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

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

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 well-sequenced, validated workflow and concrete CLI examples. Its weaknesses are abstract meta-framework padding that hurts token efficiency, and references that point to non-existent bundle files.

Suggestions

Remove the meta-framework scaffolding (SSL-primitive action table, PREPARE/ACQUIRE/ACT scene labels, LOCAL_FS/PROCESS/NETWORK scope table) to reduce abstract padding; keep the concrete commands, flags, and vendor matrix.

Create the referenced files (resources/execution-protocol.md, vendor-matrix.md, prompt-tips.md, checklist.md) or remove the dangling references so navigation targets resolve.

Move the large inlined vendor-strategy and policy detail into the referenced resource files, leaving SKILL.md a lean overview with clearly signaled one-level-deep links.

Dimension	Reasoning	Score
Conciseness	Concrete command/flag/vendor content is efficient, but substantial meta-framework scaffolding (SSL-primitive action tables, PREPARE/ACQUIRE/ACT scene labels, LOCAL_FS/PROCESS/NETWORK scope table) is abstract padding Claude does not need for this task.	3 / 5
Actionability	Provides copy-paste ready commands with full flag lists, reference-image examples, an explicit mandatory auto-forward instruction with the exact command, and a concrete output filename/tree layout covering common cases.	5 / 5
Workflow Clarity	Clear Entry→Scenes→Transitions→Failure/recovery→Exit sequence with explicit validation checkpoints (Clarification Protocol checklist, VERIFY scene, cost guardrail confirmation, doctor precheck, exit-code table) and feedback loops for the batch/paid generation operations.	5 / 5
Progressive Disclosure	Section structure and one-level-deep reference signaling are good, but the referenced files (resources/execution-protocol.md, vendor-matrix.md, prompt-tips.md, checklist.md, ../_shared/core/context-loading.md) do not exist in the bundle, so navigation targets are missing and heavy policy/vendor content remains inlined.	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 names concrete vendor capabilities and explicit trigger phrases, with clear third-person voice and a distinct niche. Trigger term coverage is good but could add natural verb forms and synonyms to reach full comprehensiveness.

Dimension	Reasoning	Score
Specificity	Enumerates three concrete vendor routes (Codex/gpt-image-2, Antigravity/nano-banana, Pollinations/flux/zimage) with specific mechanisms (ChatGPT OAuth, agy CLI, Gemini Code Assist), giving comprehensive concrete coverage.	5 / 5
Completeness	Explicitly states both what it does ('Multi-vendor AI image generation... Routes to...') and when to use it ('Use for image generation, image creation, visual asset generation, and AI art') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrases ('image generation', 'image creation', 'visual asset generation', 'AI art') but misses common variations like 'generate images'/'make a picture' and file-type triggers; 'image creation' partly duplicates 'image generation'.	4 / 5
Distinctiveness Conflict Risk	The multi-vendor authenticated routing niche and specific vendor triggers (Codex/Antigravity/Pollinations) are clearly distinct from other skills with minimal conflict risk.	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: .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.