pw-danger-gemini-web
pw-danger-gemini-web is an LLM app frameworks & APIs skill for AI agents, published by plugins-world in the pw-skills repository on GitHub. Skillspace rates pw-danger-gemini-web D (56/100) and it passed the safety scan; the rating is based on static analysis only.
通过逆向工程的 Gemini Web API 进行文本和图像生成。 核心能力: - 文本生成: 使用 Gemini 模型生成文本响应 - 图像生成: 从文本提示生成图像并保存到本地 - 视觉输入: 支持参考图像进行图生图或图生文 - 多轮对话: 通过 sessionId 保持上下文连续性 使用时机: - 需要生成高质量 AI 图像时 (封面图、配图、插画等) - 需要 Gemini 模型进行文本生成时 - 需要基于参考图像生成变体或描述时 - 作为其他技能 (pw-cover-image、pw-redbook-image) 的图像生成后端 不适用场景: - 需要官方 API 支持和稳定性保证的生产环境 - 对 API 变更敏感的关键业务流程 - 需要批量高频调用的场景 (可能触发限流) 重要提醒: - 首次使用需要用户同意免责声明 - 需要 Google 账号认证 (自动打开浏览器登录) - 在中国大陆需要配置代理访问 - 这是非官方 API, 可能随时失效
- Grade
- D
- Quality
- 56 / 100
- Safety
- Passed
- GitHub stars
- 22
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 67 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 0 collections
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.