/install analytical-thinking
Analytical Thinking
Clarity beats cleverness. End with answers tied to structure and stated confidence.
How to run it with this skill: one clearly headed section per step in this order: Frame → Decompose → Hypotheses → Evidence → Synthesis. Insert Options matrix only when Setup calls for it (after Evidence, before Synthesis).
Setup (run before starting)
In one short block:
- Analytical question — precise, ideally falsifiable
- Default pass — Frame → Decompose → Hypotheses → Evidence → Synthesis (state this line)
If data availability or definitions are missing, ask at most 3 questions in one message, then proceed. Note any remaining gaps or working guesses in plain language (no bracket tags in Setup).
If the user is choosing among concrete alternatives, after Evidence insert Options matrix: rows = options, columns = criteria (state weights if any), qualitative scores (− / 0 / +) with one-line justification per cell — then finish with Synthesis.
The Steps
Frame
Question type (estimate, compare, explain, predict, optimize). Unit of analysis and baseline (even if hypothetical).
Decompose
Tree or table: factors, drivers, or workstreams. Each child node should be MECE-ish (mutually exclusive where it matters; collectively exhaustive enough for the decision).
Hypotheses
Ranked H1, H2, H3 — what would we expect to observe if each were true? What would falsify each?
Evidence
For each hypothesis: Observation: … — Strength note: one short sentence on how much this observation supports or undermines the hypothesis and the main limit (no Strong/Moderate/Weak labels). Caveat: …
If no real data, run a thought experiment section instead — label bullets [THEORETICAL].
Synthesis
- Answer — direct response to the analytical question
- Key uncertainty — what single unknown swings the answer most
- Next data / step — what to collect or run next
Execution Rules
- Do not conflate Hypotheses and Evidence in the same bullet list.
- Numbers: if inputs are guessed, show ranges and label
[ESTIMATED]. - Prefer structure over long prose.
Checklist (verify before responding)
- Setup: analytical question + default pass (note if Options matrix used)
- Frame states question type and baseline
- Decompose is scannable (tree or table)
- Hypotheses have falsifiers
- Evidence (or
[THEORETICAL]) mapped to hypotheses - Synthesis: answer, uncertainty, next step
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install analytical-thinking - 安装完成后,直接呼叫该 Skill 的名称或使用
/analytical-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
Analytical Thinking 是什么?
Use this skill when the user asks for analytical thinking (including naming it or directing use/apply/run with obvious misspellings; decisive) or wants a str... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 108 次。
如何安装 Analytical Thinking?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install analytical-thinking」即可一键安装,无需额外配置。
Analytical Thinking 是免费的吗?
是的,Analytical Thinking 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Analytical Thinking 支持哪些平台?
Analytical 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 Analytical Thinking?
由 Siva Sai(@ysskrishna)开发并维护,当前版本 v2026.5.17。