用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/benjam3n/reasoningtool --skill asu-assumption-surfacing命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Route any input through a branching question tree to narrow down the optimal response strategy before writing. Two stages — PERCEIVE (classify input) then ACT (select response). Covers all prompt types.
Generate exhaustive guesses about user input using ALL search methods with coverage tracking. Guessing is SEARCH through possibility space. Tracks space created vs space covered to ensure comprehensive exploration.
Systematically evaluate and select from a set of guesses, options, or possibilities. Combines ARAW analysis with prioritization to determine which guesses are strong, weak, actionable, or eliminable.
基于 SOC 职业分类
正在显示 SKILL.md
| name | asu - Assumption Surfacing |
| description | Plans and beliefs rest on assumptions that are often invisible. |
| output | {"format":"prose"} |
Plans and beliefs rest on assumptions that are often invisible. These hidden assumptions can cause spectacular failures when violated. This procedure uses systematic prompts to surface assumptions that would otherwise remain hidden.
Systematically identify hidden assumptions in a plan, belief, or strategy using structured prompts. Prompts do most of the work; recognition requires some insight.
Default: 2x. Parse depth from $ARGUMENTS if specified (e.g., "/asu 4x [input]").
| Depth | Min Assumptions Surfaced | Min Domains Checked | Min Verification Tests | Min Stakeholder Perspectives |
|---|---|---|---|---|
| 1x | 5 | 2 | 1 | 1 |
| 2x | 8 | 3 | 2 | 2 |
| 4x | 12 | 5 | 3 | 3 |
| 8x | 18 | 7 | 5 | 5 |
| 16x | 25 | 9 | 8 | 7 |
These are floors. Go deeper where insight is dense. Compress where it's not.
Clearly describe the plan, belief, or strategy being examined. Be specific about what it claims or proposes.
Output: Subject description
Go through each category of prompts systematically. For each prompt, ask: "What am I assuming about this?" Record all assumptions, even obvious ones.
Output: Raw assumption list
Combine similar assumptions. Remove true duplicates. Clarify vague assumptions.
Output: Clean assumption list
For each assumption, ask: "If this assumption is wrong, does the plan still work?"
Critical = Plan fails if assumption is wrong Important = Plan degraded if wrong Minor = Doesn't significantly affect plan
Output: Prioritized assumptions
For each critical assumption:
High risk = Critical + Low confidence
Output: Confidence assessment
For high-risk assumptions (critical + low confidence):
Output: Validation plan
For each critical assumption: "If this is wrong, what's the alternative plan?" Having contingencies reduces risk.
Output: Contingency plans