aris-paper-illustration

Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.

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 ./skills/aris-paper-illustration/SKILL.md

Quality

Content

62%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 excels at workflow clarity with a well-sequenced, validated multi-stage pipeline and concrete scripts, but it is heavily padded with redundant restatements and ships as one monolithic file instead of offloading the style guide and templates into referenced files.

Suggestions

Deduplicate the style guidance: state the color palette, arrow standards, and "科研风格" DO/DON'T list once in a single Style Guide section and reference it from the prompt and verification templates instead of repeating each list 3–4 times.

Move the large STRICT review checklist and the Step 1 prompt template into separate reference files (e.g. references/review-checklist.md, references/prompt-template.md) linked one level deep from SKILL.md, turning the body into a concise overview.

Trim emphasis padding ("STRICT!", "CRITICAL", "MUST FOLLOW", repeated Key Rules that restate earlier sections) — Claude responds to a single clear instruction as well as to three emphatic restatements.

Dimension	Reasoning	Score
Conciseness	The ~680-line body restates the same guidance many times — the color palette appears in four places, arrow rules in four-plus places, plus heavy caps/emphasis padding ("STRICT!", "CRITICAL", "MUST") — fitting the anchor for noticeably verbose, padded sections; it does not, however, explain concepts Claude already knows.	2 / 5
Actionability	Provides concrete, copy-pasteable bash/curl/python scripts with real API endpoints and an env-var pre-flight check, but has minor gaps: the INITIAL_PROMPT placeholder, pseudocode decision block in Step 6, and template variables in Step 1.	4 / 5
Workflow Clarity	Steps 0–8 are clearly sequenced with explicit validation (STRICT review + 1–10 scoring), a score≥9 decision threshold, a refine→Step-2 feedback loop, and a detailed checklist — matching the anchor for clear sequence with validation, feedback loops, and checklists.	5 / 5
Progressive Disclosure	No bundle files exist and the skill is a single monolithic document; section headers are reasonable, but separable content (the style guide, the review template, the prompt templates) is fully inlined with zero one-level-deep references, so it is only "some structure" rather than a well-split overview.	3 / 5
	Total	14 / 20 Passed

Description

91%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.

A strong, concrete description that clearly states capability and trigger conditions with rich multilingual trigger phrases. The only weak spot is mild overlap risk from the generic "generate diagram" trigger alongside a sibling figure-generation skill.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("Generate publication-quality AI illustrations", "Creates architecture diagrams, method illustrations") plus the Gemini/Claude-supervised mechanism, but coverage stops short of the comprehensive multi-action anchor 5.	4 / 5
Completeness	Explicitly answers both "what" (generate paper illustrations via Gemini with a Claude-supervised refinement loop) and "when" ("Use when user says… or needs visual figures for papers") with concrete trigger phrases, matching the anchor exactly.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage with synonyms in two languages ("生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram"), matching the anchor for full keyword coverage including variations.	5 / 5
Distinctiveness Conflict Risk	Has a clear niche (AI illustrations for academic papers) but "generate diagram" is fairly generic and a sibling figure skill is referenced in the body, giving minor overlap risk rather than the minimal risk of anchor 5.	4 / 5
	Total	18 / 20 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 (697 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/aris-paper-illustration/SKILL.md
Commit: d51b64e

Reviewed: 6 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.