CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

65

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

72%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 delivers highly actionable, well-sequenced guidance with strong validation and retry loops, but it is verbose and keeps large JSON contract/output templates inline. Progressive disclosure is undercut by referenced prompt files that are absent from the bundle and by inlined content that would be better split into reference files.

Suggestions

Move the full Return Contract JSON and the verbose-mode output template into separate reference files and link to them, leaving only a concise summary inline to improve conciseness and progressive_disclosure.

Add the missing prompts/ files (image_annotate.md, caption_rewrite.md, layout_review.md) to the bundle so the references section points to real artifacts.

Trim the repeated full JSON examples and inline restatement of input defaults; reference the Input Specification once instead of re-listing default values in the workflow steps.

DimensionReasoningScore

Conciseness

The body is mostly efficient and well-structured but runs long (~370 lines) with repeated full JSON contract examples, verbose timing/format notes, and some inline restatement of defaults; it could be tightened by moving the full Return Contract and verbose-mode templates into references. It is not severely padded (above 3 would require trimming those inline blocks), but the bulk of inline JSON examples keeps it at the 'mostly efficient but could be tightened' anchor rather than 4.

3 / 5

Actionability

Provides fully executable, copy-paste-ready CLI commands for each pipeline step (sn_agent_runner.py invocations with concrete flags), explicit JSON parse instructions, and concrete expected output schemas covering the common cases.

5 / 5

Workflow Clarity

The multi-step process is clearly sequenced (Step 0-3) with explicit validation checkpoints (parse-failure returns error, layout-threshold pass/early-termination check, retry-with-fix-hints feedback loop) matching the validate->fix->retry pattern rewarded by the 5 anchor.

5 / 5

Progressive Disclosure

Structure and a References section exist, but the referenced prompt files (prompts/image_annotate.md, caption_rewrite.md, layout_review.md) are not present in the bundle, and large blocks (full Return Contract JSON, verbose output template) are inlined rather than split into separate files; this matches 'some structure but could be better organized / content that should be separate is inline' rather than 4.

3 / 5

Total

16

/

20

Passed

Description

91%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 is strong: it clearly states what the skill does, when to use it, and provides comprehensive bilingual trigger phrases with low conflict risk. The only minor weakness is that the listed actions lean toward pipeline-stage labels rather than user-facing capability verbs.

DimensionReasoningScore

Specificity

Lists several concrete actions ('imitates the style', 'image annotation (long caption)', 'caption rewriting', 'image generation') but the actions are somewhat pipeline-phase labels rather than end-user-facing capabilities, leaving minor coverage gaps, so it sits above the 3 anchor but not fully comprehensive at 5.

4 / 5

Completeness

Explicitly answers both 'what' (generates a new image imitating style with updated content via a three-stage pipeline) and 'when' ('Use when user asks to...') with concrete trigger phrases, matching the 5 anchor exactly.

5 / 5

Trigger Term Quality

Includes comprehensive natural trigger phrases in both English and Chinese that users would actually say ('imitate style', '保持这个风格重画', '按这张图风格生成', 'style transfer with new content'), covering synonyms and bilingual variations.

5 / 5

Distinctiveness Conflict Risk

The niche is clear (style imitation with content change, not pure style transfer) and triggers are distinctive bilingual phrases unlikely to collide with unrelated skills, fitting the clear-niche/minimal-conflict anchor.

5 / 5

Total

19

/

20

Passed

Validation

75%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
Reviewed

Table of Contents

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.