create-image-gpt-image-fal

Generate a single photoreal or designed image with OpenAI gpt-image via fal.ai. Supports gpt-image-1 (default, fixed sizes — the FAL fallback for Higgsfield's `gpt_image_2`) and gpt-image-2 (`openai/gpt-image-2`, custom output sizes up to 3840px). Routes to text-to-image or the edit variant depending on whether a reference image is provided. Use for photoreal character anchors, scene keyframes, and designed sheets (e.g. storyboards) where precise layout and legible text matter.

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

Quality

Content

77%

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 and error-recovery guidance. Its weaknesses are mild verbosity from dated pricing and repeated proxy warnings, and a lack of progressive file-splitting for the longer reference material.

Suggestions

Move the dated pricing table ('as of 2026-05') into a separate PRICING.md reference or a clearly marked versioned section to remove time-sensitive tokens from the main body.

Consolidate the proxy-routing / 'not a raw FAL key' warning into one canonical callout and reference it from the other sections instead of restating it three times.

Consider splitting the Failure Modes table and Cross-provider parity note into a separate reference file to improve progressive disclosure and shorten the core SKILL.md overview.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence without explaining known concepts, but dated pricing ('as of 2026-05') and repeated proxy-routing warnings (Inputs, Workflow step 1, Failure Modes) could be tightened, so it sits at 'mostly efficient but could be tightened' rather than fully lean.	2 / 3
Actionability	Provides fully executable, copy-paste-ready bash commands with concrete flags and paths, a preflight check, and a Failure Modes table with specific fixes — matching the 'fully executable code/commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	A clear 6-step numbered Workflow is backed by explicit validation (Preflight credentials/requests check, Quality Checks) and an error-recovery feedback loop (Failure Modes table), matching the 'clear sequence with explicit validation steps' anchor.	3 / 3
Progressive Disclosure	Sections are well-organized and referenced scripts (media_proxy.py, generate.py, fal_helpers.py) all exist in the bundle, but the skill is a monolithic single SKILL.md with no content split into separate reference files, so it does not fully meet the 'content appropriately split' bar for a 3.	2 / 3
	Total	10 / 12 Passed

Description

85%

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 with an explicit 'Use for' trigger that clearly answers both what and when. The main weakness is trigger-term naturalness — the use-case phrasing is somewhat domain-jargon-heavy and misses plainer variations.

Suggestions

Add plainer natural-language triggers alongside the domain terms, e.g. 'Use for generating character images, scene keyframes, and storyboard sheets' to broaden natural keyword coverage.

Consider including the simple term 'image generation' or 'create an image' as a natural entry point users would actually say.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Generate a single photoreal or designed image' and 'Routes to text-to-image or the edit variant depending on whether a reference image is provided' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers both what ('Generate a single photoreal or designed image with OpenAI gpt-image via fal.ai') and when via an explicit 'Use for ...' trigger clause, matching the score-3 anchor.	3 / 3
Trigger Term Quality	The 'Use for photoreal character anchors, scene keyframes, and designed sheets (e.g. storyboards)' clause covers relevant scenarios, but 'character anchors' and 'scene keyframes' lean toward workflow jargon and it omits simpler natural phrasings a user might say (e.g. 'generate an image of a character').	2 / 3
Distinctiveness Conflict Risk	The narrow 'OpenAI gpt-image via fal.ai' niche with specific triggers (character anchors, keyframes, storyboards) makes it unlikely to fire for the wrong skill.	3 / 3
	Total	11 / 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: gooseworks-ai/goose-skills
Path: skills/ads/capabilities/create-image-gpt-image-fal/SKILL.md
Commit: 8866b2a

Reviewed: 1 day 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.