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.
Install with Tessl CLI
npx tessl i github:jimliu/baoyu-skills --skill baoyu-danger-gemini-webOverall
score
89%
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 strong skill description that clearly articulates specific capabilities (text generation, image generation, vision input, multi-turn conversations), uses natural trigger terms users would actually say, and includes an explicit 'Use when...' clause. The mention of 'reverse-engineered Gemini Web API' and Gemini-specific triggers make it highly distinctive from other potential image generation 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.' These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (generates images and text, supports text generation, image generation, vision input, multi-turn conversations) AND when (explicit 'Use when...' clause with specific triggers for both skill-to-skill and user-facing scenarios). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'generate image with Gemini', 'Gemini text generation', 'vision-capable AI generation', 'image generation', and 'reference images'. Good coverage of natural terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with 'Gemini' as a clear differentiator, 'reverse-engineered Gemini Web API' is unique, and specific triggers like 'generate image with Gemini' create a clear niche unlikely to conflict with other image generation skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
80%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides excellent actionable guidance with efficient, well-organized reference tables and executable commands. The consent check workflow is well-defined, but the main generation workflows lack error handling and validation steps. Some sections like script directory instructions could be tightened, and EXTEND.md support details are incomplete.
Suggestions
Add validation/error handling guidance for generation commands (e.g., what to check if image generation fails, how to verify output)
Specify what settings EXTEND.md actually supports instead of just listing 'Default model | Proxy settings | Custom data directory' - provide example format
Simplify the script directory section - the 3-step agent execution instructions could be reduced to a single note about script location
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is lean and efficient, using tables for options/models/env vars instead of verbose prose. No unnecessary explanations of concepts Claude already knows. | 3 / 3 |
Actionability | Provides fully executable commands with concrete examples covering text generation, image generation, vision input, multi-turn conversations, and JSON output. All commands are copy-paste ready. | 3 / 3 |
Workflow Clarity | The consent check flow is well-sequenced with clear steps, but the main usage section lacks validation checkpoints. No guidance on error handling or verification that generation succeeded before proceeding. | 2 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but references to EXTEND.md are vague ('See Preferences section for paths and supported options') without detailing what those options actually are. The script directory explanation is somewhat verbose for what could be simpler. | 2 / 3 |
Total | 10 / 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.