CtrlK
BlogDocsLog inGet started
Tessl Logo

markdown-converter

Markdown conversion: PDF, Office, HTML, data, OCR, audio, ZIP, YouTube.

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/markdown-converter/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 excellent example of a lean, fully executable reference skill: concrete commands throughout, common cases covered, sensible section organization, and a useful troubleshooting fallback. The only weakness is mild redundancy between Basic Usage and the Examples section.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (no explanation of what a PDF is, no library comparisons), but the Examples section re-demonstrates the '-o' and stdout output patterns already shown in Basic Usage with only the file extension varying — minor redundancy that could be trimmed. This is the anchor-4 'efficient; minor instances that could be trimmed' case, not anchor 5's 'every token earns its place'.

4 / 5

Actionability

Every command shown ('uvx markitdown input.pdf -o output.md', 'cat document | uvx markitdown -x .pdf > output.md') is copy-paste executable, and the examples cover the common cases: document, spreadsheet, presentation, stdin with an extension hint, and the Azure Document Intelligence fallback. No pseudocode or vague directions anywhere.

5 / 5

Workflow Clarity

This is a simple single-purpose skill (~39 non-blank lines) where the single action 'uvx markitdown input.pdf' is unambiguous, satisfying the simple-skill exception. It even includes a decision fallback ('For complex PDFs with poor extraction, use -d with Azure Document Intelligence'). The operation is non-destructive, so the validation cap does not apply.

5 / 5

Progressive Disclosure

The skill is under 50 lines with no need for external references (none exist in the bundle), and the content is organized into well-signaled sections: Basic Usage, Supported Formats, Options, Examples, Notes. Per the scoring notes, this warrants a 5 with just well-organized sections.

5 / 5

Total

19

/

20

Passed

Description

61%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 communicates a clear, specific purpose with good format-level trigger terms, but it entirely lacks a "Use when..." clause, which both caps completeness and weakens trigger guidance. Some enumerated terms ("Office", "data") are category labels rather than the natural words users would say. It is functional but noticeably below the quality of the reference good examples.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when converting PDFs, Word, Excel, PowerPoint, HTML, ZIP archives, audio, or YouTube content to Markdown.'

Replace category labels with natural user terms and file extensions: 'Word/Excel/PowerPoint (.docx, .xlsx, .pptx)' instead of 'Office', and 'CSV/JSON' instead of 'data'.

State the action more concretely as a verb phrase (e.g. 'Converts files to Markdown using markitdown') rather than the noun fragment 'Markdown conversion'.

DimensionReasoningScore

Specificity

The description names one concrete action ("Markdown conversion") plus a list of formats, but does not list several distinct actions like the anchor-4 example ('Extracts text..., fills forms, converts pages'). It goes beyond the bare domain naming of anchor 2 but stops short of anchor 4's multi-action coverage.

3 / 5

Completeness

The "what" is clear (convert files in these formats to Markdown), but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not anchor 2 because the "what" is specific, not vague.

3 / 5

Trigger Term Quality

Phrases like "PDF, Office, HTML, data, OCR, audio, ZIP, YouTube" give good natural-term coverage, but "Office" and "data" are category labels rather than the words users say (Word, Excel, PowerPoint, CSV, .docx, .pdf), and no file extensions appear. Not the comprehensive synonym-plus-extension coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

"Markdown conversion" establishes a clear niche distinct from generic document-extraction skills, and format terms like YouTube/ZIP/OCR are distinctive. Minor overlap risk remains with PDF/Office-format extraction skills that share those trigger terms, keeping it below anchor 5.

4 / 5

Total

14

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
steipete/agent-scripts
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.