pdf-extract

Extract PDF selectable text and full-page or segmented page images (including tables) into Markdown with per-page headings and image links; use when you need both readable text and page visuals for PPT creation, review, or analysis.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Other/pdf-extract/SKILL.md

Quality

Content

61%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 content is highly actionable — a complete executable command with thorough flag documentation — and structures implementation appropriately in a real bundled script. Its weakness is conciseness: a large share of the body is generic process/safety boilerplate, and the Recommended Workflow is templated rather than a concrete PDF-specific sequence.

Suggestions

Remove or collapse the generic boilerplate sections (When Not to Use, Required Inputs, Output Contract, Validation and Safety Rules, Failure Handling, Deterministic Output Rules, Completion Checklist) since they state process guidance Claude already applies; keep only PDF-specific notes.

Replace the templated Recommended Workflow with a concrete PDF-specific sequence (run extract_pdf.py with chosen flags, check output.md has expected ## Page XX sections, verify image-dir populated) with explicit checkpoints.

Add an explicit one-line pointer to scripts/extract_pdf.py (e.g., "See scripts/extract_pdf.py for full implementation") so the progressive-disclosure reference is clearly signaled rather than only embedded in commands.

Dimension	Reasoning	Score
Conciseness	Roughly 8 of the sections (When Not to Use, Required Inputs, Recommended Workflow, Output Contract, Validation and Safety Rules, Failure Handling, Deterministic Output Rules, Completion Checklist) are generic process/safety boilerplate Claude already applies, adding tokens without PDF-specific knowledge. This is several unnecessary padded sections; not a 3 because the document is not "mostly efficient" given the volume of boilerplate; not a 1 because the PDF-specific sections are terse and do not over-explain concepts.	2 / 5
Actionability	Provides a fully executable, copy-paste-ready command with every flag ("--input input.pdf --output output.md --image-mode segment --filter-text on ...") plus per-flag explanations in Implementation Details. Covers the common cases concretely; not a 4 because there are no meaningful gaps in the example.	5 / 5
Workflow Clarity	The documented "Recommended Workflow" is 4 generic template steps ("Validate the request… Select the documented execution path…") with no concrete commands or checkpoints, while the real execution lives separately in Example Usage. A --help pre-check and generic Completion Checklist exist, so validation is not absent, but the sequence lacks explicit PDF-specific checkpoints. Not a 4 because the workflow is generic rather than a clear concrete sequence; not a 2 because some validation is present.	3 / 5
Progressive Disclosure	Overview and usage live in SKILL.md while implementation detail is delegated to the real bundle file scripts/extract_pdf.py (referenced via the executable commands), a one-level-deep split with clear section headers for navigation. Not a 5 because the script reference is embedded in commands rather than explicitly signaled (e.g., "see scripts/extract_pdf.py"), and detailed flag behavior is inlined rather than separated.	4 / 5
	Total	14 / 20 Passed

Description

92%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, complete, and distinctive, with an explicit use-when clause and concrete actions. Its main gap is trigger-term breadth: it uses "PDF" but omits common synonyms and the .pdf extension.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Extract PDF selectable text and full-page or segmented page images (including tables) into Markdown with per-page headings and image links" — covering text extraction, multiple image modes, tables, and Markdown structuring comprehensively. Not a 4 because coverage is broad and domain-specific rather than having only minor gaps.	5 / 5
Completeness	Explicitly answers both what (extract text/images into Markdown with headings and links) and when ("use when you need both readable text and page visuals for PPT creation, review, or analysis") with concrete trigger phrases. Matches the 5 anchor's pattern exactly; not a 4 because the when-clause is explicit and concrete rather than weakly implied.	5 / 5
Trigger Term Quality	Good keyword coverage with "PDF", "Markdown", "page visuals", and "PPT creation, review, or analysis", but misses common synonyms/extensions like "PDFs", ".pdf", or "PDF to Markdown". Not a 5 because it lacks the synonym and file-extension breadth the 5 anchor requires; not a 3 because it goes well beyond a single generic keyword.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — PDF text-plus-page-visual extraction into Markdown for PPT/review — with triggers unlikely to fire for unrelated skills. Not a 4 because the combined text+visuals-to-Markdown capability is distinctly scoped rather than having notable overlap with sibling skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Other/pdf-extract/SKILL.md
Commit: 63c61d3

Reviewed: 9 hours 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.