baoyu-image-gen
[Deprecated: use baoyu-imagine] AI image generation with OpenAI, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream and Replicate APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.
91
92%
Does it follow best practices?
Impact
Pending
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 description that clearly communicates what the skill does (AI image generation across multiple API providers with various features), when to use it (when users ask to generate/create/draw images), and provides operational guidance (sequential vs batch parallel). The deprecation notice is helpful for skill selection, and the enumeration of specific providers and capabilities makes it highly distinctive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions and capabilities: text-to-image, reference images, aspect ratios, batch generation from saved prompt files, sequential vs batch parallel generation. Also enumerates specific API providers. | 3 / 3 |
Completeness | Clearly answers both 'what' (AI image generation with multiple APIs, supporting text-to-image, reference images, aspect ratios, batch generation) and 'when' (explicit 'Use when user asks to generate, create, or draw images' clause, plus guidance on when to use batch parallel mode). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'generate', 'create', 'draw images'. Also mentions specific provider names (OpenAI, Google, etc.) and technical terms like 'text-to-image', 'reference images', 'aspect ratios' that users might naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: AI image generation via specific API providers. The deprecation notice and specific provider list make it very unlikely to conflict with unrelated skills. The mention of the replacement skill 'baoyu-imagine' further clarifies its identity. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill that covers a complex multi-provider image generation system. Its greatest strength is the clear progressive disclosure pattern and concrete CLI examples. The main weakness is moderate verbosity in some sections (environment variables, dialect explanations, generation mode table) that could be trimmed or moved to reference files, though much of this information is genuinely necessary configuration detail.
Suggestions
Consider moving the full environment variables table to a reference file (e.g., references/config/env-vars.md) and keeping only the most common 3-4 variables inline to improve conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some sections that could be tightened — e.g., the extensive environment variables table, the dialect explanation, and the generation mode decision table are verbose. However, much of this is genuinely novel configuration information Claude wouldn't know, so it's not egregiously padded. | 2 / 3 |
Actionability | Provides fully executable CLI commands with concrete flags, complete usage examples covering basic through advanced scenarios, and specific environment variable names. The batch file, provider selection, and model resolution are all concretely specified with copy-paste ready commands. | 3 / 3 |
Workflow Clarity | Step 0 is explicitly marked as BLOCKING with clear sequencing (check paths → load or run setup → then generate). The generation mode section provides clear decision criteria. Error handling includes retry logic and specific failure behaviors. The preference loading has a well-defined priority chain (CLI > EXTEND.md > env vars > .env files). | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure — the main SKILL.md provides a clear overview with minimum working examples, then points to one-level-deep references for provider-specific guides, usage examples, preferences schema, and first-time setup. The references table at the bottom provides clean navigation. No nested reference chains. | 3 / 3 |
Total | 11 / 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
505a7e1
- 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.