imagegen

Generate and edit images using OpenAI's Image API for project assets — UI mockups, icons, illustrations, social cards, and visual references.

Quality

55%

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/imagegen/SKILL.md

Quality

Content

50%

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

The body is token-efficient and well-sectioned for a pointer/catalogue entry, but it provides almost no executable guidance for the skill's stated purpose — the real workflow is offloaded to an external repo with a vague install instruction.

Suggestions

Include a concrete install snippet (e.g. the exact clone/copy command and target skills-directory path) instead of 'inspect the upstream README for exact paths'.

Add at least one minimal executable example of invoking OpenAI's Image API (or the upstream script) so the skill is actionable without leaving SKILL.md.

Either inline a short quick-start block or add a local reference file (e.g. QUICKSTART.md) so navigation is one level deep rather than pointing to an external URL.

Dimension	Reasoning	Score
Conciseness	The body is lean (~45 lines), assumes Claude's competence, and avoids explaining concepts Claude already knows; the only minor inefficiency is the verbatim repeat of the frontmatter description under 'What it does'.	3 / 3
Actionability	The actual image-generation workflow is deferred entirely to the upstream repo; the only command ('open https://github.com/openai/skills') opens a browser and the install step says to 'Inspect the upstream README for exact paths', so it describes rather than instructs.	1 / 3
Workflow Clarity	A loose install-then-invoke sequence is present, but the install step is underspecified ('install the upstream bundle… inspect the README for exact paths') with no concrete command, so checkpoints are implicit.	2 / 3
Progressive Disclosure	Sections are organized (What it does, Source, How to use), but substantive detail lives behind an external URL rather than clearly signaled one-level-deep local references, and no bundle files are present.	2 / 3
	Total	8 / 12 Passed

Description

60%

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 third-person with a clear capability statement, but it lacks an explicit "Use when…" trigger clause and leans on a separate triggers field for activation cues, leaving completeness and distinctiveness at the mid level.

Suggestions

Append a 'Use when...' clause naming the natural situations a user would describe (e.g. 'Use when generating UI mockups, icons, illustrations, social cards, or other visual project assets').

Fold one or two high-signal trigger phrases ('create image', 'generate an icon', 'design a mockup') into the description so activation cues live alongside the capability statement.

Add a disambiguating detail (e.g. 'via OpenAI's gpt-image model') to further separate it from generic image skills.

Dimension	Reasoning	Score
Specificity	Lists concrete actions ("Generate and edit images") plus a named API ("OpenAI's Image API") and multiple specific asset types ("UI mockups, icons, illustrations, social cards, and visual references"), matching the multi-action anchor.	3 / 3
Completeness	It clearly states what the skill does, but there is no "Use when…" clause or equivalent explicit trigger guidance, which caps completeness at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	Natural asset terms like "mockup", "icon", and "illustration" appear, but common phrasings a user would say ("create image", "photo", "logo", "banner") are absent and the actual trigger phrases live in a separate frontmatter field rather than the description.	2 / 3
Distinctiveness Conflict Risk	Naming "OpenAI's Image API" gives it a niche, but image generation is a broad category that could overlap with other image skills, and no distinct triggers appear in the description itself.	2 / 3
	Total	9 / 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: nexu-io/open-design
Path: skills/imagegen/SKILL.md
Commit: 83f3d57

Reviewed: 2 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.