markitdown

A document-conversion tool from Microsoft that turns files, images, and web pages into Markdown, a plain-text format with headings and lists. It supports formats including PDF, Word, PowerPoint, Excel, HTML, CSV, JSON, XML, EPUB, ZIP, Outlook, and images.

In plain words
What is it for?
Use it to convert one file, a folder of documents, or supported URLs, and to prepare source material for a knowledge base or language-model workflow.
Why use it?
Information stored in different file formats is harder for language models and text tools to process consistently. Converting it to Markdown preserves useful structure for reading and analysis.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/githubxsy/agent-skills/markitdown
Any agent
npx skills add GitHubxsy/agent-skills --skill markitdown
Clone the repo
git clone --depth 1 https://github.com/GitHubxsy/agent-skills

Made for: Claude Code, Codex.

Per session 206 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,775 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00206 $0.01775
Opus 5 $0.00103 $0.00888
Sonnet 5 $0.00041 $0.00355
Haiku 4.5 $0.00021 $0.00178

Measured 2d ago against content hash 7d733eb658c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

markitdown 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/convert.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/markitdown/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MarkItDown

Convert source material into Markdown optimized for language-model and text-analysis workflows. Preserve useful structure such as headings, lists, tables, links, and metadata; do not promise page-faithful visual reproduction.

Choose a workflow

  • Convert one local file or supported URL: use the markitdown CLI.
  • Convert several local files reproducibly: use scripts/convert.py.
  • Integrate conversion into an application or pass streams: use the Python API.
  • Read standalone images or images embedded in PPTX, DOCX, PDF, or XLSX: run the bundled script with an OpenAI-compatible vision model.
  • Reject audio and video inputs; this Skill does not transcribe them.

Install safely

Require Python 3.10 or newer. Prefer an isolated environment:

python3 -m venv .venv
source .venv/bin/activate
python -m pip install 'markitdown[pdf,docx,pptx,xlsx,xls,outlook]' markitdown-ocr openai

Install only required extras when dependency size matters, for example:

python -m pip install 'markitdown[pdf,docx,pptx,xlsx]'

Do not install markitdown[all] for this Skill because it includes audio-transcription dependencies. Install only the document extras required by the task.

Do not alter a user's project environment without permission. Reuse an existing compatible environment when present; otherwise explain or create an isolated one within the task scope.

Convert content

For one input:

markitdown report.pdf -o report.md
markitdown https://example.com/page -o page.md
cat report.pdf | markitdown > report.md

For multiple local inputs, run:

python scripts/convert.py file.pdf slides.pptx notes.docx --output-dir markdown
python scripts/convert.py source-folder --output-dir markdown

The script recursively converts directories and preserves their relative structure. It preserves each source extension in the output name (file.pdf.md) to avoid collisions. Add --overwrite only when replacing existing outputs is intended.

Read the full file on GitHub · 159 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 159 lines · 206 tokens per session scan A 7d733eb658c5

Subscribe to this mod's changes

markitdown is a skill published in the GitHub repository GitHubxsy/agent-skills (21 stars, last pushed 4d ago), licensed Apache-2.0. It adds 206 tokens to every session and 1,775 once invoked, about $0.0010 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens