reasoning-sandwich
CommunityStructured reasoning for safer model actions.
Software Engineering#verification#safety#reasoning#edge-cases#ai-patterns#model-allocation#pre-reasoning
Authorbaekenough
Version1.0.0
Installs0
System Documentation
What problem does it solve?
A model allocation pattern that wraps implementation actions with dedicated reasoning phases, ensuring thorough analysis before execution and verification after completion.
Core Features & Use Cases
- Pre-reasoning: Analyze requirements, identify edge cases, and define success criteria before acting.
- Action: Implement solution, generate content, and execute the plan using a balanced model.
- Post-verification: Verify outcomes against criteria and check for regressions.
Quick Start
Apply the reasoning-sandwich pattern to a task by allocating pre-reasoning, action, and post-verification models and documenting the plan and verification criteria.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: reasoning-sandwich Download link: https://github.com/baekenough/second-brain/archive/main.zip#reasoning-sandwich Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.