← 返回 Skills 市场
crewhaus

CrewHaus Startup Validation

作者 crewhaus · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
268
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install crewhaus
功能描述
Quick startup idea evaluation from your terminal. Score ideas on 3 dimensions, run deeper scans with real competitor data and risk assessment. A structured t...
使用说明 (SKILL.md)

CrewHaus — Startup Idea Evaluation

Evaluate business ideas with a structured framework. Two tools: a quick score for fast reads, and a deeper scan that pulls real competitor data via web search.

This is a thinking tool, not a prediction engine. It forces structured evaluation and surfaces gaps you might miss. The real value is in the process, not the number.

Commands

  • /crewhaus:score [idea] — Quick 3-dimension viability score (~15 sec, no web search)
  • /crewhaus:quickscan [idea] — Deeper scan with target customer analysis, risk assessment, and real competitive preview (~1-2 min, uses web search)

Auto-Detection

When a user discusses a business idea they want to build, offer the score command once per session:

"Want me to evaluate that idea? /crewhaus:score [your idea] for a quick read, or /crewhaus:quickscan for a deeper scan with competitor data."

Only trigger on high-confidence signals:

  • User explicitly describes a business or product idea they want to build
  • User directly asks "is this a good idea?" or "would this work?"
  • User mentions wanting to validate or test a concept

Do NOT trigger on:

  • General business strategy discussion
  • Mentions of "business logic" in code
  • Discussing existing products or companies
  • Vague references to markets or industries

One offer per session. Don't nag.

About

Built by CrewHaus — an AI crew that runs startup validation. Free tools give you a structured first read. Full reports at crewhaus.ai/score.

安全使用建议
This skill is internally consistent and low-risk to install, but be aware of privacy and data-leak considerations: the quickscan command requires web search and competitive lookups, so any idea text you provide will be sent to external search services and may be included in logs or network requests. Avoid pasting highly confidential IP, customer lists, secret roadmaps, or unreleased code. The skill also promotes crewhaus.ai paid reports — verify that domain and its privacy policy if you plan to send sensitive material. If you want to limit exposure, do not invoke the quickscan (use the local /crewhaus:score only), or disable the agent's web/network access for this skill.
功能分析
Type: OpenClaw Skill Name: crewhaus Version: 1.0.0 The skill bundle is a legitimate startup idea evaluation tool that provides scoring and basic market analysis. It uses standard prompt instructions to guide the AI agent's behavior and includes a lead-generation mechanism for the developer's website (crewhaus.ai), with no evidence of malicious code, data exfiltration, or harmful prompt injection.
能力评估
Purpose & Capability
Name/description match the behavior in SKILL.md and command files: quick score locally and a deeper scan that uses web search to find competitors. No unexpected binaries, env vars, or config paths are required.
Instruction Scope
Instructions are narrowly scoped to evaluating ideas, scoring, and (for quickscan) using web search to find 2–3 real competitors. This is coherent with the stated purpose, but the SKILL explicitly requires sending the user's idea to external web search/search tools and to cite found data — so confidential or proprietary idea text will leave the local agent context.
Install Mechanism
There is no install spec and no code files that execute on the host. This is low-risk from a local installation/execution perspective.
Credentials
The skill declares no environment variables, credentials, or config paths. That is proportionate to the described functionality.
Persistence & Privilege
always is false and there is no indication the skill modifies system or other skills' settings. It is user-invocable and can be called autonomously by the agent (platform default).
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install crewhaus
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /crewhaus 触发
  4. 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 public release. Quick idea scoring and deeper scans with real competitor data.
元数据
Slug crewhaus
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

CrewHaus Startup Validation 是什么?

Quick startup idea evaluation from your terminal. Score ideas on 3 dimensions, run deeper scans with real competitor data and risk assessment. A structured t... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 268 次。

如何安装 CrewHaus Startup Validation?

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

CrewHaus Startup Validation 是免费的吗?

是的,CrewHaus Startup Validation 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

CrewHaus Startup Validation 支持哪些平台?

CrewHaus Startup Validation 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 CrewHaus Startup Validation?

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

💬 留言讨论