image-generation

Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes, products, or any visual content. Supports structured prompts and reference images for guided generation.

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/public/image-generation/SKILL.md

Quality

Content

65%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 concrete commands and examples, but it is verbose, lacks validation/retry checkpoints in the workflow, and contains a dangling template reference. Tightening the examples and adding an explicit verify-or-retry step would raise the weaker dimensions.

Suggestions

Condense the two large JSON examples into one canonical example plus a shorter variant, or move detailed schemas into a separate references file to improve conciseness and progressive disclosure.

Add an explicit validation/retry checkpoint in the workflow (e.g., verify the prompt-file JSON is valid before running, and re-run with an adjusted prompt if generation fails or output is missing).

Fix or remove the dangling reference to templates/doraemon.md, which does not exist in the bundle.

Dimension	Reasoning	Score
Conciseness	Two large, conceptually overlapping JSON examples (~50 lines of detailed fields each) plus mildly redundant notes ("JSON format ensures structured, parsable prompts") make the body noticeably heavier than needed; could be tightened without losing clarity.	3 / 5
Actionability	Provides copy-paste-ready commands with all parameters documented and complete JSON prompt examples covering both the no-reference and reference-image cases; minor example filename inconsistency does not undermine executability.	5 / 5
Workflow Clarity	Steps are sequenced (understand → create prompt → execute → output handling) but lack validation checkpoints and an explicit error/retry loop despite the skill noting iterative refinement is normal, matching the anchor-3 validation-gap case.	3 / 5
Progressive Disclosure	Section structure is reasonable and references are signaled one level deep, but the referenced templates/doraemon.md does not exist in the bundle and the verbose JSON examples are inlined rather than split out, leaving organization with clear gaps.	3 / 5
	Total	14 / 20 Passed

Description

78%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.

The description clearly states what the skill does and when to use it with strong, natural trigger terms and a distinct niche. It is slightly held back by missing synonyms/extensions and trigger scenarios that would push specificity and completeness to the top level.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete capabilities ("generate, create, imagine, or visualize images", "characters, scenes, products", structured prompts, reference-image guidance), with only minor coverage gaps; not a 5 because it stops short of a comprehensive list of distinct actions.	4 / 5
Completeness	Explicitly answers both "what" (image generation via structured prompts and reference images) and "when" ("Use this skill when the user requests to generate, create, imagine, or visualize images"), but the "when" could be more specific with additional trigger scenarios.	4 / 5
Trigger Term Quality	Includes natural verbs users say ("generate, create, imagine, or visualize images") but misses common synonyms ("draw", "AI art", "picture") and file extensions (.jpg/.png), so it falls short of comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	Image generation is a clear niche with distinct, natural triggers and minimal overlap risk with other skills; matches the anchor-5 example of a well-bounded capability.	5 / 5
	Total	17 / 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
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: bytedance/deer-flow
Path: skills/public/image-generation/SKILL.md
Commit: 2a261d2

Reviewed: about 18 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.