Agent skill

Markitdown

by jimmc414 in jimmc414/Kosmos

Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing.

No licenceAuto-check passedDocuments & Office

Install Markitdown

skills CLI
$ npx skills add jimmc414/Kosmos --skill markitdown -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jimmc414/Kosmos markitdown --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jimmc414/Kosmos.git skills-src && mkdir -p .claude/skills && cp -r skills-src/kosmos-claude-scientific-skills/scientific-skills/markitdown .claude/skills/markitdown && rm -rf skills-src

Use ~/.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/

Facts

Skill name
markitdown
GitHub stars
594
Used in
2 other repos
Token cost
~1.7k tokens
SKILL.md length
459 words
Files
7 (incl. scripts, references)
Skills in repo
6
Repo updated
First seen
Licence
None found

At a glance

Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing.

  • Works in 6 steps: Document Conversion → Media Processing → Web Content Extraction → …
  • Converting documents to markdown
  • SKILL.md covers Overview, When to Use This Skill, Core Capabilities and Installation, plus 4 more sections
  • Runs Python scripts from its folder; calls uv, markitdown and python; reaches youtube.com

What it does

Markitdown is an agent skill from jimmc414/Kosmos. Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing. Use when converting documents to markdown, extracting text from PDFs/Office files, transcribing audio, performing OCR on images, extracting YouTube transcripts, or processing batches of files. Supports 20+ formats including DOCX, XLSX, PPTX, PDF, HTML, EPUB, CSV, JSON, images with OCR, and audio with transcription.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including scripts and reference files (for example `references/advanced_integrations.md`, `references/document_conversion.md` and `references/media_processing.md`).

It sits in Documents & Office, covering Document parsing, Schema markup and Transcription. It works with MarkItDown, Microsoft Excel, Microsoft PowerPoint and Microsoft Word. The repository describes itself as: Kosmos: An AI Scientist for Autonomous Discovery - An implementation and adaptation to be driven by Claude Code or API - Based on the Kosmos AI Paper -….

When your agent uses it

  • Converting documents to markdown
  • Extracting text from PDFs/Office files
  • Transcribing audio
  • Performing OCR on images

Example prompts

  • “/markitdown”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Document Conversion
  2. Media Processing
  3. Web Content Extraction
  4. Structured Data Handling
  5. Advanced Integrations
  6. Batch Processing

What it can do on your machine

Read from SKILL.md and the folder at commit 73f4d2a. 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

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • uv
    • markitdown
    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • youtube.com

    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.

Context cost

Markitdown loads about 1.7k tokens when it runs, and up to ~14k if it reads all its reference files. Until then it costs about 117 tokens; SKILL.md has 459 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~117
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~14k

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); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 459 words (~1,719 tokens).

“MarkItDown is a Python utility that converts various file formats into Markdown format, optimized for use with large language models and text analysis pipelines. It preserves document structure (headings, lists, tables, hyperlinks) while producing clean, token-efficient Markdown output.”

— opening of SKILL.md by jimmc414
name
markitdown

Read the full SKILL.md on GitHub

Files

SKILL.md and 6 other files (scripts, references) in kosmos-claude-scientific-skills/scientific-skills/markitdown of jimmc414/Kosmos.

  • SKILL.md
  • references/advanced_integrations.md
  • references/document_conversion.md
  • references/media_processing.md
  • references/structured_data.md
  • references/web_content.md
  • scripts/batch_convert.py

Open the folder on GitHubat commit 73f4d2a

Used in 2 other repositories

We found 5 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in jimmc414/Kosmos, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Markitdown 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.

Markitdown compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Markitdown this skilljimmc414/Kosmos5942 repos~1.7kAutomated safety check: PassNone
MarkitdownImCa0/just-laws78114 repos~3.2kAutomated safety check: NotesMIT
Markdown Converterintellectronica/agent-skills2954 repos~492Automated safety check: PassCC0-1.0
Document Converterwentorai/Research-Claw858—~1.3kAutomated safety check: PassCustom licence
To MarkdownMathews-Tom/armory327—~2kAutomated safety check: PassMIT
Markdown ConverterTeam-Commonly/commonly1.4k—~557Automated safety check: PassApache-2.0

Similar skills

  • Markitdown

    ImCa0/just-laws

    Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.

    781 GitHub starsUsed in 14 repos~3.2k tokens
    Documents & OfficeAuto-check: notes
  • Markdown Converter

    intellectronica/agent-skills

    Convert documents and files to Markdown using markitdown. An agent skill from intellectronica/agent-skills.

