baoyu-xhs-images
Generates Xiaohongshu (Little Red Book) infographic series with 11 visual styles and 8 layouts. Breaks content into 1-10 cartoon-style images optimized for XHS engagement. Use when user mentions "小红书图片", "XHS images", "RedNote infographics", "小红书种草", or wants social media infographics for Chinese platforms.
89
81%
Does it follow best practices?
Impact
97%
2.15xAverage score across 6 eval scenarios
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 an excellent skill description that clearly defines a specific niche (Xiaohongshu infographic generation), lists concrete capabilities with quantified parameters (11 styles, 8 layouts, 1-10 images), and provides comprehensive bilingual trigger terms. The explicit 'Use when' clause with both Chinese and English keywords ensures reliable skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and parameters: generates infographic series, 11 visual styles, 8 layouts, breaks content into 1-10 cartoon-style images, optimized for XHS engagement. Very detailed and concrete. | 3 / 3 |
Completeness | Clearly answers both 'what' (generates Xiaohongshu infographic series with specific styles, layouts, and cartoon-style images) and 'when' (explicit 'Use when' clause with specific trigger phrases and a general use case). | 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', 'social media infographics for Chinese platforms'. Covers multiple language variations users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche targeting Xiaohongshu/XHS platform specifically, with Chinese-language triggers and platform-specific terminology. Very unlikely to conflict with generic image generation or other social media skills. | 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 is a highly actionable and well-structured skill with excellent workflow clarity, featuring blocking steps, multiple user paths, and explicit validation checkpoints. However, it severely violates conciseness by inlining extensive reference material (preset galleries, compatibility matrices, auto-selection tables) that should live in the referenced files. The progressive disclosure structure exists but is undermined by the sheer volume of inline content.
Suggestions
Move the Preset Gallery tables, Style×Layout Matrix, and Auto Selection table to their respective reference files (e.g., references/style-presets.md, references/elements/canvas.md) and replace with brief summaries linking to those files.
Reduce the Style Gallery to just the style names and a one-line summary table, pointing to references/presets/<style>.md for details — the descriptions are already stored there.
Consolidate the Outline Strategies section to a brief 3-line summary table, moving the detailed YAML front matter example and differentiation requirements to references/workflows/outline-template.md.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~400+ lines. It includes extensive tables for preset galleries, auto-selection mappings, style×layout matrices, and detailed workflow descriptions that could be offloaded to reference files. Much of this content (e.g., the full preset gallery, the compatibility matrix) belongs in reference documents rather than the main SKILL.md. | 1 / 3 |
Actionability | The skill provides highly concrete, executable guidance: specific bash/powershell commands for checking preferences, exact file naming conventions, YAML front matter examples for outlines, precise prompt patterns for image generation with --ref flags, and detailed AskUserQuestion interaction patterns. The workflow steps are copy-paste actionable. | 3 / 3 |
Workflow Clarity | The workflow is exceptionally well-sequenced with a progress checklist, ASCII flow diagram, explicit blocking steps (⛔), required confirmations (⚠️), three distinct user paths (Quick/Customize/Detailed), backup rules for conflict resolution, and clear validation points. The reference image chain ensures visual consistency with explicit ordering requirements. | 3 / 3 |
Progressive Disclosure | The skill does reference external files appropriately (references/config/, references/workflows/, references/presets/) and has clear navigation to them. However, the main SKILL.md itself is a monolithic wall containing extensive content that should be in those reference files — the full preset gallery tables, the style×layout compatibility matrix, and the auto-selection table all belong in reference documents rather than inline. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
63%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 7 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (591 lines); consider splitting into references/ and linking | Warning |
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 | 7 / 11 Passed | |
- Repository
- jimliu/baoyu-skills
- Commit
9eb032a
- 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.