xhs-visual-director

Use this skill when planning, redesigning, or reviewing Xiaohongshu carousel visuals, covers, 3:4 image posts, page-by-page visual direction, image-generation prompts, style selection, layout critique, or XHS captions. It acts as a senior visual director for 小红书图文, not a generic copywriting assistant.

Quality

88%

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

Quality

Content

77%Weight 40%Scale 1-3

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 and has a well-sequenced workflow with strong validation gates, but it is verbose with heavy repetition and over-relies on inline content plus references to bundle files that are not actually present. Tightening duplication and materializing the referenced docs/templates would materially improve it.

Suggestions

Deduplicate repeated rules: state the 3:4 canvas constraint, the 10-question protocol, and the per-page field schema once in their canonical sections and reference them elsewhere rather than re-listing them multiple times.

Materialize the referenced bundle files (docs/style_system.md, docs/page_structure_rules.md, templates/*, examples/*) so the progressive-disclosure pointers resolve to real content, or remove the dangling references.

Move the full default output-format template and the per-page detailed field list into templates/xhs_carousel_plan_template.md and keep SKILL.md as a lean overview that links to it.

Dimension	Reasoning	Score
Conciseness	The ~555-line body restates the same constraints repeatedly (3:4 canvas, the 10-question protocol, per-page field lists, and the full output template appear in multiple sections), padding the token budget beyond what Claude needs. It is mostly efficient guidance but could be tightened significantly.	2 / 3
Actionability	Highly concrete and executable for an instruction-only skill — exact pixel dimensions ("1080x1440px"), margins ("左右 72px、上下 80px"), named fonts, literal negative-prompt strings, per-page field schemas, and a file-naming convention ("page-01.png") — copy-paste-ready specifics.	3 / 3
Workflow Clarity	A clear 10-step sequence (Step 1–Step 10) with explicit validation checkpoints: a visual-confirmation gate before batch generation (Step 6), an aspect-ratio consistency check (Step 9), and a self-check checklist, providing proper feedback loops for batch image generation.	3 / 3
Progressive Disclosure	References are well-signaled and one-level-deep ("按任务需要读取...不要一次性加载全部文档"), but none of the referenced docs/templates/examples files actually exist in the bundle, and large chunks of content (full output template, per-page schema) that belong in template files are inlined in SKILL.md.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 across all dimensions: it is specific, uses natural trigger terms, clearly answers both what and when with an explicit 'Use when' clause, and carves out a distinctive niche with disambiguation. No changes needed.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — "planning, redesigning, or reviewing Xiaohongshu carousel visuals, covers, 3:4 image posts, page-by-page visual direction, image-generation prompts, style selection, layout critique...XHS captions" — matching the multiple-specific-actions anchor, not the partial level 2.	3 / 3
Completeness	Explicit "Use this skill when..." trigger clause (when) plus a clear statement of what it does ("acts as a senior visual director for 小红书图文"), clearly answering both what and when.	3 / 3
Trigger Term Quality	Uses natural user-facing terms ("Xiaohongshu", "小红书图文", "covers", "3:4 image posts", "XHS captions") covering common variants a user would actually say, satisfying the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	Highly specific niche (Xiaohongshu visual direction) with distinct triggers and an explicit disambiguator ("not a generic copywriting assistant"), making conflicts with other skills unlikely.	3 / 3
	Total	12 / 12 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
skill_md_line_count	SKILL.md is long (560 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: ziguishian/xhs-visual-director-skill
Path: skill/SKILL.md
Commit: 5c730c6

Reviewed: 13 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.