    295 GitHub starsUsed in 4 repos~492 tokens
    Documents & OfficeAuto-check passed
  • Document Converter

    wentorai/Research-Claw

    Convert Office documents (PPTX, DOCX, XLSX, PDF, HTML, CSV, JSON, XML, images) to Markdown using Microsoft MarkItDown.

    858 GitHub stars~1.3k tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed
  • To Markdown

    Mathews-Tom/armory

    Convert any file or URL to clean Markdown: PDF, DOCX, XLSX, PPTX, HTML, images (OCR), audio, CSV, YouTube.

    327 GitHub stars~2k tokensUpdated yesterday
    Documents & OfficeAuto-check passed
  • Markdown Converter

    Team-Commonly/commonly

    Convert binary documents (PDF, DOCX, XLSX, PPTX, HTML, EPUB, images) to clean LLM-friendly Markdown using Microsoft's markitdown Python tool.

    1.4k GitHub stars~557 tokensUpdated today
    Documents & OfficeAuto-check passed
  • Process, convert, OCR, extract, redact, sign, and fill documents using the Nutrient DWS API.

    274k GitHub starsUsed in 4 repos~1.5k tokens
    Documents & OfficeAuto-check passed

More from jimmc414/Kosmos

  • Scholar Evaluation

    jimmc414/Kosmos

    Systematic framework for evaluating scholarly and research work based on the ScholarEval methodology.

    594 GitHub starsUsed in 2 repos~2.5k tokens
    Auto-check passed
  • Reportlab

    jimmc414/Kosmos

    PDF generation toolkit. An agent skill from jimmc414/Kosmos.

    594 GitHub starsUsed in 1 repo~4.2k tokens
    Auto-check passed
  • Scientific Schematics

    jimmc414/Kosmos

    Create publication-quality scientific diagrams, flowcharts, and schematics using Python (graphviz, matplotlib, schemdraw, networkx).

    594 GitHub stars~16k tokensUpdated 3 days ago
    Auto-check: notes
  • Hypothesis Generation

    jimmc414/Kosmos

    Generate testable hypotheses from observations. An agent skill from jimmc414/Kosmos.

    594 GitHub stars~1.7k tokensUpdated 3 days ago
    Auto-check passed
  • Scientific Writing

    jimmc414/Kosmos

    Write scientific manuscripts. An agent skill from jimmc414/Kosmos.

    594 GitHub starsUsed in 1 repo~4.1k tokens
    Auto-check passed

Questions about Markitdown

What does Markitdown do?

Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing. Markitdown is an agent skill from jimmc414/Kosmos. Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing.

When should I use Markitdown?

Markitdown fits situations like: converting documents to markdown; extracting text from PDFs/Office files; transcribing audio; performing OCR on images.

How do I install Markitdown in Claude Code?

Run `npx skills add jimmc414/Kosmos --skill markitdown -a claude-code`. Or copy the skill folder (kosmos-claude-scientific-skills/scientific-skills/markitdown in jimmc414/Kosmos) into .claude/skills/markitdown in your project. Claude Code loads it when a task matches its description.

How do I install Markitdown in Codex?

Run `npx skills add jimmc414/Kosmos --skill markitdown -a codex`. Or copy the skill folder (kosmos-claude-scientific-skills/scientific-skills/markitdown in jimmc414/Kosmos) into .agents/skills/markitdown in your project. Codex loads it when a task matches its description.

Can I use Markitdown 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 jimmc414/Kosmos --skill markitdown -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/markitdown, .gemini/skills/markitdown, .github/skills/markitdown and .opencode/skills/markitdown in your project.

What does Markitdown need to run?

Going by SKILL.md and its folder, Markitdown needs Python for the scripts in its folder and the command-line tools its instructions call (uv, markitdown and python). Our summary lists: Python 3.

Does Markitdown access the network?

SKILL.md names 1 domain. In commands or code: youtube.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Markitdown 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Markitdown use?

No licence was found for Markitdown or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Markitdown use?

About 1.7k tokens (SKILL.md is roughly 6.9k 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 12k tokens, read only when the agent opens those files.

What are the alternatives to Markitdown?

Skills that share tags, products or a category with Markitdown: Markitdown (ImCa0/just-laws, 781 stars), Markdown Converter (intellectronica/agent-skills, 295 stars), Document Converter (wentorai/Research-Claw, 858 stars) and To Markdown (Mathews-Tom/armory, 327 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Markitdown?

jimmc414 (a GitHub user) maintains it in jimmc414/Kosmos, which has 594 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 4, 2026.

Source: jimmc414/Kosmos on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.