sn-image-imitate

Generates a new image that imitates the style of a reference image while updating content based on user intent. Uses a three-stage pipeline: image annotation (long caption), caption rewriting, and image generation. Use when user asks to "imitate style", "保持这个风格重画", "按这张图风格生成", or "style transfer with new content".

Quality

88%

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%

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 executable commands, but it is slightly over-padded with redundant defaults and inlines contract content that the referenced (but missing) bundle files should hold.

Suggestions

Provide the referenced bundle files (prompts/image_annotate.md, prompts/caption_rewrite.md, prompts/layout_review.md, and ../sn-image-base/SKILL.md) so the progressive-disclosure references resolve to real content.

De-duplicate parameter defaults: state them once in the Input Specification and reference them from the Workflow rather than repeating each default in both sections.

Move the large inline return-contract JSON and timing-schema notes into a dedicated reference file to reduce inline length and keep SKILL.md as an overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence, but carries avoidable redundancy — parameter defaults are restated in both the Input Specification and the Workflow, and the timing/model placeholder notes are padded — pulling it below the lean top anchor.	2 / 3
Actionability	Provides fully executable bash CLI invocations with concrete flags, explicit JSON return contracts, and copy-paste-ready commands for every pipeline step, matching the top anchor.	3 / 3
Workflow Clarity	Sequences a clear Step 0–3 pipeline with explicit parsing/validation checkpoints, a defined error-handling strategy, and a generate→review→fix-hint retry loop, matching the anchor for clear sequence with validation and feedback loops.	3 / 3
Progressive Disclosure	References are clearly signaled and one level deep, but the referenced files (prompts/image_annotate.md, prompts/caption_rewrite.md, prompts/layout_review.md, ../sn-image-base/SKILL.md, ../../docs/sn-image-generate_en.md) do not exist in the bundle, and substantial contract/spec content is inlined rather than split out.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 is specific, complete, and distinctive, with concrete natural-language and bilingual trigger terms plus an explicit 'Use when' clause. It uses third-person voice throughout and avoids vague fluff.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions across a clear pipeline — 'image annotation (long caption)', 'caption rewriting', and 'image generation' — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Explicitly answers both 'what' (generates a style-imitating image with updated content via a three-stage pipeline) and 'when' (an explicit 'Use when user asks to...' clause), matching the top anchor.	3 / 3
Trigger Term Quality	Provides natural user phrasings a person would actually say ('imitate style', 'style transfer with new content') plus bilingual variants ('保持这个风格重画', '按这张图风格生成'), giving good coverage of natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	Style imitation with content change is a clear niche with distinct triggers; the Non-goals section further separates it from pure style transfer, making conflict with other skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 suspicious	Warning

	Total	12 / 16 Passed

Repository: OpenSenseNova/SenseNova-Skills
Path: skills/sn-image-imitate/SKILL.md
Commit: 179fea1

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.