openai-image-gen

Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery. Use when you need prompt variants or batches.

Quality

81%

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

The canonical home for this skill is openai-image-gen in steipete/agent-scripts

Quality

Content

87%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.

An exemplary lean, fully executable skill body — every command is real and copy-paste ready, and the structure is clean for a simple single-purpose tool. The only real gap is the absence of validation/verification for what is a batch API operation, which the rubric explicitly caps.

Suggestions

Add a validation step to the workflow, e.g. "Preview prompts without API calls first: python3 .../gen.py --dry-run" before the real run.

Document a verification checkpoint after generation, such as checking prompts.json for the prompt↔file mapping or confirming non-empty output before opening the gallery.

Briefly note error behavior (e.g., what happens on missing OPENAI_API_KEY or per-request timeout) so Claude can recover instead of guessing.

Dimension	Reasoning	Score
Conciseness	The ~30-line body contains only operational facts (env var, run command, flags, outputs) with zero explanation of concepts Claude already knows. Every token earns its place, matching the lean anchor 5.	5 / 5
Actionability	Commands are fully executable and copy-paste ready — the run command plus three flag examples cover count, model, prompt, size, quality, and out-dir. Verified against scripts/gen.py: all flags, the OPENAI_API_KEY env var, and the outputs (*.png, prompts.json, index.html) are real and match the script. Specific examples cover the common cases per anchor 5.	5 / 5
Workflow Clarity	The sequence (set OPENAI_API_KEY → run gen.py → open gallery) is clear, but this is a batch operation (default 8 API image requests) with no validation or verification step — no mention of --dry-run (which the script supports) to preview prompts, no check of prompts.json or the gallery before finishing, no error-handling guidance. Per the rubric, missing validation in batch operations caps workflow clarity at 3, taking precedence over the simple-skill exception.	3 / 5
Progressive Disclosure	A simple single-purpose skill under 50 lines with well-organized sections (Setup, Run, Output) and no need for external references. The single referenced path, scripts/gen.py, exists and its behavior matches the body's claims. This satisfies the simple-skill exception allowing a score of 5 with just well-organized sections.	5 / 5
	Total	18 / 20 Passed

Description

75%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, specific, and correctly structured with both a what-statement and a Use-when trigger clause. Its main weaknesses are a narrow trigger clause and missing common synonyms/model names that users might naturally say.

Suggestions

Broaden the trigger clause to cover common phrasings, e.g. "Use when the user asks to generate images, create image variants, or produce batches of AI-generated pictures".

Add natural synonyms and model names users actually say — "image generation", "DALL-E", "gpt-image" — to improve trigger matching.

Mention the output format options (sizes, quality, model selection) briefly so the capability coverage is comprehensive.

Dimension	Reasoning	Score
Specificity	Quotes several concrete actions — "Batch-generate images via OpenAI Images API", "Random prompt sampler", "`index.html` gallery" — with only minor coverage gaps (no mention of size/quality/model options). It lists several specific actions rather than only 1-2, so it sits above the anchor 3 example but below the comprehensive coverage of anchor 5.	4 / 5
Completeness	Both parts are present: what ("Batch-generate images... Random prompt sampler + gallery") and when ("Use when you need prompt variants or batches"). The when-clause is explicit but narrow — a plain "generate images" request isn't clearly covered — matching anchor 4's "'when' could be more explicit or specific" rather than the concrete trigger phrases of anchor 5.	4 / 5
Trigger Term Quality	Natural terms like "images", "OpenAI Images API", "prompt variants", and "batches" would appear in real requests, but common variations are missing — no "image generation", "pictures", or model names ("DALL-E", "gpt-image"). Good coverage with a few natural terms absent matches anchor 4.	4 / 5
Distinctiveness Conflict Risk	"OpenAI Images API" establishes a clear niche with distinct triggers, though there is minor overlap risk with other image-generation or image-editing skills (e.g., other providers or gallery/preview tools). Mostly distinct per anchor 4, not the minimal-conflict clarity of anchor 5.	4 / 5
	Total	16 / 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: marchatton/agent-skills
Path: .agents/skills/00-utilities/openai-image-gen/SKILL.md
Commit: a0eadb2

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.