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

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

100%

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 tight, actionable overview that assumes Claude's competence, gives executable commands and code, sequences workflows with validation, and cleanly defers detail to one-level-deep reference files. It is a strong example of the lean skill-body pattern.

Dimension	Reasoning	Score
Conciseness	The body is lean: a two-sentence overview, a decision table, and minimal complete code blocks, with no explanation of concepts Claude already knows. Pinned version numbers appear for reproducibility rather than as padding, and stale patterns are deferred to references/migration.md.	3 / 3
Actionability	It provides fully executable, copy-paste-ready guidance — `uv pip install "markitdown[all]==0.1.6"`, concrete `convert_local()`/`convert_stream()` Python snippets, CLI flags, and bundled script invocations — rather than abstract description.	3 / 3
Workflow Clarity	Multi-step flows are clearly sequenced (Choose the Right Path → Installation → Core Operating Rules → batch → OCR → MCP), and the numbered Quality Checks plus "Do not infer that a successful conversion is complete" provide explicit validation checkpoints for batch and conversion operations.	3 / 3
Progressive Disclosure	SKILL.md acts as an overview pointing to seven real reference files via a "Read when" table, plus inline references to references/workflows.md, references/cloud_and_ocr.md, and references/mcp_and_plugins.md, all one level deep and well-signaled.	3 / 3
	Total	12 / 12 Passed

Description

82%

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, well-keyworded, and distinct, but it lacks an explicit "Use when..." trigger clause, which caps its completeness. Adding a sentence stating when to invoke it would lift the strongest remaining weakness.

Suggestions

Add an explicit trigger clause such as "Use when converting documents or URIs to Markdown for indexing, search, or LLM/RAG ingestion" to satisfy the "when should Claude use it" requirement.

Soften jargon-heavy phrases ("heterogeneous documents", "LLM/RAG ingestion") or pair them with plainer user-facing terms to improve natural trigger matching.

Clarify that this targets MarkItDown specifically rather than generic Markdown tooling to further reduce overlap with other document skills.

Dimension	Reasoning	Score
Specificity	"Convert heterogeneous documents and selected URIs to Markdown" names a concrete action, and the description enumerates many specific capabilities — "safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server" — matching the multiple-specific-actions anchor.	3 / 3
Completeness	It clearly answers what the skill does, but there is no explicit "Use when..." trigger clause; the "when" is only implied via purpose phrases like "for text analysis, search, and LLM/RAG ingestion", which caps completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	It includes natural terms users would say ("documents", "PDF", "Office", "Markdown", "batch workflows", "OCR") alongside the tool name, giving good coverage rather than pure jargon.	3 / 3
Distinctiveness Conflict Risk	Naming "Microsoft MarkItDown" and scoping to document/URI-to-Markdown conversion carves a clear niche unlikely to conflict with adjacent skills.	3 / 3
	Total	11 / 12 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: 757b63b

Reviewed: about 12 hours 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.