← 返回 Skills 市场
Whisk Ai
作者
linmillsd7
· GitHub ↗
· v1.0.0
· MIT-0
65
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install whisk-ai
功能描述
Drop an image and describe a new scene — whisk-ai blends your visual inputs with creative AI generation to produce entirely fresh imagery. Built around Googl...
安全使用建议
This skill will upload any images you give it to a third-party API (mega-api-prod.nemovideo.ai) and will obtain or use a NEMO_TOKEN for authorization. The publisher/source and homepage are missing, and the SKILL.md claims Google 'Imagen' tech while calling an unknown domain — ask the publisher for provenance and a privacy/terms URL before trusting sensitive content. Also clarify whether the skill actually needs access to ~/.config/nemovideo/ (the frontmatter lists it but the registry metadata did not). If you decide to proceed: avoid uploading private or sensitive photos, review any returned URLs before clicking, and prefer skills from verified sources or with public documentation.
功能分析
Type: OpenClaw Skill
Name: whisk-ai
Version: 1.0.0
The whisk-ai skill is a legitimate integration for an AI image remixing service hosted on the nemovideo.ai platform. The SKILL.md file provides functional instructions for the agent to manage sessions, handle anonymous authentication via a UUID-based token exchange, and interact with a server-side image generation API. It includes appropriate error handling and security-conscious instructions (e.g., advising the agent not to expose raw tokens). No evidence of data exfiltration, malicious execution, or unauthorized access was found.
能力标签
能力评估
Purpose & Capability
The name/description (image remixing) aligns with the runtime behavior: uploading images, creating sessions, and requesting generations from a remote API. However: the skill claims to be built around Google's Whisk/Imagen tech while all network calls target mega-api-prod.nemovideo.ai (an unknown domain) — that mismatch is unexplained. The SKILL.md frontmatter also declares a config path (~/.config/nemovideo/) that the registry metadata did not list, and the skill has no public homepage or source repository to validate the backend claims.
Instruction Scope
Instructions are explicit about creating a session, uploading images, using SSE for streaming responses, polling for export, and including attribution headers. These are in-scope for an image-generation skill. It also instructs detecting install path and reading this SKILL.md frontmatter at runtime to fill attribution headers (requires reading the agent's environment/files). The skill will POST user images and prompts to the external nemovideo.ai API — this is expected for cloud processing but has privacy implications (user uploads leave the local environment).
Install Mechanism
This is instruction-only with no install spec and no code files, so nothing is written to disk by an installer. Lowest install-surface risk.
Credentials
Only NEMO_TOKEN is required, which is appropriate for a remote API. However, the SKILL.md metadata also mentions a config path (~/.config/nemovideo/) not declared elsewhere in the registry metadata, creating an inconsistency: either the skill expects to read/write that config directory (broader access than declared) or the metadata is stale/incorrect. The skill also will accept/issue an anonymous token if NEMO_TOKEN is absent, which means it will contact the remote API to obtain credentials on the fly — a behavior you should be aware of before uploading sensitive images.
Persistence & Privilege
The skill is not always-enabled and does not request system-wide persistence. It will create ephemeral sessions/tokens for operations, which is consistent with a remote-processing image skill. Autonomous invocation is allowed by default (platform normal) and not by itself a problem here.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install whisk-ai - 安装完成后，直接呼叫该 Skill 的名称或使用
/whisk-ai触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Whisk AI Image Remixer 1.0.0
- Initial release of Whisk AI, a tool for remixed image generation using Google’s Imagen backend.
- Enables creative blending of up to three input images (subject, scene, style) and text prompts for new AI-generated visuals.
- Automated credential setup with anonymous token and session management (includes 100 free credits, 7-day expiry).
- Supports upload, credits check, session state, and export to multiple formats (jpg, png, gif, mp4, etc).
- Robust error handling and clear user feedback for setup, session state, and common API issues.
元数据
常见问题
Whisk Ai 是什么？
Drop an image and describe a new scene — whisk-ai blends your visual inputs with creative AI generation to produce entirely fresh imagery. Built around Googl... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 65 次。
如何安装 Whisk Ai？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install whisk-ai」即可一键安装，无需额外配置。
Whisk Ai 是免费的吗？
是的，Whisk Ai 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Whisk Ai 支持哪些平台？
Whisk Ai 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Whisk Ai？
由 linmillsd7（@linmillsd7）开发并维护，当前版本 v1.0.0。
推荐 Skills