Markitdown
aipoch/medical-research-skills
Convert files and Office documents into clean Markdown when you need LLM-friendly, token-efficient text (e.g., for summarization, search, RAG ingestion, or dataset preparation).
Converts PDFs, Office files, HTML, images and other documents into a unified DoclingDocument with Markdown or JSON output, through the docling CLI, Python SDK or a remote service.
Install Docling Document Conversion
$ npx skills add docling-project/docling --skill docling -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install docling-project/docling docling --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/docling-project/docling.git skills-src && mkdir -p .claude/skills && cp -r skills-src/docling/.agents/skills/docling .claude/skills/docling && 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 "docling" agent skill from https://github.com/docling-project/docling/tree/main/docling/.agents/skills/docling into .claude/skills/docling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docling", 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/docling-project/docling/tree/main/docling/.agents/skills/doclingType 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 docling-project/docling --skill docling -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install docling-project/docling docling --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/docling-project/docling.git skills-src && mkdir -p .agents/skills && cp -r skills-src/docling/.agents/skills/docling .agents/skills/docling && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "docling" agent skill from https://github.com/docling-project/docling/tree/main/docling/.agents/skills/docling into .agents/skills/docling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docling", 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 docling-project/docling --skill docling -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install docling-project/docling docling --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/docling-project/docling.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/docling/.agents/skills/docling .cursor/skills/docling && 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 "docling" agent skill from https://github.com/docling-project/docling/tree/main/docling/.agents/skills/docling into .cursor/skills/docling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docling", 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/docling-project/docling.git --path docling/.agents/skills/docling--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 docling-project/docling --skill docling -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install docling-project/docling docling --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/docling-project/docling.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/docling/.agents/skills/docling .gemini/skills/docling && 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 "docling" agent skill from https://github.com/docling-project/docling/tree/main/docling/.agents/skills/docling into .gemini/skills/docling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docling", 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 docling-project/docling doclingInstalls 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 docling-project/docling --skill docling -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/docling-project/docling.git skills-src && mkdir -p .github/skills && cp -r skills-src/docling/.agents/skills/docling .github/skills/docling && 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 "docling" agent skill from https://github.com/docling-project/docling/tree/main/docling/.agents/skills/docling into .github/skills/docling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docling", 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 docling-project/docling --skill docling -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install docling-project/docling docling --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/docling-project/docling.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/docling/.agents/skills/docling .opencode/skills/docling && 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 "docling" agent skill from https://github.com/docling-project/docling/tree/main/docling/.agents/skills/docling into .opencode/skills/docling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docling", 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
docling- GitHub stars
- 68k
- Token cost
- ~1.1k tokens
- SKILL.md length
- 381 words
- Files
- 7 (incl. references)
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- MIT
At a glance
Converts PDFs, Office files, HTML, images and other documents into a unified DoclingDocument with Markdown or JSON output, through the docling CLI, Python SDK or a remote service.
- Reading a PDF or scanned document you cannot open directly
- SKILL.md covers The fastest thing that works:…, Choosing how to use Docling, Running without installing (uvx) and Output conventions
- Calls uvx
- Converting a document to Markdown or JSON
What it does
Docling turns documents such as PDF (born-digital or scanned), DOCX, PPTX, XLSX, HTML, Markdown, AsciiDoc, CSV, images, audio and XML into one DoclingDocument that can be exported as readable Markdown or structured, lossless JSON. Scanned PDFs are handled through OCR or a vision-language model. The quickest route is the docling CLI, which takes a local path or a URL and writes an output file named after the input, and that covers most requests about what a file contains.
A routing table picks the tool by need. The CLI suits one-off local reads. The Python SDK, built on DocumentConverter and PipelineOptions, suits custom pipelines, batch work, speech recognition, image and table export, and embedding in an app. DocumentExtractor, marked beta, pulls typed fields out of a document, and chunking with framework loaders feeds RAG indexes. A Service Client calls a self-hosted or managed docling-serve endpoint for scalable conversion without local ML dependencies or a GPU, and docling-slim extras install only what you use.
Six reference files cover the CLI, extraction, the Python SDK, RAG, the service client and slim packaging. Python 3.10 or newer is required, and the allowed tools cover the docling command, python, uv, uvx and pip.
When your agent uses it
- Reading a PDF or scanned document you cannot open directly
- Converting a document to Markdown or JSON
- Extracting tables or specific fields from a file
- Chunking documents for a RAG index
- Offloading conversion to a docling-serve service
Example prompts
- “Convert report.pdf to Markdown and tell me what it covers.”
- “Extract the tables from this scanned invoice using OCR.”
- “Chunk the PDFs in ./papers for a RAG index and show me the first few chunks.”
