Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/benjam3n/reasoningtool --skill met-metaphor-method명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
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.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | met - Metaphor Method |
| description | A systematic method for using metaphors to: |
| output | {"format":"prose"} |
A systematic method for using metaphors to:
Metaphors are not just decorative language. They reveal structural similarities between domains. By mapping from one domain to another, we can discover relationships that transfer.
What are you trying to understand better? This is the LITERAL domain you want insight into.
Example: "Philosophical conclusions"
Output: target_domain
What is the target domain LIKE? Find a different domain that has structural similarities.
Good source metaphors:
Example: "Conclusions are like movie endings"
Output: source_metaphor
In the source domain, what relationships exist? List them without yet checking if they apply to target.
Example (movie endings):
Output: source_relationships
For each source relationship, what's the equivalent in target? Don't force it - some may not translate.
Example translations:
Output: translated_relationships
For each translated relationship, ask:
Keep relationships that pass testing. Discard or modify those that don't.
Output: tested_relationships
For relationships that survive testing, what's the abstract structure? This is the pattern that applies to BOTH domains.
Example: "Terminal points (endings/conclusions) are evaluated relative to their trajectory (plot/argument) and driving forces (motivations/goals)"
This abstract structure is the real insight.
Output: abstract_structure
Take the abstract structure and find OTHER metaphors that instantiate it. This tests the structure's generality and may reveal new aspects.
Example: Journey metaphor also has terminal point (destination), trajectory (route), and driving forces (reasons for travel).
What new relationships does the journey metaphor reveal?
Output: iterated_insights