CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

paperbanana

Generate publication-quality academic diagrams from paper methodology text

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 strong, self-contained CLI skill reference: fully executable commands, a complete parameter table, a realistic worked example, and honest runtime expectations. Remaining room is minor — trimming the About/provenance section and adding brief error-recovery notes. No bundle files exist, and none are required for this scope.

DimensionReasoningScore

Conciseness

The body is efficient: a dense parameter table, concrete install/export/run commands, and no explanations of concepts Claude already knows. Minor trimmable content remains — the intro paragraph restates the frontmatter description and the About section (~10 lines of framework provenance and citation) is non-operational — so it does not reach lean/every-token-earns-its-place (5) but is above mostly-efficient-with-clear-slack (3).

4 / 5

Actionability

Setup ("uv pip install -r requirements.txt", "export OPENROUTER_API_KEY=..."), the full run command with every flag documented in a table, and a complete copy-paste-ready worked example with realistic method text make the guidance fully executable; the single example covers the only task type (diagram), so there are no meaningful gaps.

5 / 5

Workflow Clarity

The sequence (install → set API key → run → read output paths from stdout) is clear, with runtime expectations stated ("3-10 minutes per candidate", "~10-30 minutes total"). Minor gaps keep it from 5: no troubleshooting or error-recovery guidance (e.g., what happens with a missing API key or failed image generation), though the operation is not destructive or batch-risky so no cap applies.

4 / 5

Progressive Disclosure

A single well-organized SKILL.md with clear sections (Environment Setup, Usage, Parameters, Output, Examples, Important Notes) and no nested or buried references; no bundle files exist and none are strictly needed. Minor gap: the non-operational About/provenance section and detailed model-configuration notes could live in a separate reference file, which keeps it from 5.

4 / 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 states a concrete, single-sentence capability but omits any "when to use" trigger guidance and lacks natural synonym terms like figures or method section. It is fairly distinctive for the academic-diagramming niche. Adding an explicit trigger clause and richer synonyms would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to turn a paper's method section or figure caption into a publication-ready diagram or pipeline figure (e.g., for NeurIPS/ICML/ACL camera-ready submissions)."

Include natural synonyms users would actually say: "figures", "pipeline figures", "illustrations", "method section", "figure caption".

Mention the output (PNG image files) and multi-candidate generation to broaden the concrete actions listed, improving specificity.

DimensionReasoningScore

Specificity

"Generate publication-quality academic diagrams from paper methodology text" names the domain and one concrete action (generate diagrams), matching the 1-2 concrete actions anchor; it does not list several specific actions such as rendering pipeline figures or producing multiple candidates, so it is not a 4.

3 / 5

Completeness

The description has a clear "what" (generate publication-quality academic diagrams from methodology text) but no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines; it is above 2 because the "what" is concrete, not vague.

3 / 5

Trigger Term Quality

"academic diagrams", "publication-quality", and "paper methodology" are relevant keywords, but common variations users would naturally say are missing ("figures", "illustrations", "method section", "pipeline figure"), matching the some-keywords-but-missing-synonyms anchor rather than good coverage.

3 / 5

Distinctiveness Conflict Risk

The niche (publication-quality academic diagrams from paper methodology) is mostly distinct with only minor overlap risk against generic diagramming/visualization skills; it lacks the distinct explicit triggers needed for a 5.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

Reviewed

Table of Contents

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.