markitdown

Convert local documents to Markdown using Microsoft's markitdown CLI. Best for: PDF, Word, Excel, PowerPoint, images (OCR), audio. Can fetch URLs but Jina is faster for web. Triggers on: convert to markdown, read PDF, parse document, extract text from, docx, xlsx, pptx, OCR image, local file.

2.37x

Quality

88%

Does it follow best practices?

Impact

83%

2.37x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Discovery

100%

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

This is an excellent skill description that covers all key dimensions well. It specifies the tool, concrete actions, supported file types, comparative guidance (vs Jina), and explicit trigger terms. The description is concise yet comprehensive, making it easy for Claude to select this skill appropriately from a large pool.

Dimension	Reasoning	Score
Specificity	Lists concrete actions ('Convert local documents to Markdown') and specifies the tool ('Microsoft's markitdown CLI'), supported formats (PDF, Word, Excel, PowerPoint, images, audio), and even notes a comparative capability ('Can fetch URLs but Jina is faster for web').	3 / 3
Completeness	Clearly answers 'what' (convert local documents to Markdown using markitdown CLI, supporting multiple formats) and 'when' (explicit 'Triggers on:' clause with specific trigger terms, plus 'Best for:' guidance on file types).	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms: 'convert to markdown', 'read PDF', 'parse document', 'extract text from', 'docx', 'xlsx', 'pptx', 'OCR image', 'local file'. These are terms users would naturally use when needing this skill.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive by specifying the exact tool (markitdown CLI), focusing on local document conversion to Markdown, and even differentiating from a competing skill (Jina for web URLs). This makes it very unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Implementation

77%

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

This is a solid, actionable skill with clear executable commands and good table-based organization. Its main weakness is redundancy—the 'use Jina for URLs' message appears in at least 4 places, and the Examples section largely duplicates Basic Usage. Trimming the repeated comparisons and merging duplicate sections would make this significantly more token-efficient.

Suggestions

Consolidate the 'When to Use', 'Benchmarked Performance', and 'Comparison with Alternatives' sections into a single decision table to eliminate the repeated Jina/Firecrawl messaging.

Remove the 'Examples' section entirely since it duplicates 'Basic Usage' with nearly identical commands, or merge unique examples into Basic Usage.

Dimension	Reasoning	Score
Conciseness	The content has significant redundancy: the 'When to Use' table, 'Benchmarked Performance' table, and 'Comparison with Alternatives' table all repeat the same Jina-is-faster-for-URLs message multiple times. The 'Examples' section largely duplicates 'Basic Usage'. The supported formats table is useful but some of it (like .txt, .csv pass-through) is low-value. Could be tightened by ~40%.	2 / 3
Actionability	All commands are concrete, executable, and copy-paste ready. The CLI syntax is clear and specific with real file extensions and output redirection examples. No pseudocode or vague instructions.	3 / 3
Workflow Clarity	This is a simple single-command tool, not a multi-step workflow. The single action (run markitdown on a file) is completely unambiguous. No destructive or batch operations require validation checkpoints. Per scoring notes, simple single-purpose skills can score 3.	3 / 3
Progressive Disclosure	The content is well-structured with clear sections and tables, but everything is inline in one file. For a skill of this length (~80 lines of content), some of the reference tables (supported formats, benchmarks, comparisons) could be separated or omitted. No external references are provided. However, the redundancy across sections hurts organization.	2 / 3
	Total	10 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: NeverSight/skills_feed
Commit: 9f4534c

Reviewed: 6 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.