MarkItDown

TRUSTED · 87
Registry indexed

Convert PDFs, Office documents, and web files into clean markdown for agents.

Downloads 96.0K
Stars 80.0K
Version 1.0.0
Quality 100/100 · Excellent
Trust 87/100 · Production candidate
Audit 94/100 · Safe to try

Supply asset profile

Research and knowledge work

Deep research, source comparison, literature review, RAG, knowledge search, and reports.

Browse track

Scenario

Document processing

I need my agent to read PDFs, extract tables, and turn documents into structured data.

Agent fit

Claude Code + OpenAI Agents + Cursor

Codex, Claude Code, Cursor, CLI, or custom agents.

Install

Ready

npx skills add microsoft/markitdown

Maintenance

fresh

16d since push

Risk

Safe to try

Documentation summary is thin

GitHub quality

80K

100/100 quality · 87/100 trust

Coverage tags

ResearchDocument processingpdfmarkdowndocuments

Review notes

Documentation summary is thin · README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context

Agent adoption scorecard

Trust, audit, and install readiness at a glance

These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.

Quality

Excellent
100

High-confidence pick with strong adoption and healthy maintenance signals.

Trust

Production candidate
87

Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.

Audit

Safe to try
94

Install readiness, security metadata, maintenance, and adoption risk.

Trust Score v2

Agent install candidate

Shortlist for production use, then run a normal repository and dependency review.

CodexClaude CodeCursorOpenAgentSkill CLI

Stars

80K GitHub stars

Maintenance

16d since push

License

MIT

Install

npx skills add microsoft/markitdown

Risk summary

Review before production

  • Documentation summary is thin
  • README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context

Install readiness

Install path available

  • Install path is available
  • Repository evidence is available
  • License is declared
  • 16d since push

Agent safety v2

78/100 · Review before install

Reviewedreview

Good audit and safety signals with no high-risk permission hints in public metadata.

Review the audit page, then allow agent install in a sandboxed workflow.

Resolve via API

medium

Network access

Skill likely fetches remote pages, APIs, repositories, or external services.

medium

Filesystem access

Skill may read or write project files, documents, generated artifacts, or local workspace state.

  • Documentation summary is thin

Install targets

Install this skill in your agent workflow

Copy the registry command or an agent-specific install prompt for Codex, Claude Code, and Cursor.

skill install

OpenAgentSkill CLI

Use the registry command when your workflow supports the OpenAgentSkill installer.

$ npx skills add microsoft/markitdown

Agent resolve plan

Let an agent verify fit before installing.

The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.

Open text plan

Agent should check

  • Task fit and alternatives from Resolve API.
  • Audit score, trust score, and safety policy warnings.
  • Install target compatibility for Codex, Claude Code, Cursor, or CLI.

Copy prompt

Task: Use MarkItDown in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20MarkItDown%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/markitdown/install
Install command: npx skills add microsoft/markitdown
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.

Agent handoff

Give an agent the install path, not another directory page.

Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.

Open install API

Agent prompt

Use MarkItDown for this task. Review https://www.openagentskill.com/api/skills/markitdown/install, then install with: npx skills add microsoft/markitdown

Registry metadata

Agent-readable profile for automatic skill selection.

This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.

Open manifest

Agent fit

100/100

Document processing

Platforms

Codex, Claude Code, Cursor, OpenAI Agents

Audit report

Safe to try · 94/100

Review install readiness, maintenance, trust, quality, and metadata warnings before adding this skill to an agent workflow.

View audit report

Agent decision cockpit

Primary pick for Document processing

Use this as a leading candidate, then validate the README and install path in your own agent stack.

100
Readiness
Adopt
Stage

Role in stack

Primary pick

Primary fit

Document processing

Trust label

Production-ready

Install path

Command ready

Use when

  • Document processing workflows
  • Claude Code teams
  • teams that value GitHub adoption signals

Evidence

  • 80,000 GitHub stars
  • recent repository activity
  • install command or GitHub repo available
  • 100/100 quality profile

Review first

  • No OpenAgentSkill engagement data yet

Implementation path

  1. 1Install it in a sandbox agent and run one Document processing task end to end.
  2. 2Compare output quality, latency, and failure behavior against at least one alternative.
  3. 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.

Trust profile

Production candidate

Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.

87
Trust score

GitHub adoption

PASS

80K GitHub stars

Recent maintenance

PASS

16d since push

License clarity

PASS

MIT

README/SKILL.md completeness

CHECK

Public metadata needs stronger README/SKILL.md context

Good signals

  • AI review approved
  • Install path is available
  • Repository evidence is available
  • Recently maintained repository
  • Large GitHub adoption signal
  • High quality score

Review before install

  • Documentation summary is thin
  • README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context

Recommended action

Shortlist for production use, then run a normal repository and dependency review.

Quality profile

Excellent candidate for agent workflows

High-confidence pick with strong adoption and healthy maintenance signals.

100
GitHub stars
80K
Freshness
16d ago
Install ready
Yes
License
MIT

Workflow fit

Use this skill in these scenarios

Stack fit

Add it to a complete workflow

Overview

Convert PDFs, Office documents, and web files into clean markdown for agents.

Platform Compatibility

codexFULL
claude-codeFULL
cursorFULL

Technical Details

Version
1.0.0
License
MIT
Last Updated
6/1/2026
Published
6/1/2026

Frameworks & Tools

CodexClaude CodeCursor

Decision snapshot

Primary pick

100
Ready
Adopt
Stage

80,000 GitHub stars

Audit Snapshot

Install and adoption review

94
Safe to try
Security
92/100
Maintenance
100/100
Install
92/100
Open full audit

Growth loop

Share this skill

X

Scenario-led draft for MarkItDown, with the OpenAgentSkill Update theme and canonical URL.

OpenAgentSkill Update
Today: MarkItDown

Use it when you need an agent to browse, extract, or monitor web pages without building a scraper from scratch.

80.0K stars - Document Processing
Link: https://www.openagentskill.com/skills/markitdown?ref=x
#AIAgents #OpenAgentSkill
Open X draft
Optional reply with install command
Link for MarkItDown:
https://www.openagentskill.com/skills/markitdown?ref=x

Install: npx skills add microsoft/markitdown

Listing source

Registry indexed

Claimable

This listing was indexed from public sources and is not marked official until a maintainer claim is approved.

Creator
microsoft
Indexed by
OpenAgentSkill community index

Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.

Claim this skill

Owner claim

Claim this skill listing

This registry indexed listing is attributed to microsoft but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.

README badge

Add this badge to your GitHub README to show the listing, trust score, and install handoff.

[![OpenAgentSkill](https://www.openagentskill.com/api/badge/markitdown)](https://www.openagentskill.com/skills/markitdown)

Author

M

microsoft

@microsoft

Health Signals

GitHub stars
80.0K
Quality score
93/100
Last GitHub push
Jun 1, 2026
Framework hints
3
OpenAgentSkill views
0
Install copies
0
Outbound clicks
0

Community Signal

Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.

Trust & Safety

Production candidate

87
  • GitHub adoption80K GitHub starsPASS
  • Recent maintenance16d since pushPASS
  • License clarityMITPASS
  • README/SKILL.md completenessPublic metadata needs stronger README/SKILL.md contextCHECK
  • Dependency riskno major dependency risk hints in public metadataPASS
  • Install availabilitynpx skills add microsoft/markitdownPASS