pdf-markdown-validator

Validate PDF to Markdown conversion quality using multi-dimensional metrics. Assess table accuracy, style preservation (bold/italic/headings), robustness, and performance with standardized F1-scoring methodology.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/pdf-markdown-validator/SKILL.md

Quality

Content

65%

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 with concrete commands and complete examples, but it is verbose for a single SKILL.md and keeps material inline that would benefit from being split into reference files, with implicit rather than explicit validation checkpoints in its workflow.

Suggestions

Split inline reference material (ground-truth annotation format, full CI YAML, metric definitions, troubleshooting) into separate reference files and link to them with clearly signaled 'See X for Y' pointers to improve progressive disclosure.

Add an explicit validation checkpoint to the validation workflow (e.g. a bolded 'Validate output passes --fail-below 75 before iterating') to satisfy the batch-operation feedback-loop requirement.

Trim sections that re-explain concepts Claude already knows — notably the Markdown-syntax primer in 'Ground-Truth Annotation Format' and the generic 'Best Practices' lists — to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The ~700-line body is mostly efficient (formulas, interpretation bands, concrete CLI commands earn their place) but pads sections Claude already knows, such as the 'Ground-Truth Annotation Format' teaching standard Markdown syntax and generic 'Best Practices' advice.	2 / 3
Actionability	Provides fully executable, copy-paste-ready guidance: exact 'cargo run' and 'python3 scripts/validate.py' invocations with full flags, a complete GitHub Actions YAML, and concrete jq queries against the JSON report.	3 / 3
Workflow Clarity	The 'Workflow: Running a Full Validation' section sequences five steps, but for a batch-corpus operation it lacks explicit validate→fix→retry checkpoints (no bolded 'validate, only then proceed' gate within the steps), which caps workflow clarity at 2 per the rubric.	2 / 3
Progressive Disclosure	Real bundle scripts exist and are referenced, but the body is largely monolithic: full ground-truth format, CI YAML, metric definitions, troubleshooting, and best practices are inline rather than split into one-level-deep reference files with clearly signaled navigation.	2 / 3
	Total	9 / 12 Passed

Description

82%

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, technical, and well-differentiated, but it omits an explicit 'Use when...' trigger clause, which caps its completeness at 2. Adding user-facing trigger phrasing would lift the weakest dimension.

Suggestions

Append a 'Use when...' clause naming natural user triggers, e.g. 'Use when validating PDF→Markdown conversion quality, benchmarking PDF extractors, or checking conversion fidelity in CI.'

Soften technical jargon like 'standardized F1-scoring methodology' toward language a user would naturally say (e.g. 'scores table and style accuracy').

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Validate PDF to Markdown conversion quality', 'Assess table accuracy, style preservation (bold/italic/headings), robustness, and performance' — matching the anchor for enumerating several specific concrete actions.	3 / 3
Completeness	Clearly states what the skill does but lacks any 'Use when...' clause or equivalent explicit trigger guidance; per the rubric, a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	Uses the natural terms users would say — 'PDF', 'Markdown', 'PDF to Markdown conversion' — alongside specific sub-metric terms, giving good coverage rather than opaque jargon.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche — PDF→Markdown conversion quality validation via F1 metrics — distinct from generic PDF-extraction skills and unlikely to trigger for the wrong skill.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (725 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	13 / 16 Passed

Repository: raphaelmansuy/edgequake
Path: .github/skills/pdf-markdown-validator/SKILL.md
Commit: 62e6adb

Reviewed: 1 day 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.