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 cls-checklist-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 | cls - Checklist Search |
| description | The simplest possible search: enumerate items, check each against |
| output | {"format":"prose"} |
The simplest possible search: enumerate items, check each against criteria, return those that pass. Intelligence is in creating the checklist, not in following it.
Find items that match criteria by checking each item against a defined checklist. Pure mechanical matching - no judgment required.
List all criteria that items must meet. Each criterion must be:
Output: Numbered criteria list
List all items to be checked. Include everything - filtering happens via criteria.
Output: Numbered item list
For each item, check each criterion. Record PASS (✓) or FAIL (✗) for each. No judgment - just mechanical checking.
Output: Results matrix
Based on mode:
Output: Final pass/fail for each item
List all items that passed. Optionally rank by number of criteria met or weighted score.
Output: Filtered list