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

82%

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

81%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.

A highly actionable, well-sequenced skill body with strong validation checkpoints and clear external references. The main weakness is conciseness — redundancy and verbose table cells inflate the body — alongside inlined detail that could live in the referenced resource files.

Suggestions

De-duplicate the resources list (it appears under Dependencies and again under References/Configuration) into a single canonical pointer set.

Tighten the verbose vendor-table and reference-support-table cells into terser key/value phrasing to reclaim tokens.

Move the full Clarification Protocol and category-specific briefs into resources/prompt-tips.md, keeping only the core checklist and amplification shortcut inline in SKILL.md.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and domain-specific, but the 283-line body carries redundancy (resources listed in both Dependencies and References/Configuration) and wordy cells in the vendor/reference tables that could be tightened without losing clarity.	3 / 5
Actionability	Provides copy-paste-ready commands ('oma image generate "<prompt>" --vendor auto --size auto --quality auto --output json', doctor, vendor list) plus concrete reference-image and standalone invocation examples covering the common cases.	5 / 5
Workflow Clarity	Clear PREPARE/ACQUIRE/ACT/VERIFY/FINALIZE sequence with explicit validation (VERIFY scene, 'oma image doctor', manifest/exit-code checks), a Clarification Protocol checklist, and a Failure-and-recovery section with feedback loops for a batch/paid operation.	5 / 5
Progressive Disclosure	Well-signaled one-level-deep references (resources/execution-protocol.md, vendor-matrix.md, prompt-tips.md, checklist.md) with a dedicated References section, but no bundle files are present and some heavyweight content (vendor table, Clarification Protocol) is inlined rather than split out.	4 / 5
	Total	17 / 20 Passed

Description

83%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 names concrete vendors and models and includes an explicit 'Use for' trigger clause covering both what and when. It could add a few more natural synonyms (illustrations, concept art) and acknowledge comparison/vendor-routing as a distinct trigger.

Suggestions

Add natural trigger synonyms that users commonly say, such as 'illustrations', 'product photos', 'concept art', and 'mockups', to broaden keyword coverage.

Surface the vendor-comparison use case ('compare output between multiple image models') as an explicit trigger in the description, since it is a distinctive capability.

Dimension	Reasoning	Score
Specificity	Lists several concrete routing actions to three named vendors with specific models (Codex/gpt-image-2, Antigravity/nano-banana, Pollinations/flux/zimage), but the actions center on dispatch/routing rather than enumerating the full set of generation actions.	4 / 5
Completeness	Explicitly answers 'what' (multi-vendor AI image generation with auth-aware parallel dispatch to three vendors) and 'when' via the explicit 'Use for image generation, image creation, visual asset generation, and AI art' trigger clause.	5 / 5
Trigger Term Quality	Includes natural terms users would say ('image generation, image creation, visual asset generation, and AI art') with synonyms, but misses common variations like 'illustrations', 'product photos', or 'concept art' that appear in the body.	4 / 5
Distinctiveness Conflict Risk	The multi-vendor auth-aware routing niche is clearly distinct from single-purpose image skills, but 'image generation'/'AI art' triggers carry minor overlap risk with other image-related skills.	4 / 5
	Total	17 / 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: .agents/skills/oma-image/SKILL.md
Commit: 7721120

Reviewed: 3 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.