markdown-tools
Converts documents to markdown with multi-tool orchestration for best quality. Supports Quick Mode (fast, single tool) and Heavy Mode (best quality, multi-tool merge). Use when converting PDF/DOCX/PPTX files to markdown, extracting images from documents, validating conversion quality, or needing LLM-optimized document output.
92
93%
Does it follow best practices?
Impact
84%
7.63xAverage score across 3 eval scenarios
Passed
No known issues
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 a strong skill description that excels across all dimensions. It provides specific capabilities with two distinct modes, includes natural trigger terms covering common file types, has an explicit 'Use when' clause with multiple scenarios, and carves out a clear niche around document-to-markdown conversion with quality validation.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'Converts documents to markdown', 'multi-tool orchestration', 'Quick Mode (fast, single tool)', 'Heavy Mode (best quality, multi-tool merge)', 'extracting images', 'validating conversion quality'. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Converts documents to markdown with multi-tool orchestration') and when ('Use when converting PDF/DOCX/PPTX files to markdown, extracting images from documents, validating conversion quality, or needing LLM-optimized document output'). Explicit 'Use when' clause with multiple trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'PDF', 'DOCX', 'PPTX', 'markdown', 'converting', 'extracting images', 'document output'. Good coverage of file types and common conversion terminology. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on document-to-markdown conversion with specific file types (PDF/DOCX/PPTX) and unique features (Quick Mode vs Heavy Mode, multi-tool orchestration, LLM-optimized output). Unlikely to conflict with generic document or code skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill with excellent conciseness and actionability. The dual-mode architecture is clearly explained with practical tables and executable commands. The main weakness is that validation steps aren't integrated into the conversion workflow as explicit checkpoints, which is important for document conversion operations that can fail silently.
Suggestions
Integrate validation as an explicit step in the Basic Conversion workflow (e.g., 'After conversion, validate: uv run scripts/validate_output.py ... If quality metrics fail, retry with Heavy Mode')
Add a feedback loop to the Heavy Mode Workflow section showing what to do when merge quality is insufficient
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, using tables for quick reference and avoiding explanations of concepts Claude already knows. Every section provides actionable information without padding. | 3 / 3 |
Actionability | Provides fully executable bash commands and clear installation steps. Commands are copy-paste ready with specific flags and options documented in context. | 3 / 3 |
Workflow Clarity | Heavy Mode workflow is explained with clear steps, but lacks explicit validation checkpoints and feedback loops. The quality validation section exists but isn't integrated into the conversion workflow as a mandatory step. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections, tables for quick scanning, and appropriate references to detailed documentation (heavy-mode-guide.md, tool-comparison.md, conversion-examples.md) that are one level deep. | 3 / 3 |
Total | 11 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- fernandezbaptiste/claude-code-skills
- Commit
4f0eae8
- 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.