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

66%

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

Fix and improve this skill with Tessl

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

Quality

Content

63%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, parameters, and worked JSON examples, and the provider-configuration section is dense with genuinely non-obvious operational detail. Weaknesses are a broken reference to a nonexistent template file, an internally inconsistent first example (prompt-file name mismatch), and inline-heavy examples plus filler notes that hurt token efficiency.

Suggestions

Fix the broken reference: the body links to `templates/doraemon.md` but no such file exists in the bundle — either add the template file or remove the 'Specific Templates' section.

Correct the first worked example: the prompt file is created as `asian-woman.json` but the execute command references `cyberpunk-hacker.json` (and outputs `cyberpunk-hacker-01.jpg`), so copy-paste use would fail.

Move the two large example JSON payloads (especially the ~55-line Star Wars example) into a `references/examples.md` file and trim the filler 'Notes' entries that restate things Claude already knows, to improve token efficiency and progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient (commands, parameter tables, env-var settings) but contains filler — the Notes section asserts things Claude already knows ("JSON format ensures structured, parsable prompts", "Iterative refinement is normal for optimal results") — and the ~55-line inline Star Wars example JSON could be trimmed. This matches the "mostly efficient but could be tightened" anchor rather than the noticeably-verbose 2.	3 / 5
Actionability	Concrete, executable bash invocations with a parameter table, exact paths, and complete JSON prompt examples. However the first example is internally inconsistent — it creates `/mnt/user-data/workspace/asian-woman.json` but the execute command passes `--prompt-file /mnt/user-data/workspace/cyberpunk-hacker.json` — and scene/product scenarios get field lists rather than usable schemas, keeping it below fully copy-paste-ready.	4 / 5
Workflow Clarity	A clear three-step sequence (understand requirements → create structured prompt → execute script) with concrete commands, an output-handling section, and documented error behavior (the MiniMax 1500-character prompt cap returning an error). No validation checkpoints exist, but the operation is non-destructive so the cap does not apply; it lacks the explicit validate/fix/retry loop of a 5.	4 / 5
Progressive Disclosure	Scored against the actual bundle: `scripts/generate.py` exists and is correctly referenced, but the body's only template pointer, `templates/doraemon.md`, is missing from the bundle — a broken navigation path. Combined with large inline example JSON blocks that belong in separate reference files, this matches the "some structure but could be better organized; content that should be separate is inline" anchor.	3 / 5
	Total	14 / 20 Passed

Description

70%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 solid description with an explicit and well-phrased trigger clause and good synonym coverage of user intent. Its main weakness is a thin capability inventory — it says the domain and the prompt/reference mechanisms but does not enumerate the concrete actions the skill performs.

Dimension	Reasoning	Score
Specificity	Names the image-generation domain plus two concrete capabilities ("structured prompts and reference images for guided generation"), matching the anchor for domain + 1-2 concrete actions. It does not list several distinct actions, so it falls short of a 4.	3 / 5
Completeness	Both parts are present: an explicit "Use this skill when the user requests..." trigger clause and a what-statement about generating images with structured prompts and references. The what-side is thinner than the anchor-5 example's multi-action inventory, so it sits at 4 rather than 5.	4 / 5
Trigger Term Quality	Strong natural-keyword coverage with synonyms ("generate, create, imagine, or visualize images", "characters, scenes, products"), but misses common user phrasings like "draw", "make a picture", or "AI art" that would warrant a 5.	4 / 5
Distinctiveness Conflict Risk	A clear image-generation niche with distinct trigger verbs, but "visualize... any visual content" creates minor overlap risk with chart/dataviz or image-editing skills, matching the "mostly distinct, minor overlap risk" anchor rather than 5.	4 / 5
	Total	15 / 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: ee44d1e

Reviewed: 19 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.