Large PDFs: >600 pages uses page ranges; >200MB splits the file into chunks
  • Polling until completion or timeout

Read the full file on GitHub · 94 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 94 lines · 147 tokens per session scan A 52b501a66ff9

Subscribe to this mod's changes

convert-to-markdown is a skill published in the GitHub repository AvatarGanymede/MinerU-MCP (5 stars, last pushed 6mo ago), licensed MIT. It adds 147 tokens to every session and 1,070 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

DocumentsPDFagent-skillmarkdownconversionmcp-serverminerupdf-to-markdown
Related

Other skills, from other repositories

pdf-table-to-excel

A workflow for turning tables in PDF files into Excel workbooks, with one sheet per table and supporting images and quality notes. It uses MinerU, a tool that extracts content from PDFs, and needs an image-reading model to check the results.

kujiangmudao/tablepack · 132 tokens

n8n-binary-and-data

Handle files and binary data in n8n correctly. Use when working with files, images, PDFs, attachments, uploads or downloads, base64, vision/multimodal input, or when an AI agent needs a file as tool input or output — and whenever the user mentions $binary, binaryPropertyName, "read the PDF", "attach the file", "send…

czlonkowski/n8n-mcp · 135 tokens

doc-convert

A converter that formats Markdown documents as HTML, printable PDF files, or long PNG images. Markdown is plain text with simple formatting marks for headings, lists, tables, and code.

ZJU-REAL/Easel · 77 tokens

exam-study-guide

A study-guide builder for a completed exam chapter that has not yet passed its required checks. It creates a structured teaching checklist and, in full mode, a self-contained HTML and printable PDF guide with readable formulas, visible images, explanations, examples, and answers.

ZeKaiNie/universal-examprep-skill · 113 tokens

markdown-to-pdf

Convert a markdown file to PDF using mistune + reportlab. Use when the user wants to convert a .md file to PDF, or when another skill needs to produce a PDF from markdown output.

staskh/trading_skills · 45 tokens

figure-remap

Extract single figures from PDF textbooks on-demand with built-in QC verification. Primary use: when writing/supplementing a note that needs an embedded figure (anatomy, classification, algorithm, imaging). Each call checks an existing fast-path crop, re-extracts from PDF if missing/wrong, retries with local-vision…

drpwchen/textbook-to-note · 126 tokens