oma-image

Multi-vendor AI image generation with authentication-aware parallel dispatch. Routes to Codex (gpt-image-2 via ChatGPT OAuth), Antigravity (Gemini-family "nano-banana" image models via `agy` CLI + Gemini Code Assist; exact model chosen internally by agy), and Pollinations (flux/zimage, free with signup). Use for image generation, image creation, visual asset generation, and AI art.

Quality

88%

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%

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 concrete commands and a well-sequenced, validated workflow. It is held back by verbosity/redundancy and by progressive-disclosure references that point to bundle files not actually present.

Suggestions

Trim redundancy between the Scheduling section and the Guardrails section, and remove the abstract SSL-primitive Actions table to improve conciseness toward the lean level-3 bar.

Provide the referenced resources/ files (execution-protocol.md, vendor-matrix.md, prompt-tips.md, checklist.md) or remove the dangling references so progressive disclosure is backed by an actual bundle.

Move the inline vendor strategy detail and host-specific reference-path quirks into a referenced resource file so the SKILL.md body stays a focused overview.

Dimension	Reasoning	Score
Conciseness	The ~270-line body is mostly efficient but includes redundancy (overlapping Scheduling lists restated later in guardrails) and abstract ceremony (the SSL-primitive "Actions" table) that could be tightened; it does not reach the lean level-3 bar where every token earns its place.	2 / 3
Actionability	Concrete copy-paste-ready commands appear throughout ("oma image generate '<prompt>' --vendor auto...", "oma image doctor", reference flags, full option list), matching the fully-executable level-3 anchor rather than the pseudocode/incomplete level 2.	3 / 3
Workflow Clarity	The PREPARE→ACQUIRE→ACT→VERIFY→FINALIZE sequence has explicit validation checkpoints in VERIFY and a failure-and-recovery section with feedback loops (auth missing → report; outdated CLI → run oma update), matching the level-3 anchor with explicit validation and error-recovery loops.	3 / 3
Progressive Disclosure	References are signaled one-level-deep in a tidy References section, but the referenced bundle files (resources/execution-protocol.md, vendor-matrix.md, prompt-tips.md, checklist.md) do not exist in the bundle, and some detail that could be split (full vendor strategy, host-specific reference path quirks) is inline; this fits level 2 rather than the well-split level 3.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 third-person description that specifies concrete vendor-routing actions, explicit natural trigger terms, and a clear use-when clause. It is both complete and distinctive with no fluff or voice violations.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and specific vendor routes: "Routes to Codex (gpt-image-2 via ChatGPT OAuth) and Pollinations (flux/zimage...)" and "Gemini provider is present but disabled by default", matching the level-3 anchor of multiple specific concrete actions rather than the partial level-2.	3 / 3
Completeness	It clearly answers what (multi-vendor AI image generation, routes to named vendors) and when via an explicit "Use for..." trigger clause, matching level 3 and exceeding the level-2 cap for a missing when-clause.	3 / 3
Trigger Term Quality	"Use for image generation, image creation, visual asset generation, and AI art" gives good coverage of natural terms a user would actually say, matching level 3 rather than the partial-coverage level 2.	3 / 3
Distinctiveness Conflict Risk	The named multi-vendor auth-aware image-generation niche with specific vendor triggers is clearly distinguishable and unlikely to conflict with other skills, matching level 3 rather than the overlapping level 2.	3 / 3
	Total	12 / 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: first-fluke/oh-my-agent
Path: .agents/skills/oma-image/SKILL.md
Commit: 3021301

Reviewed: about 21 hours 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.