← 返回 Skills 市场
69
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install wisgate-models
功能描述
Query Wisgate for model pricing, capabilities, and configuration details. Use when adding a model to OpenClaw, comparing Wisgate pricing, or checking if a mo...
安全使用建议
This skill appears to do what it says (manage Wisgate models) but its documentation is incomplete and expects local assets and an API key that are not declared in the metadata. Before installing or letting the agent run it autonomously: 1) Verify the Firecrawl script exists at ~/.openclaw/workspace/skills/firecrawl-search/scripts/scrape.py and inspect its code to ensure it only scrapes the intended pages. 2) Find where FIRECRAWL_API_KEY is stored (TOOLS.md is referenced) and avoid putting unrelated secrets there; prefer declaring required env vars explicitly. 3) Back up MODELS.json and openclaw.json before allowing the skill to edit them. 4) If you do not want config changes made automatically, restrict autonomous invocation or require manual approval for writes. Clarifying these missing metadata items (required env var, config paths, and the Firecrawl dependency) would raise confidence.
功能分析
Type: OpenClaw Skill
Name: wisgate-models
Version: 0.1.0
The skill bundle is a utility for managing AI model configurations and pricing data specifically for the Wisgate provider. It provides instructions for the agent to query a local 'MODELS.json' file, update 'openclaw.json' configurations, and scrape model details from 'wisgate.ai' using an external Firecrawl script. The logic is consistent with its stated purpose of model management and lacks indicators of malicious intent or data exfiltration.
能力标签
能力评估
Purpose & Capability
The name/description align with the instructions: the skill is about adding and inspecting Wisgate models and mapping them into OpenClaw config. However, the SKILL.md expects access to local OpenClaw files (MODELS.json, openclaw.json, TOOLS.md) and a Firecrawl script in a specific path (~/.openclaw/workspace/skills/...), yet the skill metadata declares no required files, binaries, or environment variables. That mismatch suggests incomplete metadata or sloppy documentation.
Instruction Scope
Instructions tell the agent to read and write local configuration files (MODELS.json, openclaw.json), and to run a local Python scraper script that will fetch pages from https://wisgate.ai. They also reference an environment variable (FIRECRAWL_API_KEY) and TOOLS.md for the key. The skill text does not explicitly limit what other files or env vars may be read; relying on unspecified local files and keys broadens scope beyond what's declared.
Install Mechanism
There is no install spec and no code files (instruction-only), which is the lowest-risk install mechanism. The main risk comes from instructions invoking an external local script rather than from any install process.
Credentials
The SKILL.md uses FIRECRAWL_API_KEY but the skill metadata lists no required environment variables or primary credential. It also expects access to TOOLS.md and to modify MODELS.json and openclaw.json. Requesting these local files/keys would be reasonable for the stated purpose, but the omission from metadata is an incoherence that should be resolved before use.
Persistence & Privilege
The skill is not always-loaded and is user-invocable, which is appropriate. It does instruct modifying agent configuration files (MODELS.json, openclaw.json) — normal for a model-management helper — but you should be aware it expects permission to write those configs.
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 wisgate-models - 安装完成后，直接呼叫该 Skill 的名称或使用
/wisgate-models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
v0.1.0
First public version.
Context: https://wisgate.ai/ provide low-cost API access to a large number of models (from OpenAI, Anthropic, Google, xAI and others); this skill is for your Lobster to set itself up with access to them if you have an API key (which you'll need to get from Wisgate by signing up and paying). The API supports OpenAI, Anthropic, and Google styles.
- contains a brief description on creating for itself a MODELS.json file with all relevant data on available models from any API provider, but doesn't go into much detail.
**TODO: script or skill to pre-populate MODELS.json with info from https://wisgate.ai/models**
- assumes you have Firecrawl set up for efficient searching (especially to access the Wisgate models page, which is heavily Javascript based and therefore may be a challenge for other scripted ways of accessing), and there's a Firecrawl skill & scripts to do so;
**TODO: make this a less explicit dependency, suggest scraping pages in other ways**
- assumes certain provider names in openclaw.json ;
**TODO: make this more flexible, or add management of providers to the skill**
- assumes an auth profile to exist in openclaw.json that defines "wisgate", with "mode":"api_key"
- assumes providers in openclaw.json named
- "custom-api-wisgate-ai" (with "baseUrl":"https://api.wisgate.ai/", and "api": "anthropic-messages")
- "custom-api-wisgate-google" (with "baseUrl": "https://api.wisgate.ai/v1beta", and "api": "google-generative-ai")
- "custom-api-wisgate-ai-openai" (with "baseUrl": "https://api.wisgate.ai/v1", and "api": "openai-completions")
元数据
常见问题
Manage OpenClaw's use of models available at wisgate.ai API 是什么？
Query Wisgate for model pricing, capabilities, and configuration details. Use when adding a model to OpenClaw, comparing Wisgate pricing, or checking if a mo... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 69 次。
如何安装 Manage OpenClaw's use of models available at wisgate.ai API？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install wisgate-models」即可一键安装，无需额外配置。
Manage OpenClaw's use of models available at wisgate.ai API 是免费的吗？
是的，Manage OpenClaw's use of models available at wisgate.ai API 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Manage OpenClaw's use of models available at wisgate.ai API 支持哪些平台？
Manage OpenClaw's use of models available at wisgate.ai API 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 Manage OpenClaw's use of models available at wisgate.ai API？
由 flofrie（@flofrie）开发并维护，当前版本 v0.1.0。
推荐 Skills