oma-image

Multi-vendor AI image generation with authentication-aware parallel dispatch. Routes to Codex (gpt-image-2 via ChatGPT OAuth) and Pollinations (flux/zimage, free with signup). Gemini provider is present but disabled by default (requires billing). Use for image generation, image creation, visual asset generation, and AI art.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%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 highly actionable with a clear validated workflow and executable commands, but it is somewhat verbose and its progressive-disclosure references dangle — none of the cited resources/, config/, or shared files are present in the bundle.

Suggestions

Create the referenced bundle files (resources/execution-protocol.md, vendor-matrix.md, prompt-tips.md, checklist.md, config/image-config.yaml) or remove the references, so signaled navigation does not dead-end.

Trim inferable rationale such as the CLI-first concept paragraph and the English-caption explanation to tighten conciseness.

Move the large vendor table and/or clarification protocol into referenced files and summarize inline, improving token efficiency and structure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but includes rationale prose Claude can infer ('image models are trained predominantly on English captions', the CLI-first concept paragraph, and the long Gemini-disabled explanation) that could be trimmed.	3 / 5
Actionability	Provides copy-paste ready commands (`oma image generate`, `oma image doctor`, `oma image list-vendors`), a full flag inventory, canonical paths, reference-image examples, and output layout covering the common cases.	5 / 5
Workflow Clarity	Clear PREPARE/ACQUIRE/ACT/VERIFY/FINALIZE sequence with an explicit VERIFY validation step, exit-code failure-and-recovery mapping, and a clarification checklist with feedback loops for batch/cost-guarded operations.	5 / 5
Progressive Disclosure	References to resources/execution-protocol.md, vendor-matrix.md, prompt-tips.md, checklist.md, config/image-config.yaml, and ../_shared/core/context-loading.md are signaled but those files do not exist in the bundle, and substantial content (vendor table, clarification protocol) is inlined rather than split out.	3 / 5
	Total	16 / 20 Passed

Description

92%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.

A strong, specific description that covers what the skill does and when to use it with concrete vendor/model detail and natural trigger terms. The only gap is slightly redundant trigger phrasing and the absence of file-extension keywords.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions across named vendors and models — 'Routes to Codex (gpt-image-2 via ChatGPT OAuth) and Pollinations (flux/zimage)' with 'authentication-aware parallel dispatch' — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what ('Multi-vendor AI image generation with authentication-aware parallel dispatch' plus per-vendor routing) and when ('Use for image generation, image creation, visual asset generation, and AI art') with concrete trigger phrases.	5 / 5
Trigger Term Quality	'image generation, image creation, visual asset generation, and AI art' are natural user phrases, but 'generation'/'creation' are near-duplicates and file extensions (.png/.jpg) are absent, leaving a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	The multi-vendor AI image routing niche with named providers and models is clearly distinct and unlikely to trigger the wrong skill.	5 / 5
	Total	19 / 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: first-fluke/oh-my-agent
Path: benchmarks/runs/oma/.agents/skills/oma-image/SKILL.md
Commit: 032c988

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.