baoyu-image-gen
AI image generation with OpenAI, Azure OpenAI, Google, OpenRouter, DashScope, 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.
74
71%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/baoyu-image-gen/SKILL.mdQuality
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 communicates what the skill does (AI image generation across multiple API providers with specific capabilities), when to use it (user asks to generate/create/draw images), and even provides nuanced guidance on sequential vs batch parallel modes. It uses third person voice throughout, includes natural trigger terms, and is distinctive enough to avoid conflicts with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and capabilities: text-to-image generation, reference images, aspect ratios, batch generation from saved prompt files, sequential vs batch parallel generation. Also enumerates specific API providers (OpenAI, Azure OpenAI, Google, OpenRouter, DashScope, MiniMax, Jimeng, Seedream, Replicate). | 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 generation). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'generate', 'create', 'draw images', 'image generation', 'text-to-image', 'reference images', 'aspect ratios', 'batch generation', 'prompts'. Also names specific API providers which serve as trigger terms for users requesting those services. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: AI image generation via specific named APIs. The enumeration of providers and specific capabilities (text-to-image, reference images, batch generation) makes it very unlikely to conflict with other skills. The domain is well-defined and distinct. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is highly actionable with excellent concrete examples and CLI commands, but it is severely bloated — the inline content reads more like comprehensive API documentation than a concise skill guide. Provider-specific model details, environment variable tables, and size recommendation tables should be moved to reference files, leaving only a lean overview in SKILL.md. The deprecation notice at the top also raises the question of why this content exists at all.
Suggestions
Move provider-specific model details (DashScope models, MiniMax models, OpenRouter models, Replicate models) into separate reference files (e.g., references/providers/dashscope.md) and link to them from a brief provider table in SKILL.md.
Move the environment variables table to a dedicated reference file (e.g., references/config/env-vars.md) — Claude doesn't need 30+ env var definitions inline for every invocation.
Add explicit post-generation validation steps (e.g., 'Verify output file exists and is non-zero size') to improve workflow clarity for both single and batch generation.
Since the skill is deprecated, consider reducing the entire body to just the deprecation warning and a pointer to baoyu-imagine, rather than maintaining hundreds of lines of now-obsolete documentation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is extremely verbose at ~400+ lines, with exhaustive listings of environment variables, model details, provider-specific notes, and DashScope size tables that could easily be in reference files. Much of this is reference documentation that Claude doesn't need inline — it bloats the context window significantly. | 1 / 3 |
Actionability | The skill provides fully executable CLI commands with concrete examples for every provider, batch file JSON format, and specific flag usage. Commands are copy-paste ready with clear parameter explanations. | 3 / 3 |
Workflow Clarity | Step 0 (Load Preferences) is clearly sequenced with a blocking gate and validation table, and the deprecation warning at the top is explicit. However, the overall generation workflow lacks explicit validation checkpoints — there's no 'verify the output image exists' or error recovery loop beyond mentioning auto-retry. The decision tables for batch vs sequential are helpful but the end-to-end workflow is implicit. | 2 / 3 |
Progressive Disclosure | The skill is a monolithic wall of text with massive inline reference content (DashScope model families, MiniMax details, OpenRouter models, environment variables, size tables) that should be split into separate reference files. Only a few references point to external files (first-time-setup.md, preferences-schema.md) while hundreds of lines of provider-specific documentation remain inline. | 1 / 3 |
Total | 7 / 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
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.