baoyu-xhs-images
[Deprecated: use baoyu-image-cards] Generates Xiaohongshu (Little Red Book) image card series with 12 visual styles, 8 layouts, and 3 color palettes. Breaks content into 1-10 cartoon-style image cards optimized for XHS engagement. Use when user mentions "小红书图片", "XHS images", "RedNote infographics", "小红书种草", "小绿书", "微信图文", "微信贴图", or wants social media infographic series for Chinese platforms.
65
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is a strong skill description that excels across all dimensions. It provides specific capabilities (styles, layouts, palettes, card counts), comprehensive bilingual trigger terms covering natural user phrases, and a clear 'Use when' clause. The deprecation notice at the start is a minor concern as it could cause confusion, but it doesn't detract from the description's quality for skill selection purposes.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and parameters: generates image card series, specifies 12 visual styles, 8 layouts, 3 color palettes, breaks content into 1-10 cartoon-style cards, and notes optimization for XHS engagement. | 3 / 3 |
Completeness | Clearly answers both 'what' (generates Xiaohongshu image card series with specific styles/layouts/palettes) and 'when' (explicit 'Use when' clause with detailed trigger terms and use cases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms in both Chinese and English: '小红书图片', 'XHS images', 'RedNote infographics', '小红书种草', '小绿书', '微信图文', '微信贴图', and the broader 'social media infographic series for Chinese platforms'. These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche targeting Xiaohongshu/Chinese social media image cards specifically. The deprecation notice even points to a successor skill, and the trigger terms are very platform-specific, making conflicts with other skills unlikely. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is extremely thorough and actionable with an excellent workflow structure featuring blocking gates, validation steps, and clear branching paths. However, it severely violates conciseness by inlining hundreds of lines of reference material (style matrices, preset tables, palette specs, tool resolution policies) that should live in the referenced files it already points to. The result is a monolithic document that would consume significant context window despite having a well-designed reference file structure.
Suggestions
Move the Style × Layout Matrix, full Presets tables, Auto-Selection table, and Palette hex definitions into their respective reference files (already listed in the References section) and keep only 2-3 example presets inline.
Condense the Image Generation Tools section to ~5 lines of priority rules and move the detailed resolution logic to a reference file like `references/config/image-backend-resolution.md`.
Trim the Confirmation Policy and Step 2 sections by moving the verbatim display templates and Path B/C detailed question flows entirely into `references/confirmation.md`, keeping only the high-level flow description inline.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Contains extensive tables, matrices, and configuration details that could be split into reference files. The Image Generation Tools section alone is a wall of policy text. Much of this (tool resolution logic, slug naming conventions, backup rules) could be in referenced files rather than inline. The skill explains many things Claude could infer or that belong in separate reference docs. | 1 / 3 |
Actionability | Highly actionable with concrete file paths, exact CLI options, specific workflow steps, YAML frontmatter examples, directory structures, and precise naming conventions. The workflow is copy-paste ready with clear commands and file operations. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with explicit blocking gates (Step 0 BLOCKING, Step 2 REQUIRED), clear sequencing (Steps 0-4), validation checkpoints (confirmation policy, backup rules), and error recovery (auto-retry on failure). The image-1 anchor chain is clearly explained as a critical consistency step. Path A/B/C branching is well-defined. | 3 / 3 |
Progressive Disclosure | References to external files are well-organized in the References table, and the skill correctly points to `references/` subdirectories. However, massive amounts of content that should be in those reference files is duplicated inline — the full style×layout matrix, all preset tables, auto-selection table, palette hex codes, and detailed confirmation flow descriptions are all inline rather than in the referenced files. The SKILL.md tries to be both overview and reference simultaneously. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 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 |
Total | 8 / 11 Passed | |
- Repository
- jimliu/baoyu-skills
- Commit
bd5745f
- 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.