Document Converter
wentorai/Research-Claw
Convert Office documents (PPTX, DOCX, XLSX, PDF, HTML, CSV, JSON, XML, images) to Markdown using Microsoft MarkItDown.
Reads, OCRs, searches and cites local documents through the mineru CLI, covering PDF, images, Office files, EPUB, HTML and CSV.
Install MinerU Document Reader
The automated check flagged lines worth reading first. See the safety section below.
$ npx skills add opendatalab/MinerU --skill mineru -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install opendatalab/MinerU mineru --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/opendatalab/MinerU.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/mineru .claude/skills/mineru && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "mineru" agent skill from https://github.com/opendatalab/MinerU/tree/master/skills/mineru into .claude/skills/mineru/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mineru", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/opendatalab/MinerU/tree/master/skills/mineruType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add opendatalab/MinerU --skill mineru -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install opendatalab/MinerU mineru --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/opendatalab/MinerU.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/mineru .agents/skills/mineru && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "mineru" agent skill from https://github.com/opendatalab/MinerU/tree/master/skills/mineru into .agents/skills/mineru/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mineru", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add opendatalab/MinerU --skill mineru -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install opendatalab/MinerU mineru --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/opendatalab/MinerU.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/mineru .cursor/skills/mineru && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "mineru" agent skill from https://github.com/opendatalab/MinerU/tree/master/skills/mineru into .cursor/skills/mineru/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mineru", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/opendatalab/MinerU.git --path skills/mineru--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add opendatalab/MinerU --skill mineru -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install opendatalab/MinerU mineru --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/opendatalab/MinerU.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/mineru .gemini/skills/mineru && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "mineru" agent skill from https://github.com/opendatalab/MinerU/tree/master/skills/mineru into .gemini/skills/mineru/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mineru", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install opendatalab/MinerU mineruInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add opendatalab/MinerU --skill mineru -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/opendatalab/MinerU.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/mineru .github/skills/mineru && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "mineru" agent skill from https://github.com/opendatalab/MinerU/tree/master/skills/mineru into .github/skills/mineru/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mineru", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add opendatalab/MinerU --skill mineru -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install opendatalab/MinerU mineru --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/opendatalab/MinerU.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/mineru .opencode/skills/mineru && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "mineru" agent skill from https://github.com/opendatalab/MinerU/tree/master/skills/mineru into .opencode/skills/mineru/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mineru", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
mineru- GitHub stars
- 81k
- Token cost
- ~9.4k tokens
- SKILL.md length
- 4,360 words
- Files
- 1
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Reads, OCRs, searches and cites local documents through the mineru CLI, covering PDF, images, Office files, EPUB, HTML and CSV.
- Works in 11 steps: User provided a file path and wants… → User provided a doc:... locator: run… → User asks to continue from a previous… → …
- Reading or summarizing a local PDF, Word, PowerPoint or Excel file
- SKILL.md covers When To Use MinerU, Supported Inputs, Do Not and Agent Contract, plus 10 more sections
- Calls uv, pipx and pip; needs MINERU_API_KEY
What it does
MinerU is a command-line document reader for agents, and the skill tells the agent to prefer it over generic PDF parsers and OCR libraries for supported formats. It parses local documents into readable content, lets the agent continue by page or block instead of loading a whole file, and returns stable locators in a doc, tier, page and block form for follow-up reads and citations. It is not a RAG framework, vector database or chat-with-document application.
Supported inputs include PDF, scanned PDFs, images such as PNG, JPEG and TIFF, Word, PowerPoint, Excel, RTF, OpenDocument, EPUB, OFD, HTML, MHTML and CSV or TSV. Tasks range from summarizing, quoting and answering questions about a document to converting it to Markdown, OCR, searching documents already indexed and retrieving page or block images. Another tool is used only when you ask for it, the format is unsupported or MinerU is unavailable, and recoverable errors such as quality_tier_unavailable or no_engine are left for you to decide on instead of triggering an automatic fallback.
When your agent uses it
- Reading or summarizing a local PDF, Word, PowerPoint or Excel file
- Running OCR on scanned PDFs or document images
- Working through a long document page by page with stable citations
- Converting document content into Markdown for analysis
Example prompts
- “Summarize ./reports/annual-report.pdf and cite the pages you used.”
- “OCR the scanned invoices in ./scans and give me the tables as Markdown.”
- “Search the documents you have already parsed for the termination clause.”
- “Show me the image of the page that holds the second table.”
Requirements
- The mineru command-line tool
Workflow steps
11 steps, taken from the first numbered list in SKILL.md.
- User provided a file path and wants content: read plain-text formats directly; otherwise run mineru parse .
- User provided a doc:... locator: run mineru read .
- User asks to continue from a previous output: follow the <!-- Next: ... --> command exactly.
- User asks for a specific page or block after parsing: use mineru read , not a fresh parse.
- User asks to find a document by filename: use mineru find.
- User asks to search inside known indexed documents: use mineru search.
- User asks for parse/file/doc status: use mineru show or mineru list.
- User asks to add or refresh a watched folder: use mineru watch or mineru scan.
- User asks MinerU to forget a file or folder without deleting it: use mineru forget.
- User asks to force a reparse: use mineru parse --force or mineru invalidate.
