← 返回 Skills 市场
artyomx33

Inversion Strategist

作者 artyomx33 · GitHub ↗ · v1.0.0
cross-platform ✓ 安全检测通过
1830
总下载
1
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install inversion-strategist
功能描述
Flip problems upside down - instead of "how to succeed", ask "how to definitely fail" then avoid those paths. Use when user says "invert", "inversion", "flip it", "opposite approach", "how would this fail", "avoid failure", "what NOT to do", "Munger", "anti-goals", "guarantee failure".
使用说明 (SKILL.md)

Inversion Strategist

The Core Principle

"Invert, always invert." - Carl Jacobi

Instead of: "How do I achieve X?" Ask: "What would GUARANTEE I DON'T achieve X?" Then: Systematically avoid those things.

The Process

  1. State the goal
  2. Invert it: "What would guarantee failure?"
  3. List failure paths (7-10, obvious AND subtle)
  4. Categorize: Fatal / Damaging / Annoying
  5. Flip to avoidance strategies
  6. Build anti-checklist

Output Format

GOAL: [What you want]
INVERTED: "How would I guarantee failure at [goal]?"

FAILURE PATHS:

🔴 FATAL:
• [Path] → AVOID BY: [Strategy]

🟡 DAMAGING:
• [Path] → AVOID BY: [Strategy]

🟢 ANNOYING:
• [Path] → AVOID BY: [Strategy]

ANTI-CHECKLIST:
□ Never [behavior]
□ Never [behavior]

PRO-CHECKLIST:
□ Always [opposite of failure]
□ Always [opposite of failure]

Charlie Munger Wisdom

"It is remarkable how much long-term advantage people like us have gotten by trying to be consistently not stupid, instead of trying to be very intelligent."

"Tell me where I'm going to die, and I'll never go there."

Integration

Compounds with:

  • first-principles-decomposer → Rebuild from fundamentals after inverting
  • pre-mortem-analyst → Inversion finds paths; pre-mortem stress-tests timeline
  • six-thinking-hats → Black Hat is inversion-lite; combine for thorough analysis

See references/examples.md for Artem-specific inversions

安全使用建议
This is a lightweight, instruction-only skill for structured brainstorming (inversion). It appears internally consistent and does not ask for secrets or install code. Before enabling, consider: (1) avoid feeding any sensitive credentials or private data into prompts to any skill; (2) be mindful that enumerating 'failure paths' could reveal sensitive operational weaknesses — do not use this to plan or expose harmful actions; (3) if you later combine this skill with others that do have network/credential access, review those other skills for appropriate permissions.
功能分析
Type: OpenClaw Skill Name: inversion-strategist Version: 1.0.0 The skill bundle is designed to implement an 'inversion strategy' for problem-solving. All files (`_meta.json`, `SKILL.md`, `references/examples.md`, `references/framework.md`) contain only documentation, instructions for the AI agent on how to apply the strategy, and examples. There is no executable code, no attempts at data exfiltration, malicious execution, persistence, or prompt injection with harmful objectives. The instructions in `SKILL.md` are solely focused on guiding the agent's thought process and output format for its stated purpose, including reading internal skill documentation.
能力评估
Purpose & Capability
Name/description (flip problems via inversion) match the SKILL.md and example files, which provide only procedural guidance and templates. Nothing requested or included (no env vars, no binaries, no code) is unrelated to the stated purpose.
Instruction Scope
Runtime instructions are limited to asking questions, listing failure paths, categorizing them, and producing checklists. The SKILL.md does not instruct the agent to read system files, environment variables, or transmit data to external endpoints.
Install Mechanism
No install specification and no code files (instruction-only). Nothing will be written to disk or fetched at install time, which minimizes surface area for unexpected behavior.
Credentials
The skill declares no required environment variables, credentials, or config paths. There are no disproportionate credential or secret requests.
Persistence & Privilege
always is false and the skill is user-invocable (normal). It does not request persistent privileges or try to modify other skills or system configuration.
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 inversion-strategist
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /inversion-strategist 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 release - Munger method: guarantee failure then avoid. By Artem Tolmachev, Teddy Kids, TISA & Claude.
元数据
Slug inversion-strategist
版本 1.0.0
许可证
累计安装 2
当前安装数 2
历史版本数 1
常见问题

Inversion Strategist 是什么?

Flip problems upside down - instead of "how to succeed", ask "how to definitely fail" then avoid those paths. Use when user says "invert", "inversion", "flip it", "opposite approach", "how would this fail", "avoid failure", "what NOT to do", "Munger", "anti-goals", "guarantee failure". 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 1830 次。

如何安装 Inversion Strategist?

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

Inversion Strategist 是免费的吗?

是的,Inversion Strategist 完全免费(开源免费),可自由下载、安装和使用。

Inversion Strategist 支持哪些平台?

Inversion Strategist 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 Inversion Strategist?

由 artyomx33(@artyomx33)开发并维护,当前版本 v1.0.0。

💬 留言讨论