dialectical-cot
CommunityDialectical CoT for safer, verifiable thinking
Software Engineering#verification#chain-of-thought#calibration#ai-reasoning#dialectical-cot#memory-priming
Authorveegee82
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Dialectical-CoT provides a structured approach to chain-of-thought that enforces a thesis/antithesis/synthesis rhythm with per-step calibration, preventing one-shot greediness and enabling verifiable reasoning progress.
Core Features & Use Cases
- Five-step per-step protocol (thesis, antithesis, synthesis, decision, log) to guide each reasoning step.
- Memory-primed, task-type aware primers plus a calibration loop to improve reliability and guard against bias.
- Ground-truth verification and bias invariance to ensure outcomes are measured against external truth and not memory artifacts.
Quick Start
Run the dialectical-CoT harness on your task to begin processing with thesis, antithesis, synthesis, and calibration.
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: dialectical-cot Download link: https://github.com/veegee82/loss-driven-development/archive/main.zip#dialectical-cot 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 471,000+ vetted skills library on demand.