CtrlK
BlogDocsLog inGet started
Tessl Logo

markitdown

Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more.

55

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

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

Quality

Content

53%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 highly actionable and reasonably well-structured with genuine reference files, but it is verbose, includes a major off-topic schematics tangent, and lacks validation feedback loops for its batch workflows. Trimming padding and adding verify steps would address the lowest dimensions.

Suggestions

Remove or relocate the 'Visual Enhancement with Scientific Schematics' section; it promotes a different skill and references scripts/generate_schematic.py which is not in the bundle.

Add a validation/verification checkpoint to the batch conversion examples (e.g. assert each output .md is non-empty and re-run on failure) to lift workflow clarity above 3.

Move the six near-identical 'Common Use Cases' code recipes into assets/example_usage.md (already present but never referenced) to reduce inlined redundancy.

DimensionReasoningScore

Conciseness

The ~480-line body is noticeably verbose: it re-derives concepts Claude already knows ('Markdown is token-efficient and well-understood by modern language models'), restates obvious performance notes, and includes a large off-topic 'Visual Enhancement with Scientific Schematics' tangent referencing a non-existent script.

2 / 5

Actionability

Mostly executable pip/CLI/Python examples that are copy-paste ready and cover common cases; minor gaps from placeholder values (api keys, VIDEO_ID) and a schematics command pointing to a missing script.

4 / 5

Workflow Clarity

Steps exist as use-case recipes but lack explicit validation checkpoints; because batch conversion is covered, the missing verify/feedback loop caps workflow clarity at 3 per the rubric.

3 / 5

Progressive Disclosure

Good structure with a 'Next Steps' section signaling real one-level-deep references (api_reference.md, file_formats.md, batch_convert.py, convert_with_ai.py); minor gaps from heavy inlined code and an unreferenced assets/example_usage.md.

4 / 5

Total

13

/

20

Passed

Description

73%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 trigger-term rich with broad format coverage, but it omits any explicit 'Use when' trigger guidance, which caps completeness. It is largely distinct and unlikely to misfire, though a 'when to use' clause would lift the weakest dimension.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when converting PDFs, Word, Excel, PowerPoint, images, audio, or web content into Markdown for LLM processing.'

Pair format extensions with natural synonyms (e.g. DOCX/Word, XLSX/Excel, PPTX/PowerPoint) so the trigger matches how users phrase requests.

DimensionReasoningScore

Specificity

Names the domain ('Convert files and office documents to Markdown') and lists several concrete capabilities (OCR for images, transcription for audio) across many formats, with only minor gaps in enumerating distinct actions.

4 / 5

Completeness

The 'what' is clearly stated (convert files to Markdown, supported formats), but there is no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Comprehensive coverage of natural terms and file extensions users would say: 'PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs'.

5 / 5

Distinctiveness Conflict Risk

The file-to-Markdown conversion niche with a distinctive format list is mostly distinct, with only minor overlap risk against general document/file skills.

4 / 5

Total

16

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository
foryourhealth111-pixel/Vibe-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.