baoyu-image-gen
AI image generation with OpenAI, Google and DashScope APIs. Supports text-to-image, reference images, aspect ratios. Sequential by default; parallel generation available on request. Use when user asks to generate, create, or draw images.
Install with Tessl CLI
npx tessl i github:jimliu/baoyu-skills --skill baoyu-image-genOverall
score
93%
Does it follow best practices?
Validation for skill structure
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 well-crafted skill description that hits all the key criteria. It specifies concrete capabilities (text-to-image, reference images, aspect ratios), names the specific APIs used, includes natural trigger terms users would say, and has an explicit 'Use when' clause. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'text-to-image, reference images, aspect ratios' and specifies three distinct APIs (OpenAI, Google, DashScope). Also clarifies execution modes (sequential/parallel). | 3 / 3 |
Completeness | Clearly answers both what ('AI image generation with OpenAI, Google and DashScope APIs. Supports text-to-image, reference images, aspect ratios') AND when ('Use when user asks to generate, create, or draw images') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'generate', 'create', 'draw images'. These are common verbs users naturally use when requesting image generation. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on AI image generation with specific API providers named. The triggers 'generate, create, or draw images' are distinct and unlikely to conflict with document processing or other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
88%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-crafted skill with excellent conciseness and actionability. The command examples are comprehensive and the option tables are clear. The main weakness is the lack of explicit validation steps for verifying generated images or handling failures in batch operations, which is important for a tool that creates files.
Suggestions
Add a validation step after generation (e.g., verify output file exists and has expected size/format)
Include explicit error recovery workflow for batch generation failures (e.g., which images succeeded, how to retry failed ones)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, using tables for structured data and avoiding unnecessary explanations. It assumes Claude understands CLI tools, environment variables, and API concepts without over-explaining. | 3 / 3 |
Actionability | Provides fully executable bash commands with multiple usage examples covering basic, advanced, and provider-specific scenarios. All commands are copy-paste ready with clear option documentation. | 3 / 3 |
Workflow Clarity | While the skill documents options and error handling well, it lacks explicit validation checkpoints. The generation workflow doesn't specify how to verify successful output or handle partial failures in batch operations. | 2 / 3 |
Progressive Disclosure | Well-organized with clear sections (Usage, Options, Environment Variables, etc.). References EXTEND.md for customization without deep nesting. Tables effectively organize structured information. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
88%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 14 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
Total | 14 / 16 Passed | |
- 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.