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 agi-araw-to-gosm-integration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 | agi - ARAW to GOSM Integration |
| description | Systematic procedure for translating ARAW exploration outputs |
| output | {"format":"prose"} |
Systematic procedure for translating ARAW exploration outputs into GOSM execution inputs.
ARAW = Exploration engine (maps possibility space) GOSM = Execution engine (turns insights into action)
This bridge ensures ARAW findings automatically populate GOSM structures.
If multiple ARAW databases exist: python synthesize.py *.db --find-tensions --extract-actions actions.json
This produces:
From synthesis output, identify:
MUST_VERIFY (before strategy commitment):
These become GOSM gates that must pass before proceeding.
For each crux node:
assumption: id: [from ARAW] claim: [original claim text] confidence: [ARAW probability estimate] criticality: CRITICAL | HIGH | MEDIUM | LOW validation_method: [how to test] validation_status: UNVALIDATED if_false_action: [contingency] source: ARAW:[database_name]
For each claim with probability < 0.7:
risk: id: [generated] description: [claim might be false] probability: [1 - ARAW probability] impact: [from leverage score] mitigation: [if applicable] contingency: [ARAW ASSUME_WRONG branch] source: ARAW:[database_name]
From ARAW branches, extract:
Feed into Strategy Discovery phase.
For each ARAW tension:
decision_point: id: [generated] question: [tension summary] option_a: [one side of tension] option_b: [other side of tension] resolution_criteria: [how to decide] current_choice: UNRESOLVED source: ARAW_TENSION
For themes appearing in 2+ ARAW runs:
foundation: claim: [theme summary] confidence: HIGH (cross-verified) sources: [list of ARAW databases] validation_needed: MINIMAL
These can be treated as near-axioms for planning.