CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

66

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/markitdown/SKILL.md
SKILL.md
Quality
Evals
Security

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 an efficient, highly actionable overview with executable examples, explicit validation checkpoints, and well-signaled one-level-deep reference files that all exist. Its only real weakness is minor conciseness slack where the routing table and operating rules overlap slightly.

DimensionReasoningScore

Conciseness

Dense and competence-assuming with no 'what is a PDF' filler; the 'Choose the Right Path' table slightly overlaps the Core Operating Rules and a few lines could be trimmed, so it sits below a fully lean 5.

4 / 5

Actionability

Provides copy-paste-ready, fully executable guidance across the common cases: pinned install commands, CLI invocations, complete Python convert_local/convert_stream examples with imports, and batch-script usage with flags.

5 / 5

Workflow Clarity

Clear routing table, numbered Core Operating Rules, an explicit numbered Quality Checks validation sequence, and a Troubleshooting error-recovery table provide explicit checkpoints and feedback for risky batch/external operations.

5 / 5

Progressive Disclosure

The body is a clear overview with a 'Reference Files' table that signals each one-level-deep references/*.md by 'Read when' condition; all referenced files and scripts were verified to exist, with bulk detail appropriately split out.

5 / 5

Total

19

/

20

Passed

Description

66%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 and distinctive, naming the tool and a broad capability surface with good natural trigger terms. Its main weakness is the absence of an explicit 'Use when...' trigger clause, leaving the activation guidance only weakly implied.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when converting local PDFs, Office, HTML, CSV, or EPUB files (or selected URIs) to Markdown for search, text analysis, or LLM/RAG ingestion.'

Include a few concrete file extensions or synonyms (.pdf, .docx, .pptx, 'convert to Markdown') to improve trigger-term coverage for users who name formats directly.

Lead with the most common discrete actions (extract text, preserve structure, batch-convert) before the broad capability list to sharpen specificity.

DimensionReasoningScore

Specificity

Names the tool and enumerates a broad set of concrete capability areas (local conversion, streams, Office/PDF/data, batch, plugins, OCR, Azure, MCP); slightly below 5 because it lists domains rather than discrete discrete actions like extract/fill/merge.

4 / 5

Completeness

A clear 'what' is present but there is no explicit 'Use when...' trigger clause; the 'when' is only weakly implied via 'for text analysis, search, and LLM/RAG ingestion', which caps completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Good natural-term coverage (documents, URIs, Markdown, Office/PDF, batch, plugins, OCR, Azure, MCP, RAG) a user would say; a few synonyms/extensions like .docx or 'convert to markdown' are missing.

4 / 5

Distinctiveness Conflict Risk

Naming the specific tool (Microsoft MarkItDown) plus ecosystem specifics (Azure, MCP) gives a clear niche with only minor overlap risk against closely related conversion skills.

4 / 5

Total

15

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
K-Dense-AI/scientific-agent-skills
Reviewed

Table of Contents

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.