← 返回 Skills 市场
89
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install web3-agent-screener
功能描述
Web3 AI Agent 项目专业筛选评估工具。输入项目名称或描述，通过11维度专业框架进行深度评估，输出可投资级别评级、核心逻辑、风险提示及综合建议。适用于三年以上价值投资视角的项目筛选。
安全使用建议
This skill is instruction-only and internally consistent with its purpose. Before enabling it, verify what your agent's batch_web_search tool does (where queries are sent, logging/retention policies, and any rate limits). If you will supply private project data, confirm the platform won’t leak it in searches or logs. Treat its outputs as analytic assistance only — investment recommendations should be cross-checked against primary data sources and a qualified advisor; the screening thresholds and judgments are subjective and depend on data freshness and source reliability.
功能分析
Type: OpenClaw Skill
Name: web3-agent-screener
Version: 1.0.0
The skill is a legitimate tool designed to evaluate Web3 AI Agent projects based on a structured 11-dimension framework. It instructs the agent to perform market research using standard web search tools and generate a formatted investment report. No evidence of malicious intent, data exfiltration, or unauthorized execution was found in SKILL.md or _meta.json.
能力评估
Purpose & Capability
Name/description (Web3 project screener) matches the instructions: gather market/TVL/listing/investor data and run an 11-dimension evaluation. The skill does not request unrelated binaries, environment variables, or config paths.
Instruction Scope
SKILL.md confines runtime actions to searching public data (via batch_web_search), evaluating 11 specific dimensions, and producing a structured report. It does not instruct reading local files, accessing unrelated credentials, or transmitting data to unexpected endpoints. It does rely on the platform's batch_web_search capability for data collection.
Install Mechanism
No install spec and no code files — instruction-only. Nothing is downloaded or written to disk by the skill itself.
Credentials
The skill declares no required environment variables, credentials, or config paths — consistent with a public-data analysis tool.
Persistence & Privilege
always is false and default model invocation/autonomy is unchanged. The skill does not request persistent presence or modification of other skills/configuration.
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 web3-agent-screener - 安装完成后，直接呼叫该 Skill 的名称或使用
/web3-agent-screener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: 基于11维度评估框架的专业Web3 AI Agent项目筛选工具
元数据
常见问题
Web3 AI Agent项目专业筛选器 是什么？
Web3 AI Agent 项目专业筛选评估工具。输入项目名称或描述，通过11维度专业框架进行深度评估，输出可投资级别评级、核心逻辑、风险提示及综合建议。适用于三年以上价值投资视角的项目筛选。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 89 次。
如何安装 Web3 AI Agent项目专业筛选器？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install web3-agent-screener」即可一键安装，无需额外配置。
Web3 AI Agent项目专业筛选器 是免费的吗？
是的，Web3 AI Agent项目专业筛选器 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Web3 AI Agent项目专业筛选器 支持哪些平台？
Web3 AI Agent项目专业筛选器 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 Web3 AI Agent项目专业筛选器？
由 wgx2010（@wgx2010）开发并维护，当前版本 v1.0.0。
推荐 Skills