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 ipss-interpretation-space-search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 | ipss - Interpretation Space Search |
| description | Ambiguity means multiple interpretations are possible. |
| output | {"format":"prose"} |
Ambiguity means multiple interpretations are possible. Instead of guessing, systematically:
When input is ambiguous, generate all possible interpretations and search for the best one using explicit criteria.
Record exactly what was said/observed. Don't interpret yet - just capture.
Output: Raw input
Record all available context:
Output: Context summary
Using generation methods, produce all plausible interpretations. Be comprehensive - include interpretations you doubt.
For each interpretation, state:
Output: List of interpretations
Remove interpretations that:
Don't remove just because unlikely - keep for scoring.
Output: Filtered interpretations
For each interpretation, score on each criterion (1-10). Be consistent across interpretations.
Output: Scored interpretations
Sort by weighted total score. Note the gap between #1 and #2.
Output: Ranked interpretations
Confidence based on:
If confidence is low, consider:
Output: Confidence assessment
Select best interpretation. Verify it accounts for all key aspects of input. Note what would change the interpretation.
Output: Selected interpretation with caveats