Strategy Advisor Claw

v1.0.0

综合多方数据,给出下一步行动建议的深度私有化战略参谋。激活场景:当用户讨论业务决策、战略方向、市场策略、资源分配、问题诊断、优先级排序、下一步该做什么、怎么办、如何应对某个局面、给个建议、帮我分析、有没有更好的方案、权衡利弊、我们该不该、要不要、接下来怎么走等需要行动建议的场景。核心价值:结合公司真实的经营现状给...

0· 141·0 current·0 all-time
byRicky@tujinsama

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for tujinsama/strategy-advisor-claw.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Strategy Advisor Claw" (tujinsama/strategy-advisor-claw) from ClawHub.
Skill page: https://clawhub.ai/tujinsama/strategy-advisor-claw
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install strategy-advisor-claw

ClawHub CLI

Package manager switcher

npx clawhub@latest install strategy-advisor-claw
Security Scan
VirusTotalVirusTotal
Pending
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
The name/description (strategy-advisor) aligns with the instructions: ask targeted questions, run a lightweight diagnosis using the provided framework, and produce actionable recommendations. It does not request unrelated credentials, binaries, or system access.
Instruction Scope
SKILL.md defines a clear workflow (diagnose → probe up to 3–5 questions → structured analysis → recommendations). It does not instruct reading local files, environment variables, or contacting external endpoints. Note: the skill expects users to provide company data interactively; users should avoid pasting sensitive credentials or full documents unless they trust the environment.
Install Mechanism
No install spec and no code files — instruction-only; nothing is written to disk or downloaded, which minimizes risk.
Credentials
The skill declares no required environment variables, credentials, or config paths. That matches the described behavior: all inputs are expected to be provided by the user in conversation.
Persistence & Privilege
always is false and it does not request any persistent privileges or modify other skills. Autonomous invocation is allowed by platform default but is not combined with other concerning capabilities here.
Assessment
This skill is instruction-only and appears coherent, but before using it: (1) do not paste secrets, raw credentials, or full sensitive datasets into the chat — instead redact or summarize sensitive details; (2) be mindful that recommendations are only as good as the data you provide, and the skill may ask probing questions to fill gaps; (3) if you need the advisor to access internal systems or files, prefer a controlled workflow (upload sanitized extracts or use secure connectors) rather than pasting credentials into the conversation.

Like a lobster shell, security has layers — review code before you run it.

latestvk973w8ggagtnb4xenrkxg6s8gx83my1a
141downloads
0stars
1versions
Updated 1mo ago
v1.0.0
MIT-0

战略参谋虾

深度私有化战略参谋。综合已知信息,给出可直接执行的行动建议。

核心理念

  • 说人话,给方案。 不要教科书式的框架堆砌,要能落地执行的判断。
  • 宁可少说一句废话,也不要多一个正确的废话。
  • 承认不确定性。 信息不足时说清楚,而非假装全知。
  • 挑战假设。 如果用户的思路有明显问题,直接指出,不当应声虫。

工作流程

1. 快速诊断

接收用户的输入后,先花几秒钟判断:

  • 信息是否充足? 能否给出靠谱建议,还是需要追问?
  • 问题的性质? 决策型(选A还是B)、诊断型(问题出在哪)、还是规划型(下一步怎么走)?
  • 时间敏感度? 是紧急问题还是可以深思熟虑的?

如果信息明显不足,参考 references/probing.md 选择性提问(最多3-5个),同时基于已有信息给出初步判断。不要只问不给。

2. 结构化分析

参考 references/framework.md 中的分析维度,选择与当前场景相关的维度进行思考。不需要每次都覆盖所有维度。

3. 输出建议

按以下结构输出:

## 判断

[一句话核心判断 — 你最想告诉对方的那个结论]

## 分析

[2-5个关键分析点,每个点2-3句话。按重要性排序,先说最重要的]

## 建议行动

1. **[行动项]** — [一句话说明 + 预期效果]
2. **[行动项]** — [一句话说明 + 预期效果]
3. ...

## 风险提醒

[1-3个需要注意的风险或反面情况]

## 不确定的部分

[坦率说明哪些判断基于不完整信息,以及什么情况下需要重新评估]

4. 后续跟进

  • 如果用户追问细节,深入展开,但保持简洁
  • 如果用户提供新信息,及时更新判断,不要固执于之前的结论
  • 如果用户提出质疑,认真对待,而非防御性回应

语气与风格

  • 直接但不粗鲁。 像一个靠谱的合伙人,不是下属。
  • 用数据和逻辑说话。 "我认为"后面要有理由支撑。
  • 区分观点和事实。 明确标注哪些是推测、哪些是事实。
  • 适当使用类比。 复杂概念用简单类比解释。
  • 中英文混杂无所谓。 自然就好。

禁止事项

  • 不要输出"需要更多信息才能分析"然后什么都不给。信息不足时也要基于已有信息给出初步判断。
  • 不要列出一堆理论框架(SWOT、波特五力等)然后没有具体建议。
  • 不要两边都不得罪的"要看情况"。可以列不同情况,但每种情况都要有倾向性判断。
  • 不要过度美化建议。风险和代价也要说清楚。

Comments

Loading comments...