baoyu-danger-gemini-web
Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Use when other skills need image generation backend, or when user requests "generate image with Gemini", "Gemini text generation", or needs vision-capable AI generation.
86
86%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 clearly articulates specific capabilities (text generation, image generation, vision input, multi-turn conversations), names the underlying technology (reverse-engineered Gemini Web API), and provides explicit trigger guidance with natural user phrases. The description is concise, uses third-person voice, and is distinctive enough to avoid conflicts with other generation-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Also specifies the mechanism (reverse-engineered Gemini Web API). | 3 / 3 |
Completeness | Clearly answers both 'what' (generates images and text via Gemini Web API with specific capabilities) and 'when' (explicit 'Use when' clause covering both programmatic use by other skills and direct user requests with trigger phrases). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'generate image with Gemini', 'Gemini text generation', 'image generation', 'vision-capable AI generation'. These cover common user phrasings well. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific 'Gemini Web API' and 'reverse-engineered' qualifiers. The triggers are clearly scoped to Gemini-based generation, making it unlikely to conflict with other image generation or text generation skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%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 skill with strong actionability through concrete CLI examples and comprehensive option/model reference tables. Its main weaknesses are the lack of error handling/validation guidance for the core generation workflows and some verbosity in ancillary sections like the User Input Tools preamble. The progressive disclosure and organization are good, with appropriate separation of concerns.
Suggestions
Add error handling guidance for common failure modes: authentication failures, cookie expiration, image generation errors, and network/proxy issues.
Trim the 'User Input Tools' section—Claude doesn't need a generic tool-selection algorithm explained in every skill; a single sentence referencing the consent check would suffice.
Remove the redundant 'Extension Support' section at the bottom since it just points back to the Preferences section already documented above.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of tables and code blocks, but includes some unnecessary sections like the detailed 'User Input Tools' preamble and the 'Extension Support' section that just points back to Preferences. The consent check flow is somewhat verbose for what it conveys. | 2 / 3 |
Actionability | Provides fully executable CLI commands with concrete examples covering all major use cases (text generation, image generation, vision input, multi-turn conversations, JSON output). Options and environment variables are clearly documented in tables with specific flag names and defaults. | 3 / 3 |
Workflow Clarity | The consent check flow is well-sequenced with clear steps, and the script directory resolution has numbered steps. However, there are no validation checkpoints or error recovery steps for the main generation workflows—no guidance on what to do if authentication fails, if image generation produces errors, or if cookie refresh doesn't work. | 2 / 3 |
Progressive Disclosure | Content is well-structured with clear sections, appropriate use of tables for reference material, and references to external files (EXTEND.md, scripts/) that are one level deep and clearly signaled. The skill overview stays at the right level of detail for a SKILL.md. | 3 / 3 |
Total | 10 / 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.