convert-documents-to-markdown

Convert Word, PPT, Excel, ODT, RTF, EPUB, CSV, PDF to Markdown. Trigger: office doc you cannot read directly.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

100%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 a tightly written, fully executable reference for a single-purpose CLI: copy-paste commands, explicit exit-code validation, an OCR error-recovery loop, and programmatic alternatives, with no padding and no unnecessary external references.

Dimension	Reasoning	Score
Conciseness	Lean commands with inline comments and no explanations of concepts Claude already knows; every line (Node requirement, exit codes, OCR rerun, API key) earns its place, matching the 5 anchor.	5 / 5
Actionability	Three copy-paste npx commands plus concrete exit codes, an OCR rerun command, and named library packages with their API give fully executable guidance covering the common cases, matching the 5 anchor.	5 / 5
Workflow Clarity	The single CLI action is unambiguous (simple-skill exception) and is reinforced by explicit validation via exit codes 0/1/2/3 and a feedback loop (exit 3 → rerun with --ocr hosted), matching the 5 anchor.	5 / 5
Progressive Disclosure	Under 50 lines with no need for external references and well-organized sections (heading, command block, numbered rules); no bundle files exist to verify, so the simple-skill exception yields a 5.	5 / 5
	Total	20 / 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 concise and clearly communicates a distinct niche with explicit trigger guidance, but it describes only one capability and lacks file-extension/synonym trigger terms that would push specificity and trigger quality higher.

Suggestions

Add file extensions and synonyms to broaden natural triggers, e.g. "Word/PowerPoint/Excel (.docx, .pptx, .xlsx), PDF, …".

Name a second concrete action besides conversion (e.g. extracts text/tables, preserves structure) to lift specificity from one action to several.

Expand the trigger clause to enumerate user phrasings, e.g. "Use when the user gives you a Word/PPT/Excel/PDF you can't read directly."

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ("Convert … to Markdown") across a comprehensive format list, but offers only a single action rather than the multiple specific actions the 4/5 anchors require.	3 / 5
Completeness	Explicitly answers both what (convert listed formats to Markdown) and when ("Trigger: office doc you cannot read directly"), but the trigger is a single terse condition that could be more specific, matching the 4 rather than the 5 anchor.	4 / 5
Trigger Term Quality	Lists natural format terms users actually say ("Word, PPT, Excel, … PDF"), but omits file extensions (e.g. .pdf, .docx) and synonyms (PowerPoint, spreadsheet) that the 5 anchor calls for.	4 / 5
Distinctiveness Conflict Risk	A clear document-to-Markdown niche pinned to a specific format list with a distinct trigger ("office doc you cannot read directly") gives minimal conflict risk, matching the 5 anchor.	5 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: YoizenSA/dev-ai-workflow
Path: ywai/skills/convert-documents-to-markdown/SKILL.md
Commit: 36f5af5

Reviewed: 2 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.