Tessl • The package manager for agent skills

SkillPublic

imagegen

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

Quality

63%

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

43%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.

This body is a catalogue stub rather than a usable skill: it repeats the description, lists provenance, and defers everything actionable to an external GitHub repo. It is concise but fails to give the agent any executable workflow for actually generating or editing images.

Suggestions

Replace the duplicated 'What it does' and 'Source' sections with a minimal quick-start (e.g., the concrete install command for the upstream bundle and a basic Image API call example) so the skill is actionable on its own.

Turn 'How to use' into a real sequenced workflow: install the bundle into the agent's skills directory, verify the install, then invoke by name or trigger — with an explicit command for each step.

Bundle or inline the essential upstream material (key scripts/references) locally, or at minimum link to the exact upstream paths for the workflow, scripts, and references rather than a bare repository URL.

Dimension	Reasoning	Score
Conciseness	The body is short and lean with no padded concept explanations, but 'What it does' repeats the frontmatter description verbatim and 'Source' duplicates the upstream URL already in frontmatter, so a few tokens are redundant.	4 / 5
Actionability	The only concrete command is `open https://github.com/openai/skills`; there is no install command, no code, and no API usage guidance, so the reader gets high-level hints without executable steps.	2 / 5
Workflow Clarity	A rough sequence exists (inspect upstream README, install bundle, invoke by name/trigger) but the actual installation steps and commands are undefined, leaving major gaps between the listed steps.	2 / 5
Progressive Disclosure	Sections are clear and the skill is short, but the real content lives entirely in an external repo URL rather than in bundled reference files, so there is no well-signaled local one-level-deep reference structure — the body is a pointer, not an overview of the skill's own material.	3 / 5
	Total	11 / 20 Passed

Description

66%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 specific and concrete about what the skill does and its niche, with natural trigger terms in the frontmatter. Its main weakness is the missing explicit 'when to use' guidance, plus a few absent trigger variants that would improve discovery and distinctiveness.

Suggestions

Append an explicit trigger clause, e.g., 'Use when the user asks to generate, edit, or create images, icons, mockups, or illustrations with AI' — this directly addresses the completeness cap.

Add missing natural trigger variants like 'edit image', 'AI image generation', 'logo', and 'illustration' to broaden coverage.

Sharpen distinctiveness by naming the editing capability (e.g., 'edit and remix existing images from image prompts') so it does not collide with UI/mockup skills on the generic 'mockup' trigger.

Dimension	Reasoning	Score
Specificity	'Generate and edit images using OpenAI's Image API for project assets — UI mockups, icons, illustrations, social cards, and visual references' names two concrete actions, a specific API, and concrete deliverables, but omits other capabilities (variations, editing modes, input formats) leaving minor gaps.	4 / 5
Completeness	The 'what' is clear and concrete, but there is no 'Use when...' clause or equivalent explicit trigger guidance in the description — the 'when' is only weakly implied by the asset list, which caps completeness at 3.	3 / 5
Trigger Term Quality	Natural phrases like 'generate image', 'create image', 'image gen', 'icon design', and 'mockup' match what users would say, but common variants such as 'edit image', 'AI image', 'logo', or file extensions are missing.	4 / 5
Distinctiveness Conflict Risk	'OpenAI's Image API' establishes a clear niche, but generic triggers like 'mockup' and 'icon design' risk overlap with UI-design and icon-creation skills.	4 / 5
	Total	15 / 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/imagegen/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.

imagegen

Table of Contents

Is this your skill?