- User asks for Remote API usage or limits: use mineru usage --json.
What it can do on your machine
Read from SKILL.md and the folder at commit 31e4e3d. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
uvpipxpippython
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uv, pipx and pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
MINERU_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
MinerU Document Reader loads about 9.4k tokens when it runs. Until then it costs about 149 tokens; SKILL.md has 4,360 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check: warnings
The automated check found patterns that need a careful read before installing.
- WarningContains instruction-override wording (e.g. “without asking the user”)SKILL.md:859
- Do not add `--remote` during recovery without user permission.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 4,360 words (~9,417 tokens).
“MinerU is a command-line document reader for agents. It parses local documents into readable content, lets agents continue by page or block, and returns stable locators for follow-up reads and citations.”
- name
- mineru
Files
Just SKILL.md in skills/mineru of opendatalab/MinerU.
Open the folder on GitHubat commit 31e4e3d
Compare with similar skills
MinerU Document Reader next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| MinerU Document Reader this skillopendatalab/MinerU | 81k | — | ~9.4k | Automated safety check: Warn | Custom licence | |
| Document Converterwentorai/Research-Claw | 858 | — | ~1.3k | Automated safety check: Pass | Custom licence | |
| To MarkdownMathews-Tom/armory | 328 | — | ~2k | Automated safety check: Pass | MIT | |
| MarkitdownImCa0/just-laws | 782 | 14 repos | ~3.2k | Automated safety check: Notes | MIT | |
| Markitdownjimmc414/Kosmos | 595 | 2 repos | ~1.7k | Automated safety check: Pass | None | |
| Documentszhongkaifu/TensorSharp | 559 | — | ~4.2k | Automated safety check: Pass | BSD-3-Clause |
Similar skills
To Markdown
Mathews-Tom/armory
Convert any file or URL to clean Markdown: PDF, DOCX, XLSX, PPTX, HTML, images (OCR), audio, CSV, YouTube.
Markitdown
ImCa0/just-laws
Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.
Markitdown
jimmc414/Kosmos
Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing.
Documents
zhongkaifu/TensorSharp
Read and write real documents on the device - PDF, XLSX, DOCX, PPTX and CSV.
Markdown Exporter
bowenliang123/markdown-exporter
Convert Markdown text to DOCX, PPTX, XLSX, PDF, PNG, SVG, HTML, IPYNB, MD, CSV, JSON, JSONL, XML files, and extract code blocks in Markdown to Python, Bash,JS and etc files.
Related
Categories
Questions about MinerU Document Reader
What does MinerU Document Reader do?
Reads, OCRs, searches and cites local documents through the mineru CLI, covering PDF, images, Office files, EPUB, HTML and CSV. MinerU is a command-line document reader for agents, and the skill tells the agent to prefer it over generic PDF parsers and OCR libraries for supported formats. It parses local documents into readable content, lets the agent continue by page or block instead of loading a whole file, and returns stable locators in a doc, tier, page and block form for follow-up reads and citations.
When should I use MinerU Document Reader?
MinerU Document Reader fits situations like: reading or summarizing a local PDF, Word, PowerPoint or Excel file; running OCR on scanned PDFs or document images; working through a long document page by page with stable citations; converting document content into Markdown for analysis.
How do I install MinerU Document Reader in Claude Code?
Run `npx skills add opendatalab/MinerU --skill mineru -a claude-code`. Or copy the skill folder (skills/mineru in opendatalab/MinerU) into .claude/skills/mineru in your project. Claude Code loads it when a task matches its description.
How do I install MinerU Document Reader in Codex?
Run `npx skills add opendatalab/MinerU --skill mineru -a codex`. Or copy the skill folder (skills/mineru in opendatalab/MinerU) into .agents/skills/mineru in your project. Codex loads it when a task matches its description.
Can I use MinerU Document Reader in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add opendatalab/MinerU --skill mineru -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mineru, .gemini/skills/mineru, .github/skills/mineru and .opencode/skills/mineru in your project.
What does MinerU Document Reader need to run?
Going by SKILL.md and its folder, MinerU Document Reader needs the command-line tools its instructions call (uv, pipx, pip and python) and credentials named MINERU_API_KEY. Our summary lists: The mineru command-line tool.
Does MinerU Document Reader access the network?
SKILL.md contains no URLs. Its commands use uv and pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is MinerU Document Reader safe to install?
Our automated static check of SKILL.md flagged 1 warning(s): contains instruction-override wording (e.g. “without asking the user”). Read the flagged lines before installing; the check is not a guarantee either way.
What licence does MinerU Document Reader use?
MinerU Document Reader has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does MinerU Document Reader use?
About 9.4k tokens (SKILL.md is roughly 38k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to MinerU Document Reader?
Skills that share tags, products or a category with MinerU Document Reader: Document Converter (wentorai/Research-Claw, 858 stars), To Markdown (Mathews-Tom/armory, 328 stars), Markitdown (ImCa0/just-laws, 782 stars) and Markitdown (jimmc414/Kosmos, 595 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains MinerU Document Reader?
opendatalab (a GitHub organization) maintains it in opendatalab/MinerU, which has 81,321 GitHub stars. The repository was last updated on October 9, 2026.
Source: opendatalab/MinerU on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.