Requirements
- Python 3.10 or newer
- The docling package
- Compatibility (from SKILL.md): Requires Python 3.10+
- Pre-approved tools (allowed-tools): Bash(docling:*), Bash(docling-tools:*), Bash(python3:*), Bash(python:*), Bash(uvx:*), Bash(uv:*), Bash(pip:*)
What it can do on your machine
Read from SKILL.md and the folder at commit ef6ba52. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
Bash(docling:*)Bash(docling-tools:*)Bash(python3:*)Bash(python:*)Bash(uvx:*)Bash(uv:*)Bash(pip:*)
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
uvx
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uvx, 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 no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Compatibility
Requires Python 3.10+
From compatibility in the SKILL.md frontmatter.
Context cost
Docling Document Conversion loads about 1.1k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 187 tokens; SKILL.md has 381 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 passed
The automated check found no risky patterns in SKILL.md.
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
The full file from docling-project/docling at commit ef6ba52, republished under its MIT licence (© docling-project). 381 words, ~1,116 tokens.
Download SKILL.mdSave it as
.claude/skills/docling/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.- name
- docling
- description
- Use Docling to understand the content of documents in any supported format — PDF (born-digital or scanned), DOCX, PPTX, XLSX, HTML, Markdown, AsciiDoc, CSV, images, audio, and XML — by converting them into a unified DoclingDocument (Markdown or structured JSON). Use this skill whenever you need to read, parse, convert, extract, or chunk a document you cannot read directly: "what's in this PDF", "convert this to markdown", "extract the tables", "chunk this for RAG", "read this scanned document", "parse this DOCX/PPTX". Covers the `docling` CLI, the Python SDK (DocumentConverter + PipelineOptions), the remote Service Client (self-hosted or managed docling-serve), and the docling-slim install extras for a minimal dependency footprint.
- allowed-tools
- Bash(docling:*), Bash(docling-tools:*), Bash(python3:*), Bash(python:*), Bash(uvx:*), Bash(uv:*), Bash(pip:*)
- compatibility
- Requires Python 3.10+
- license
- MIT
- metadata.author
- docling-project
- metadata.version
- 1.0
- metadata.upstream
- https://github.com/docling-project/docling
Docling
Docling converts documents — PDF, DOCX, PPTX, XLSX, HTML, Markdown, AsciiDoc,
CSV, images, audio, and XML — into a single unified representation, the
DoclingDocument, which you can export as Markdown (human-readable) or
JSON (structured, lossless). Reach for Docling whenever you need to
understand the content of a file you cannot read directly, especially PDFs
(including scanned ones, via OCR or a vision-language model).
The fastest thing that works: the CLI
If you just need to read a document's content, run the CLI. It is installed with
the docling package and accepts a local path or a URL:
docling report.pdf --to md --output /tmp/ # → /tmp/report.md
docling https://example.com/paper.pdf --to json --output /tmp/Output files are named after the input (report.pdf → report.md). Default
output directory is the current directory. This handles the majority of
"what's in this file" requests. See references/cli.md
for pipelines (standard vs VLM vs native), OCR engines, tables, scanned PDFs,
passwords, and every flag.
Choosing how to use Docling
| You need to… | Use | Reference |
|---|---|---|
| Read / convert a file once, from the shell | CLI (docling …) | references/cli.md |
| Convert programmatically, tune the pipeline, batch, ASR, export images/tables | Python SDK (DocumentConverter + PipelineOptions) | references/python-sdk.md |
| Pull specific typed fields out of a document (not the whole doc) | DocumentExtractor (structured extraction, beta) | references/extraction.md |
| Chunk documents for retrieval / feed a RAG index | Chunking + framework loaders | references/rag.md |
| Offload conversion to a remote service — low latency, scalable, no local ML deps or GPU | Service Client (self-hosted or managed docling-serve) | references/service-client.md |
| Install only the dependencies you actually use | docling-slim extras | references/slim-packaging.md |
Show full SKILL.md (145 more words)Show less
Rules of thumb:
- Local, one-off, no code → CLI.
- Custom pipeline, chunking, structure analysis, embedding in an app → Python SDK.
- Many documents, low-latency, no GPU/ML install to manage, scale on demand
→ Service Client against a
docling-serveendpoint (self-hosted or the managed Docling for IBM watsonx service). - Minimize install size / avoid pulling torch and OCR engines you don't need → docling-slim with targeted extras.
Running without installing (uvx)
You can run the CLI without a persistent install:
uvx --from docling docling report.pdf --to md --output /tmp/Output conventions
- Always report the conversion status and (for PDFs) the page count.
- If the user does not specify a format, ask whether they want Markdown (readable) or JSON / DoclingDocument (structured, lossless).
- For tables, prefer
export_to_markdown()/export_to_dataframe()on the table item (Python) — see references/python-sdk.md. - If a converted PDF comes back near-empty, repeated, or full of
�, the source is likely scanned or complex layout — retry with OCR or--pipeline vlm(see references/cli.md).
© docling-project, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 6 other files (references) in docling/.agents/skills/docling of docling-project/docling.
