imagegenskill

Generate renderable, scientific-style SVG graphics directly from natural-language requirements (no image models). Use when users ask for an image/picture/scientific diagram/visualization poster or explicitly request SVG output for web-embeddable vector graphics.

Quality

73%

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/imagegenskill/SKILL.md

Quality

Content

63%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 actionable and reasonably well-sequenced with executable examples and a feedback loop for tuning, but it carries some redundancy with the description and fails to surface the existing reference bundle files. Tightening the speculative/padded sections and linking the references would lift the weaker dimensions.

Suggestions

Link the reference bundle files where relevant (e.g., 'See references/prompting.md for brief guidelines, references/sample-prompts.md for examples') instead of leaving references/ entirely unmentioned.

Remove the speculative Dependencies note and either list the actual stdlib-only imports or state plainly that svg_gen.py uses only the Python standard library (which the script confirms).

Trim the 'When to Use' list to avoid restating the frontmatter description, or repurpose it as trigger examples not already covered there.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, but the 'When to Use' section repeats the frontmatter description and the Dependencies note speculates about unspecified third-party packages ('If scripts/svg_gen.py imports external libraries, add them here'), which is padding Claude could infer or verify directly.	3 / 5
Actionability	Provides concrete, copy-pasteable bash (mkdir, heredoc brief, python scripts/svg_gen.py, ls) and names specific tuning parameters (node_count, noise_points, band_count, ring_density); the edit-the-script-top / sed approach to configuration is a minor gap versus CLI flags.	4 / 5
Workflow Clarity	A clear four-step sequence ends with an inspection checkpoint ('Open output/svggen/latest.svg to inspect the result') and a tuning/troubleshooting section provides a fix-and-regenerate feedback loop; minor validation gaps remain but the operation is non-destructive so the destructive-cap does not apply.	4 / 5
Progressive Disclosure	The body is well-sectioned and correctly references scripts/svg_gen.py, but five bundle files in references/ (cli.md, codex-network.md, image-api.md, prompting.md, sample-prompts.md) are never linked or signaled from SKILL.md, leaving navigation of the bundle incomplete.	3 / 5
	Total	14 / 20 Passed

Description

82%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 well-structured, explicitly covering both capability and trigger conditions with natural user-facing terms and a clearly distinct niche. Its only weakness is specificity, naming essentially one concrete action rather than a comprehensive set.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ('Generate renderable, scientific-style SVG graphics directly from natural-language requirements') but offers only a single action plus a constraint ('no image models'), not the several specific actions a 4 requires.	3 / 5
Completeness	Explicitly answers both what (generate renderable scientific-style SVG from NL) and when ('Use when users ask for an image/picture/scientific diagram/visualization poster or explicitly request SVG output') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-term coverage ('image', 'picture', 'scientific diagram', 'visualization poster', 'SVG output', 'web-embeddable vector graphics') users would actually say, though the .svg extension and terms like 'chart'/'figure' are missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche (NL-to-SVG without image models) with distinct triggers; the '(no image models)' qualifier explicitly separates it from diffusion/LLM image-gen skills, minimizing conflict risk.	5 / 5
	Total	17 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Other/imagegenskill/SKILL.md
Commit: f5ef65b

Reviewed: ~15 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.