/install lateral-thinking
Lateral Thinking
Movement before judgment. Treat provocative lines as stepping stones, not final positions.
How to run it with this skill: one clearly headed section per move in the default order from Setup (Provocation (Po) → Extract principle → Concept fan → Candidates), or the alternate path the user chose.
Setup (run before starting)
In one short block:
- Stuck point — what pattern or assumption feels rigid?
- Default pass — Provocation (Po) → Extract principle → Concept fan → Candidates (state this line)
If safety or legal constraints are unclear, ask at most 3 questions in one message before generating provocations. Note any remaining gaps in plain language (no bracket tags in Setup).
If the user asks for random stimulus instead of a Po, replace the Provocation step with Random entry: one random noun or image, then several bridges (property → analogy → mechanism → application) into ideas.
If the user asks to challenge implicit rules, replace Provocation / Extract principle / Concept fan with: list implicit rules → for each, Challenge / Reframe / Test (smallest experiment) → Escape (two ways to sidestep the load-bearing rule) → then Candidates only from that thread.
The Moves
Provocation
Offer one primary Po (statement can be illogical or impossible) formatted:
Po: … — Movement idea: what useful idea does this suggest if we treat it as a springboard?
Extract principle
From the movement idea, state one operating principle that could work in the real world (even if the Po itself is absurd).
Concept fan
Widen from the principle along three directions — broaden, deepen, redirect — with several branches per direction unless the user wants more.
Candidates
Several actionable ideas. Tag each: near-term / stretch / experimental.
Execution Rules
- Never present a Po as a factual recommendation; always pair with Movement or Principle.
- If a provocation touches safety, ethics, or law, stop and surface the conflict explicitly — do not rationalize harm.
- One response for all moves unless interactive pacing is requested.
Checklist (verify before responding)
- Setup: stuck point + default pass (note if Random entry or rule-challenge path used)
- Po paired with movement; or alternate path completed as requested
- Concept fan has three directions with multiple branches each
- Candidates tagged near-term / stretch / experimental
- No Po presented as literal policy
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install lateral-thinking - 安装完成后,直接呼叫该 Skill 的名称或使用
/lateral-thinking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
Lateral Thinking 是什么?
Use this skill when the user asks for lateral thinking (including naming it or directing use/apply/run with obvious misspellings; decisive) or wants to break... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 100 次。
如何安装 Lateral Thinking?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install lateral-thinking」即可一键安装,无需额外配置。
Lateral Thinking 是免费的吗?
是的,Lateral Thinking 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Lateral Thinking 支持哪些平台?
Lateral Thinking 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 Lateral Thinking?
由 Siva Sai(@ysskrishna)开发并维护,当前版本 v2026.5.17。