generate-image

Generate or edit images using AI models (FLUX, Nano Banana 2). Use for general-purpose image generation including photos, illustrations, artwork, visual assets, concept art, and any image that is not a technical diagram or schematic. For flowcharts, circuits, pathways, and technical diagrams, use the scientific-schematics skill instead.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/generate-image/SKILL.md

Quality

Content

71%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.

Highly actionable with comprehensive executable examples and a clear API-key setup sequence, but the body is over-long for a SKILL.md: redundant command-example sections and inlined use-case catalogs bloat token use and leave no room for progressive disclosure into reference files.

Suggestions

Condense "Common Usage Patterns" and "Example Use Cases" into a compact parameter table plus 2-3 representative examples; the repeated flag variations are redundant.

Move the detailed model comparison and the scientific/presentation/poster use-case catalogs into a references/ file (e.g. EXAMPLES.md) and link to it one level deep from SKILL.md to improve progressive disclosure.

Drop or trim the "When to Use This Skill" section since it duplicates the frontmatter description, and present the generate-then-edit workflow as one explicit sequenced flow with a validate-output checkpoint.

Dimension	Reasoning	Score
Conciseness	Mostly concrete commands with little concept-fluff, but the "Common Usage Patterns" (six near-identical flag variations) and "Example Use Cases" sections repeat the same invocation heavily, and "When to Use" duplicates the frontmatter description, so it could be tightened noticeably.	3 / 5
Actionability	Fully executable, copy-paste-ready bash commands throughout (e.g. `python scripts/generate_image.py "A beautiful sunset over mountains"`), with a documented parameter table and examples covering generate, edit, model selection, custom output, and multi-image cases.	5 / 5
Workflow Clarity	A clear numbered API-key setup sequence and a simple single-command generation flow with an error-handling feedback hint ("read the error message and address the issue before retrying") give most checkpoints, though the overall flow is scattered across sections rather than one coherent validated sequence.	4 / 5
Progressive Disclosure	Well-sectioned single file that correctly references the one real bundle file (scripts/generate_image.py), but at ~173 lines it is monolithic — model details and the lengthy example catalogs are inlined in SKILL.md rather than split into one-level-deep reference files, matching the "content that should be separate is inline" anchor.	3 / 5
	Total	15 / 20 Passed

Description

87%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 description that clearly answers what and when, uses third-person imperative voice, and explicitly redirects technical-diagram cases to a sibling skill. Minor gaps in synonym/file-extension trigger terms keep trigger quality and specificity just below full marks.

Dimension	Reasoning	Score
Specificity	Names two concrete actions ("Generate or edit images") plus a broad enumeration of output types ("photos, illustrations, artwork, visual assets, concept art"), giving several specific actions with only minor gaps versus the comprehensive multi-operation anchor at 5.	4 / 5
Completeness	Explicitly states what it does ("Generate or edit images using AI models") and when to use it ("Use for general-purpose image generation including...") with concrete trigger phrases, and adds an explicit redirect for the boundary case, matching the anchor that answers both what AND when.	5 / 5
Trigger Term Quality	Strong natural-term coverage ("image generation", "photos", "illustrations", "artwork", "concept art", "flowcharts", "circuits", "pathways") for both use and boundary cases, but missing common synonyms/extensions like "draw", "picture", "render", or .png/.jpg that the 5 anchor requires.	4 / 5
Distinctiveness Conflict Risk	Clear niche (general-purpose images) reinforced by explicit hand-off ("For flowcharts, circuits, pathways, and technical diagrams, use the scientific-schematics skill instead"), minimizing conflict risk as the 5 anchor describes.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/generate-image/SKILL.md
Commit: d5ae560

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.