Tessl • The package manager for agent skills

Blog Docs Log inGet started

SkillPublic

imagen

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

Quality

57%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/imagen/SKILL.md

Quality

Content

47%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 lean and well-organized as a catalogue entry, but it provides almost no executable guidance: the real workflow lives entirely behind an upstream GitHub URL, and the install step is described only in prose. As a result actionability and workflow clarity sit low even though conciseness and structure are good.

Suggestions

Replace the prose 'install the upstream bundle into your active agent's skills directory' with the actual install command (e.g., a git clone or copy step with a concrete destination path) so the core instruction is executable.

Include a minimal end-to-end usage example — the API call or prompt pattern for generating one image — so the skill works without round-tripping to the upstream README.

Drop the 'What it does' section or replace it with non-duplicated information (e.g., prerequisites or auth setup), since it currently repeats the frontmatter description verbatim.

Dimension	Reasoning	Score
Conciseness	The body is short with no padding and no explanations of concepts Claude already knows; the only trimmable fat is the 'What it does' section repeating the frontmatter description verbatim, placing it just below the 'every token earns its place' anchor.	4 / 5
Actionability	The sole concrete command is 'open https://github.com/sanjay3290/imagen' — the actual image-generation steps are entirely deferred to an off-site README, matching the 'minimal concrete guidance; high-level hints but missing the specific steps' anchor rather than anchor 3's partial executable guidance.	2 / 5
Workflow Clarity	A rough sequence exists (inspect upstream README → install the bundle → invoke by name or trigger), but the critical install step has no command and the core executable workflow is a gap rather than merely missing checkpoints, fitting anchor 2's 'rough sequence present but many gaps'.	2 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are all absent) and the body is well under 50 lines with clear sections and one clearly signaled one-level reference (the upstream repo), though the actual detailed content lives entirely off-repo with no local signposting, keeping it just below the top anchor.	4 / 5
	Total	12 / 20 Passed

Description

50%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 clearly states what the skill does at a domain level but stops short of a trigger clause and enumerates output types rather than multiple concrete actions. Broad asset terms like 'icons' and 'illustrations' leave moderate conflict risk with other image skills. Adding a 'Use when...' clause and more varied natural trigger phrases would lift completeness and trigger-term quality.

Suggestions

Append a 'Use when...' clause (e.g., 'Use when the user asks for images, mockups, icons, or illustrations or mentions Gemini/Imagen') to satisfy the explicit trigger guidance the completeness dimension requires.

Replace the generic 'visual assets' tail with more natural synonyms users actually say — 'image generation', 'draw', 'create a picture', 'logo' — to improve trigger-term coverage.

List concrete actions beyond a single 'Generate images' (e.g., creating UI mockups, generating icons at specific sizes, producing illustrations in a requested style) to strengthen specificity.

Dimension	Reasoning	Score
Specificity	Names the domain ('Google Gemini's image generation API') and one action ('Generate images') with several output types ('UI mockups, icons, illustrations, and visual assets'), but these enumerate deliverables rather than multiple distinct actions, matching the '1-2 concrete actions' anchor rather than anchor 4's list of several actions.	3 / 5
Completeness	Has a clear 'what' (generate images for UI mockups, icons, illustrations) but no 'Use when...' clause or equivalent explicit trigger guidance, which the judging guidelines cap at 3.	3 / 5
Trigger Term Quality	Includes some natural terms users would say ('icons', 'illustrations', 'UI mockups') but misses common variations and synonyms such as 'image generation', 'draw', 'create image', or 'logo', fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The provider reference ('Google Gemini's image generation API') is fairly specific, but broad terms like 'icons', 'illustrations', and 'visual assets' would overlap with any other image-generation or drawing skill, matching the 'somewhat specific but could still overlap' anchor.	3 / 5
	Total	12 / 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: nexu-io/open-design
Path: skills/imagen/SKILL.md
Revision: 78d5637

Reviewed: 17 days ago

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.

imagen

Table of Contents

Is this your skill?