- SKILL.md
- references/cli.md
- references/extraction.md
- references/python-sdk.md
- references/rag.md
- references/service-client.md
- references/slim-packaging.md
Open the folder on GitHubat commit ef6ba52
Compare with similar skills
Docling Document Conversion 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 |
|---|---|---|---|---|---|---|
| Docling Document Conversion this skilldocling-project/docling | 68k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Markitdownaipoch/medical-research-skills | 2k | — | ~1.3k | Automated safety check: Pass | MIT | |
| PDF Processinganthropics/skills | 180k | 48 repos | ~2k | Automated safety check: Pass | Proprietary | |
| PDF Processing GuideshareAI-lab/learn-claude-code | 78k | 5 repos | ~646 | Automated safety check: Pass | MIT | |
| PDF Processing with PythonHKUDS/DeepTutor | 41k | — | ~2.7k | Automated safety check: Pass | Apache-2.0 | |
| PDF ToolkitTokenRhythm/opensquilla | 7.1k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
PDF Processing
anthropics/skills
Handles everyday PDF jobs in Python and on the command line: extract text and tables, merge, split, rotate, watermark, fill forms, encrypt and OCR.
PDF Processing Guide
shareAI-lab/learn-claude-code
Gives the agent command-line and Python recipes for reading, creating, merging and splitting PDF files, plus tips for large and scanned documents.
PDF Processing with Python
HKUDS/DeepTutor
Reads, extracts from, creates, merges, splits, watermarks, encrypts and fills PDF files with pdfplumber, pypdf and reportlab inside a Python sandbox.
PDF Toolkit
TokenRhythm/opensquilla
Deterministic PDF operations through bundled scripts: extract text and tables, merge files or page ranges, split by range, fill form fields and build PDFs from data.
PDF Toolkit
XiaomiMiMo/MiMo-Code
Reads, transforms, composes and fills PDFs with Python scripts for extraction, merging, watermarking, encryption, OCR and form filling.
More from docling-project/docling
Building Pydantic AI Agents
docling-project/docling
Patterns and tested examples for building agents with Pydantic AI: tools, capabilities, structured output, dependency injection, hooks, YAML specs, streaming and testing.
Dignified Python Standards
docling-project/docling
Applies opinionated production Python conventions chosen by the project's Python version: modern type syntax, pathlib, explicit checks and interface guidance.
Docling Pull Request Review
docling-project/docling
Reviews or re-reviews a Docling pull request in fixed stages, with findings that can be reproduced and an explicit record of every check that was run.
Related
Works with
Categories
Questions about Docling Document Conversion
What does Docling Document Conversion do?
Converts PDFs, Office files, HTML, images and other documents into a unified DoclingDocument with Markdown or JSON output, through the docling CLI, Python SDK or a remote service. Docling turns documents such as PDF (born-digital or scanned), DOCX, PPTX, XLSX, HTML, Markdown, AsciiDoc, CSV, images, audio and XML into one DoclingDocument that can be exported as readable Markdown or structured, lossless JSON. Scanned PDFs are handled through OCR or a vision-language model.
When should I use Docling Document Conversion?
Docling Document Conversion fits situations like: reading a PDF or scanned document you cannot open directly; converting a document to Markdown or JSON; extracting tables or specific fields from a file; chunking documents for a RAG index.
How do I install Docling Document Conversion in Claude Code?
Run `npx skills add docling-project/docling --skill docling -a claude-code`. Or copy the skill folder (docling/.agents/skills/docling in docling-project/docling) into .claude/skills/docling in your project. Claude Code loads it when a task matches its description.
How do I install Docling Document Conversion in Codex?
Run `npx skills add docling-project/docling --skill docling -a codex`. Or copy the skill folder (docling/.agents/skills/docling in docling-project/docling) into .agents/skills/docling in your project. Codex loads it when a task matches its description.
Can I use Docling Document Conversion 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 docling-project/docling --skill docling -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/docling, .gemini/skills/docling, .github/skills/docling and .opencode/skills/docling in your project.
What does Docling Document Conversion need to run?
Going by SKILL.md and its folder, Docling Document Conversion needs the command-line tools its instructions call (uvx). Our summary lists: Python 3.10 or newer; The docling package. Its frontmatter pre-approves these tools: Bash(docling:*), Bash(docling-tools:*), Bash(python3:*), Bash(python:*), Bash(uvx:*), Bash(uv:*), Bash(pip:*). Compatibility (from SKILL.md): Requires Python 3.10+.
Does Docling Document Conversion access the network?
SKILL.md contains no URLs. Its commands use uvx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Docling Document Conversion safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Docling Document Conversion use?
Docling Document Conversion is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Docling Document Conversion use?
About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9.7k tokens, read only when the agent opens those files.
What are the alternatives to Docling Document Conversion?
Skills that share tags, products or a category with Docling Document Conversion: Markitdown (aipoch/medical-research-skills, 2k stars), PDF Processing (anthropics/skills, 180k stars), PDF Processing Guide (shareAI-lab/learn-claude-code, 78k stars) and PDF Processing with Python (HKUDS/DeepTutor, 41k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Docling Document Conversion?
docling-project (a GitHub organization) maintains it in docling-project/docling, which has 68,469 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 6, 2026.
Source: docling-project/docling on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.