openai-image-gen

OpenAI Images API: batches, prompt sampler, gallery.

Quality

62%

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/openai-image-gen/SKILL.md

Quality

Content

76%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 admirably lean and gives concrete executable commands with good flag coverage, but it documents an install path that mismatches the bundled script and omits any validation for a batch paid-API operation. Aligning the path and adding a pre-flight check would raise actionability and workflow clarity.

Suggestions

Reference the bundled script with a relative path (e.g. 'python3 scripts/gen.py') or explain the install-path assumption so commands are executable as written.

Add a validation checkpoint before the batch call, e.g. confirm OPENAI_API_KEY is set and echo the count/estimated cost before generating.

Add a brief verify step after generation, e.g. check that index.html and the expected number of PNGs exist before running 'open'.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence: a one-line intro, an env requirement, executable commands, flags, and an output list, with no padding or explanation of concepts Claude already knows.	5 / 5
Actionability	Commands are concrete and copy-paste ready with useful flag examples, but the documented path '~/Projects/agent-scripts/skills/openai-image-gen/scripts/gen.py' differs from the bundled 'scripts/gen.py', a minor gap in executability.	4 / 5
Workflow Clarity	The setup-run-open sequence is clear, but this is a batch operation against a paid API with no validation checkpoint (e.g. confirm count/cost, verify API key, check outputs), which caps workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	Sections (Setup, Run, Output) are well organized for a simple skill, but the bundled script is not referenced via a relative path from the body, leaving a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

48%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 concise and names a distinct niche, but it is a label rather than a sentence: it lacks concrete action verbs and any 'Use when...' trigger guidance. Adding an explicit trigger clause and a few natural synonyms would lift completeness and trigger-term quality.

Suggestions

Rewrite as a third-person action sentence, e.g. 'Generates images via the OpenAI Images API in batches with a prompt sampler and HTML gallery.'

Add a 'Use when...' clause naming natural triggers like 'generate images', 'create images', 'DALL-E', or 'image generation'.

Include concrete actions (generate, batch, render, build gallery) instead of bare feature nouns to improve specificity.

Dimension	Reasoning	Score
Specificity	The description names the domain ('OpenAI Images API') and lists feature nouns ('batches, prompt sampler, gallery') but uses no concrete verbs describing actions, matching the 'names the domain but actions are minimal or generic' anchor.	2 / 5
Completeness	A clear 'what' is present (image generation via OpenAI Images API with batching/sampler/gallery), but there is no 'Use when...' clause or equivalent trigger guidance, capping completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	'OpenAI Images API' is a relevant natural term, but common user phrases like 'generate images', 'create images', 'DALL-E', and 'image generation' are absent, leaving keyword coverage incomplete.	3 / 5
Distinctiveness Conflict Risk	'OpenAI Images API' carves a clear niche with minimal conflict risk, though the terse feature list keeps it just short of fully distinct triggers.	4 / 5
	Total	12 / 20 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: steipete/agent-scripts
Path: skills/openai-image-gen/SKILL.md
Commit: dc4f583

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.