baoyu-xhs-images

Generates infographic image card series with 12 visual styles, 8 layouts, and 3 color palettes. Breaks content into 1-10 cartoon-style image cards optimized for social media engagement. Use when user mentions "小红书图片", "小红书种草", "小绿书", "微信图文", "微信贴图", "image cards", "图片卡片", baoyu-xhs-images, or wants social media infographic series.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-architected, highly actionable skill body with a clear gated workflow and clean progressive disclosure into real reference files. Its only weakness is mild verbosity in the backend-resolution and policy prose.

Suggestions

Dedupe the 'Concrete tool names ... are examples — substitute the local equivalents' note (it appears in both User Input Tools and Image Generation Tools) into a single stated-once rule.

Trim the justificatory prose in the Image Generation Tools section (e.g., the quoted Codex imagegen description and the lengthy ⛔ rationale blocks) — keep the hard rule and one short reason, moving detail into references/codex-imagegen.md.

Consider relocating the large Auto-Selection and Style × Layout Matrix tables to a reference file, keeping only the pointer inline, to reduce the body's token footprint.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence (no basic-concept padding), but the ~485-line body repeats the 'substitute the local equivalent' disclaimer twice and includes lengthy justification prose (e.g., the quoted Codex imagegen description, extended backend-resolution caveats) that could be tightened or moved to references.	2 / 3
Actionability	Provides concrete, copy-paste-ready guidance: exact CLI flags, file-naming conventions (NN-{type}-{slug}.md), a directory tree, YAML frontmatter examples, and a linked executable invocation contract in references/codex-imagegen.md.	3 / 3
Workflow Clarity	A clearly sequenced Step 0–4 workflow with an explicit BLOCKING gate, validation checkpoints (verify prompt files exist before batching, backup-before-overwrite), and a retry-once feedback loop for failures — matching the highest anchor.	3 / 3
Progressive Disclosure	SKILL.md is an overview with one-level-deep, well-signaled references (verified present: presets/, palettes/, elements/, workflows/, config/), a navigation table mapping each file to its content, and content appropriately split across bundle files.	3 / 3
	Total	11 / 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.

A tight, third-person description that quantifies capabilities and provides explicit bilingual triggers covering both what and when. It hits the top anchor on every dimension with no fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete, quantified actions — 'infographic image card series with 12 visual styles, 8 layouts, and 3 color palettes' and 'Breaks content into 1-10 cartoon-style image cards' — matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what (generates styled image card series) and when via an explicit 'Use when user mentions ...' trigger clause, satisfying the highest anchor.	3 / 3
Trigger Term Quality	Covers natural user phrasings in both languages — '小红书图片', '小红书种草', '小绿书', '微信图文', '微信贴图', 'image cards', '图片卡片', baoyu-xhs-images — strong coverage of terms users would actually say.	3 / 3
Distinctiveness Conflict Risk	Clear niche (social-media infographic image-card series) with highly specific bilingual triggers unlikely to fire for unrelated skills.	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
referenced_paths_exist	Referenced path issues: 17 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: jimliu/baoyu-skills
Commit: c9a50cc

Reviewed: 3 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.