基于 SOC 职业分类
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 bi-bounded-inquiry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。
正在显示 SKILL.md
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.
| name | bi - Bounded Inquiry |
| description | Unbounded inquiry cannot terminate - every answer opens new questions. |
| output | {"format":"prose"} |
Unbounded inquiry cannot terminate - every answer opens new questions. Bounded inquiry can terminate - closure is possible within scope.
This procedure establishes explicit boundaries for any inquiry, enabling satisfying closure rather than infinite regress.
Default: 2x. Parse depth from $ARGUMENTS if specified (e.g., "/bi 4x [input]").
| Depth | Min Inquiry Branches | Min Depth per Branch | Min Boundary Tests | Min Convergence Checks |
|---|---|---|---|---|
| 1x | 2 | 2 | 1 | 1 |
| 2x | 3 | 3 | 2 | 2 |
| 4x | 5 | 4 | 3 | 3 |
| 8x | 7 | 5 | 5 | 4 |
| 16x | 10 | 7 | 7 | 6 |
These are floors. Go deeper where insight is dense. Compress where it's not.
Before beginning inquiry, explicitly state:
Be specific. "Understand X" is too vague. "Be able to predict Y given Z" is specific.
Output: goal_statement
Explicitly state:
Questions outside scope are acknowledged but deferred: "That's outside this inquiry. We can address it separately."
Output: scope_definition
Explicitly state:
This prevents moving goalposts and endless "but what if?"
Output: rules_definition
Explicitly state:
If there are no stakes, ask: Why are we doing this?
Output: stakes_definition
Pursue the inquiry, but check against boundaries:
Out-of-scope questions: Acknowledge and defer. Goal-irrelevant tangents: Note and return. Rule-violating moves: Reject or flag.
Output: inquiry_process
Inquiry terminates when:
State the termination explicitly: "This inquiry is complete because [criterion]."
Output: termination_statement