← 返回 Skills 市场

turing-shikuan-skill

Name: turing-shikuan-skill
Author: xyyyyyaa

作者 xyyyyyaa · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ⚠ suspicious

总下载

当前安装

版本数

在 OpenClaw 中安装

/install turing-shikuan-skill

功能描述

当用户希望识别商品图片中的品类、品牌、系列或简要商品信息时，优先调用已配置的 turing-shikuan-mcp，并按固定格式输出识款结果；支持首次配置指引，但不用于真假鉴定、真伪判断或质量判断。

安全使用建议

This skill appears to do what it says (call a turing MCP to identify product info), but note two issues before installing or running setup.sh: - The skill requires API Key/Secret (TURING_SHIKUAN_API_KEY/TURING_SHIKUAN_API_SECRET or TURING_API_KEY/TURING_API_SECRET) though the registry metadata does not declare them. Expect to provide these credentials in your environment if you use it. - The setup.sh will attempt to install 'mcporter' globally via 'npm install -g mcporter' if it isn't present. Installing global npm packages can run arbitrary code from the npm registry; verify the 'mcporter' package's reputation/source before running, or prefer to install it manually after review. If you are uncomfortable: (1) do not run setup.sh; (2) configure the MCP manually in a safe way (e.g., via your mcporter CLI after vetting it); (3) only provide API keys to trusted endpoints and consider using scoped/project credentials. If possible, ask the skill author to update the registry metadata to declare the required environment variables and to avoid unpinned global npm installs.

功能分析

Type: OpenClaw Skill Name: turing-shikuan-skill Version: 1.0.0 The skill bundle is a legitimate tool for product identification using the 'turing-shikuan-mcp' server. It includes a setup script (setup.sh) that automates the configuration of the MCP server using the 'mcporter' utility and requires API credentials to be provided via environment variables. The instructions in SKILL.md are clearly defined, providing specific execution rules, output templates, and scope limitations (e.g., explicitly stating it does not perform authenticity checks) to ensure the agent behaves as intended without any evidence of malicious intent or data exfiltration.

能力评估

ℹ Purpose & Capability

Skill name/description match the instructions: it calls a turing-shikuan-mcp to identify product kind/brand/series/summary. However, the SKILL.md requires API Key/Secret for the MCP but the skill metadata lists no required environment variables or primary credential, causing an inconsistency between declared requirements and actual runtime needs.

✓ Instruction Scope

SKILL.md stays on-topic: it only describes configuring the MCP and calling it with an image_url, extracting specific fields, and avoiding guessing or authentication/quality judgments. It does instruct the user/agent to run setup.sh to register the MCP and to set environment variables for API credentials; it does not attempt to read unrelated files or exfiltrate other data.

⚠ Install Mechanism

There is no registry install spec, but the included setup.sh may be executed per the instructions; it will run 'npm install -g mcporter' if mcporter is missing. Installing a global npm package from the public registry without pinning/version or verifying the package introduces moderate risk (arbitrary code execution via npm package). The setup script itself is short and appears to only register the MCP, but the npm install step is the notable risk.

⚠ Credentials

SKILL.md requires API credentials (TURING_SHIKUAN_API_KEY/SECRET or TURING_API_KEY/SECRET) to register the MCP and the setup.sh reads them. The registry metadata, however, declares no required env vars or primary credential. That mismatch is concerning because the skill will prompt for credentials at runtime but did not declare them up-front in its metadata.

✓ Persistence & Privilege

The skill is instruction-only and not marked always:true. The setup.sh registers an MCP entry with mcporter at project scope (local), which is a limited change and not a system-wide privilege escalation. The skill does not attempt to modify other skills or system configs beyond mcporter project scope.

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 turing-shikuan-skill
安装完成后，直接呼叫该 Skill 的名称或使用 /turing-shikuan-skill 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

Initial release of turing-shikuan-demo, focusing on product image recognition via turing-shikuan-mcp. - Supports product category, brand, series, and brief info extraction from image URLs using turing-shikuan-mcp - Provides step-by-step setup instructions and guides for first-time configuration (API Key/Secret setup, `setup.sh`) - Ensures strict distinction: only “识款” (product recognition), not authenticity, quality, or value judgments - Enforces a fixed output template and refusal to guess or supplement missing information - Includes robust error handling for unconfigured MCP, missing/invalid URLs, incomplete responses, and out-of-scope requests

元数据

Slug turing-shikuan-skill

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题

turing-shikuan-skill 是什么？

当用户希望识别商品图片中的品类、品牌、系列或简要商品信息时，优先调用已配置的 turing-shikuan-mcp，并按固定格式输出识款结果；支持首次配置指引，但不用于真假鉴定、真伪判断或质量判断。它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 84 次。

如何安装 turing-shikuan-skill？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install turing-shikuan-skill」即可一键安装，无需额外配置。

turing-shikuan-skill 是免费的吗？

是的，turing-shikuan-skill 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

turing-shikuan-skill 支持哪些平台？

turing-shikuan-skill 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 turing-shikuan-skill？

由 xyyyyyaa（@xyyyyyaa）开发并维护，当前版本 v1.0.0。