openai-image-gen

Generate images using OpenAI's DALL-E 3 API. Use when needing to create graphics, icons, backgrounds, or any visual assets. Requires OPENAI_API_KEY in environment.

3.46x

Quality

—

Does it follow best practices?

Impact

97%

3.46x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

65%

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

The body is highly actionable with complete, copy-paste command examples, but it is weighed down by a long inline set of site-specific preset prompts and lacks validation checkpoints around its batch-generation workflow. Referenced scripts are also not present as bundle files.

Suggestions

Move the Gothic Cathedral Presets into a separate reference file (e.g. references/gothic-presets.md) and link to it from a short overview, keeping SKILL.md a lean quick-start.

Add a verification step to the Batch Generation workflow (e.g. confirm each output file exists and check for API errors before declaring success) to lift workflow clarity.

Either ship the referenced `generate.sh` and `batch-gothic.sh` as scripts in the bundle or replace the hardcoded `~/.claude/skills/openai-image-gen/...` paths with relative references so the commands are runnable as delivered.

Dimension	Reasoning	Score
Conciseness	The core usage and parameter sections are efficient and assume Claude's competence, but the large inline 'Gothic Cathedral Presets' block of pre-baked prompts for one specific site is heavy inline content that pads the file without earning every token for general use.	2 / 3
Actionability	Commands are fully executable and copy-paste ready — every example is a complete `generate.sh` invocation with concrete prompts, sizes, and quality flags, plus a parameter table and a batch script.	3 / 3
Workflow Clarity	The single-action generate flow is unambiguous, but the 'Batch Generation' step has no validation or verification checkpoint; per the rubric, missing validation in batch operations caps workflow clarity at 2.	2 / 3
Progressive Disclosure	Sections are organized, but no bundle files exist and the body references `generate.sh` / `batch-gothic.sh` that are not present, while the sizable Gothic presets block is inline content that would be better split into a separate reference file.	2 / 3
	Total	9 / 12 Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-formed description that states the capability, gives an explicit 'Use when' trigger with natural user terms, and names the specific DALL-E 3 API to stay distinctive. Its only weakness is that it describes a single action rather than a breadth of concrete actions.

Dimension	Reasoning	Score
Specificity	The description names the domain and a concrete action ('Generate images using OpenAI's DALL-E 3 API') but offers essentially one capability rather than the multiple distinct actions the top anchor requires; the listed types (graphics, icons, backgrounds) are variations of a single image-generation action.	2 / 3
Completeness	It explicitly answers both 'what' ('Generate images using OpenAI's DALL-E 3 API') and 'when' via an explicit 'Use when needing to create graphics, icons, backgrounds, or any visual assets' trigger clause.	3 / 3
Trigger Term Quality	'graphics, icons, backgrounds, or any visual assets' are natural terms a user would actually say when requesting images, giving good coverage of common phrasings rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	The 'DALL-E 3 API' niche is specific and unlikely to overlap with other skills, and the visual-asset triggers are clearly scoped to image generation.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: NeverSight/skills_feed
Commit: c2b0563

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.