markitdown

Convert heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured, highly actionable overview with executable examples, explicit validation checkpoints, and exemplary one-level-deep progressive disclosure into real bundle files. The only minor weakness is slight conciseness loss from embedded version/date information.

Dimension	Reasoning	Score
Conciseness	The body is efficient, table-driven, and assumes Claude's competence, but a few sentences and the in-body version/date ('May 26, 2026', '0.1.6') could be trimmed or moved to a deprecation/migration section.	4 / 5
Actionability	Fully executable, copy-paste-ready CLI commands and Python snippets with complete imports cover the common cases (local file, stream, CLI, batch, MCP).	5 / 5
Workflow Clarity	Multi-step processes are clearly sequenced with explicit validation (install verification, a 5-step Quality Checks checklist, batch overwrite/skip guards) and feedback loops via the troubleshooting table.	5 / 5
Progressive Disclosure	A clear overview with a 'Reference Files' table giving 'Read when' guidance to one-level-deep reference files; all referenced files and scripts were verified to exist and content is appropriately split.	5 / 5
	Total	19 / 20 Passed

Description

71%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, comprehensive, and third-person with a clearly stated 'what', but it omits an explicit 'Use when...' trigger clause, which caps completeness at 3 and limits distinctiveness to 4.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers (e.g., 'Use when converting PDFs, Office files, or HTML to Markdown for analysis, search, or RAG ingestion').

Include common file extensions or synonyms (e.g., .pdf, .docx, .pptx, .xlsx) to broaden natural trigger-term coverage.

Tie the trigger phrasing to user-said phrases like 'convert to Markdown' or 'extract text from documents' to raise distinctiveness and completeness.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete conversion scopes and actions (local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, MCP server), matching the comprehensive-coverage anchor.	5 / 5
Completeness	The 'what' is clear and concrete, but there is no explicit 'Use when...' or equivalent trigger guidance, so completeness is capped at 3 per the rubric.	3 / 5
Trigger Term Quality	Good natural-term coverage (Markdown, PDF, documents, batch, OCR, Azure, LLM/RAG) but lacks some file extensions and synonyms that would push it to comprehensive.	4 / 5
Distinctiveness Conflict Risk	Naming the specific Microsoft MarkItDown tool plus unique features (MCP server, Azure, RAG) makes it mostly distinct with only minor overlap risk against related document skills.	4 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/markitdown/SKILL.md
Commit: 1e5eeff

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.