paper-image-extractor

Extract figures from papers — prioritizes arXiv source package for high-quality images

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/paper-image-extractor/SKILL.md

Quality

Content

80%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 concise, well-structured, and actionable with a real backing script, but it lacks validation/verification checkpoints for what is a batch extraction operation, capping workflow clarity. Adding a verify step and the specific PDF-to-PNG command would lift the two lower dimensions.

Suggestions

Add a verification checkpoint after extraction, e.g. 'Verify expected image count and that files are non-empty before generating index.md.'

Provide the concrete command for Priority 1 step 4 ('Convert PDF figures to PNG') instead of leaving it as a bare instruction.

Add an error-recovery note for failed arXiv downloads (e.g. retry, then fall through to Priority 2) to introduce the feedback loop the batch workflow currently lacks.

Dimension	Reasoning	Score
Conciseness	The body is lean — short numbered tiers, one bash command, tight bullet lists — with no over-explanation of concepts Claude already knows; every line earns its place, matching the lean-and-efficient anchor.	5 / 5
Actionability	It provides concrete executable guidance (the e-print URL, the extract_images.py invocation, named image directories) backed by a real bundle script, but Priority 1 step 4 ('Convert PDF figures to PNG') lacks the specific command, leaving a minor gap that sits just below the fully copy-paste-ready anchor.	4 / 5
Workflow Clarity	The 3-tier fallback sequence is clearly ordered, but this is a batch operation (downloading packages, extracting all figures) with no validation or verification checkpoints and no error-recovery loop, so per the guidelines workflow clarity is capped at 3.	3 / 5
Progressive Disclosure	This is a sub-50-line single-purpose skill with well-organized sections (Goal, Strategy, Output, Scripts, Dependencies) and a single one-level-deep script reference that exists in the bundle, matching the simple-skill exception for a top score.	5 / 5
	Total	17 / 20 Passed

Description

53%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 concrete and distinct but lacks a "when to use" trigger clause, which caps its completeness. Adding a Use-when clause with natural user phrasings and file extensions would lift the trigger-term and completeness scores.

Suggestions

Add a 'Use when...' clause naming concrete triggers, e.g. 'Use when the user asks to extract figures, images, or plots from arXiv papers or PDFs.'

Include natural synonyms and file extensions users say ('figures', 'plots', 'images', 'arXiv', '.pdf') to improve trigger-term coverage.

Mention the PDF fallback briefly in the description so the what-coverage is more comprehensive.

Dimension	Reasoning	Score
Specificity	The description names the domain and two concrete actions — "Extract figures from papers" and "prioritizes arXiv source package for high-quality images" — but coverage is not comprehensive (no mention of PDF fallback or conversion), matching the anchor that lists 1-2 concrete actions.	3 / 5
Completeness	It clearly states the "what" (extract figures from papers, prioritizing arXiv source) but provides no "Use when..." trigger guidance, so per the guidelines the missing when-clause caps completeness at 3.	3 / 5
Trigger Term Quality	It includes relevant keywords ("figures", "papers", "arXiv") but misses the natural phrases a user would actually say (e.g. "get images from a paper", "extract figures", file extensions like .pdf), matching the anchor with some relevant keywords but missing common variations.	3 / 5
Distinctiveness Conflict Risk	The arXiv-source-package framing carves out a distinct niche with only minor overlap risk against generic PDF-extraction skills, matching the "mostly distinct; minor overlap risk" anchor; it is not generic enough for 3 nor fully conflict-free for 5.	4 / 5
	Total	13 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/paper-image-extractor/SKILL.md
Commit: 4b35756

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.