sia-code/decision-trace

Record AI decisions with context, alternatives, and outcomes in sia-code memory.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/DxTa/dotfiles --skill sia-code-decision-trace
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sia-code/decision-trace
Source: https://github.com/DxTa/dotfiles/tree/main/opencode/skills/sia-code/decision-trace
Command: npx skills add https://github.com/DxTa/dotfiles --skill sia-code-decision-trace

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill addresses the problem of "knowledge loss" in AI memory by ensuring that not just what decisions were made, but why they were made, are recorded and retrievable. This prevents AI agents from treating every situation as novel.

Core Features & Use Cases

  • Structured Decision Recording: Enforces a consistent format for capturing context, reasoning, and outcomes of decisions.
  • Enhanced Memory Recall: Allows future AI sessions to understand the historical rationale behind past choices, leading to more informed and consistent actions.
  • Use Case: When an AI agent decides to implement a specific retry logic for API calls, this Skill ensures the memory entry includes why that specific logic was chosen over alternatives, and what the observed outcome was, making the learning actionable for future similar scenarios.

Quick Start

Use the sia-code memory add-decision command to record a new decision with its full context and reasoning.

Frequently Asked Questions about sia-code/decision-trace

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I capture the reasoning behind AI decision making in memory?

To capture AI decision making reasoning, you can use a structured decision trace format that records context, alternatives considered, and outcomes. This prevents knowledge loss by ensuring future AI sessions understand the historical rationale behind past choices.

Why does my AI agent treat every situation as novel instead of learning from past decisions?

AI agents treat situations as novel when memory entries only record what decision was made without the why. Enforcing a structured decision trace captures the reasoning context and outcomes, enabling persistent learning and consistent future actions.

What's the best way to structure AI memory entries for knowledge retention?

The best way to structure AI memory entries for knowledge retention is to enforce a consistent decision trace format. This format moves beyond simple outcome recording by explicitly capturing context, reasoning, and the alternatives considered for each decision.

How do I record context and alternatives considered when an AI makes a decision?

You can record decision context and alternatives by using the memory add-decision command. This command enforces a structured decision trace format that captures the full reasoning and observed outcomes for future knowledge management.

Can I integrate reasoning capture with existing AI memory management systems?

Yes, structured reasoning capture integrates directly with sia-code memory management for persistent learning. This integration ensures that captured decision context and outcomes are retrievable across future AI sessions for enhanced recall.