imagen

Generate images using Google Gemini's image generation API for UI mockups, icons, illustrations, and visual assets.

Quality

64%

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/imagen/SKILL.md

Quality

Content

57%

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

The content is concise and cleanly organized but functions only as a pointer: it provides no executable guidance for actually generating images and delegates the real workflow to an upstream repo, which sinks actionability and weakens workflow clarity.

Suggestions

Inline a minimal concrete example of invoking Gemini's image API (a short code snippet or exact command) so the skill is actionable without leaving SKILL.md.

Replace the vague 'install the upstream bundle' step with explicit, verifiable install steps (e.g. a clone command and target skills-directory path) plus a check that the skill is registered.

Add a validation checkpoint after installation (e.g. confirm the skill appears in the agent's skill list) to lift workflow clarity above 2.

Dimension	Reasoning	Score
Conciseness	The body is lean (~25 lines) and does not explain concepts Claude already knows; it assumes competence and keeps every section tight, matching 'Lean and efficient; every token earns its place' despite a minor repetition of the description in the 'What it does' section.	3 / 3
Actionability	The only concrete instruction is `open https://github.com/sanjay3290/imagen`; the actual image-generation workflow is delegated to an external repo with vague direction ('install the upstream bundle into your active agent's skills directory'), so it 'describes rather than instructs' with no executable code or commands for the skill's core task.	1 / 3
Workflow Clarity	A loose sequence exists (inspect the upstream README → install the bundle → invoke by name or trigger), but the steps are imprecise and lack any validation checkpoints, matching 'Steps listed but validation gaps; sequence present but checkpoints missing or implicit' rather than the unambiguous single-action case that would warrant a 3.	2 / 3
Progressive Disclosure	With no local bundle files (references/scripts/assets absent) and well-organized sections (What it does, Source, How to use), the body fits the simple-skill allowance where progressive disclosure scores 3 with just clear organization; the single outbound reference (the upstream URL) is clearly signaled one level deep.	3 / 3
	Total	9 / 12 Passed

Description

72%

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 specific and well-triggered around a clear Gemini image-generation niche, but it omits an explicit 'Use when...' clause, which caps completeness at 2 and keeps the description from being fully self-contained.

Suggestions

Append an explicit usage clause, e.g. 'Use when the user asks to generate UI mockups, icons, illustrations, or other visual assets with Gemini image generation.'

Broaden the action verbs beyond 'Generate' (e.g. 'Generate, edit, and vary images') to lift specificity from a single action to multiple concrete actions.

Trim generic triggers like 'illustration' and 'icon' or qualify them ('gemini illustration') to reduce overlap with unrelated design skills.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Google Gemini's image generation API') and several target outputs ('UI mockups, icons, illustrations, and visual assets') but centers on a single action ('Generate images'), which matches 'Names domain and some actions, but not comprehensive' rather than the multiple distinct actions required for a 3.	2 / 3
Completeness	It clearly answers 'what' (generate images via Gemini's API) but lacks an explicit 'Use when...' clause or equivalent trigger guidance inside the description; the judging guideline caps completeness at 2 when such a clause is missing, even though use-case hints appear in the 'for UI mockups...' tail.	2 / 3
Trigger Term Quality	The description surfaces natural terms users would say — 'images', 'Google Gemini', 'image generation', 'UI mockups', 'icons', 'illustrations', 'visual assets' — supplemented by explicit frontmatter triggers ('gemini image', 'imagen', 'google image gen', 'illustration', 'icon'), giving good coverage of natural phrasings.	3 / 3
Distinctiveness Conflict Risk	Tying the skill to 'Google Gemini's image generation API' carves a clear niche, and the Gemini-specific triggers ('imagen', 'gemini image', 'google image gen') are unlikely to fire for unrelated skills, matching 'Clear niche with distinct triggers'; the generic 'illustration'/'icon' triggers are a minor overlap risk but do not outweigh the distinct framing.	3 / 3
	Total	10 / 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/imagen/SKILL.md
Commit: 83f3d57

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.