paperbanana

Generate publication-quality academic diagrams from paper methodology text

Quality

63%

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 ./skill/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is strong on actionability and workflow clarity thanks to executable commands and a clear single-command flow, but loses points for the inline About/citation material and lack of any progressive-disclosure structure. Tightening the non-operational prose would push it higher.

Suggestions

Move the "About" section (framework description and arXiv citation) into a separate reference file or trim it to one line, keeping SKILL.md focused on execution.

Consider splitting the full parameter table or extended examples into a referenced file and keeping only the quick-start subset inline to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with a clean parameter table and runnable commands, but the "About" section (framework description and arXiv citation) and the duplicated pipeline intro add context not needed to execute the skill, so it could be tightened.	2 / 3
Actionability	It provides fully executable bash commands for install, API-key setup, and invocation, plus a concrete worked example and a complete parameter table with defaults — copy-paste ready.	3 / 3
Workflow Clarity	This is effectively a single-action skill (run `skill/run.py`); the setup → set key → run sequence is clear and unambiguous, and the internal pipeline already includes a Critic feedback loop, so the simple-skill carve-out applies.	3 / 3
Progressive Disclosure	The file is well-organized into labeled sections with no nested references, but it is a single monolithic SKILL.md over 50 lines with no progressive disclosure to supporting files, and the framework/About content is inline rather than split out.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 states a clear, specific capability but lacks an explicit "Use when" trigger clause and only describes a single action, leaving it at the middle tier across most dimensions. Adding natural trigger terms and a when-to-use clause would raise it substantially.

Suggestions

Append an explicit trigger clause, e.g. ".Use when generating figures or diagrams for an academic paper, or when the user asks for publication-ready illustrations from a methodology section."

Expand the action list to multiple concrete verbs (e.g. "Generate, refine, and layout publication-quality academic diagrams and pipeline figures") to improve specificity.

Add common natural terms users would say ("figures", "illustrations", "paper figures", "pipeline diagrams") for better trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names a concrete action ("Generate ... academic diagrams") and a clear domain ("paper methodology text"), but lists only a single action rather than multiple specific concrete actions, matching the score-2 anchor.	2 / 3
Completeness	It clearly answers what the skill does, but provides no "Use when..." clause or equivalent explicit trigger guidance for when Claude should invoke it, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	It includes relevant natural terms like "academic diagrams" and "paper methodology text" that a user might say, but misses common variations such as "figures", "illustrations", or "pipeline figures", so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	The niche (publication-quality academic diagrams from paper methodology) is fairly specific, but without distinct trigger terms it could still overlap with general diagram or figure-generation skills.	2 / 3
	Total	8 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: dwzhu-pku/PaperBanana
Path: skill/SKILL.md
Commit: 8364555

Reviewed: 5 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.