decision-log

Create and search numbered decision records in ADR format.

15|3|Updated Jul 8, 2026
One-click install
npx skills add https://github.com/moonlight-lupin/agent-skills --skill decision-log-moonlight-lupin
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: decision-log
Source: https://github.com/moonlight-lupin/agent-skills/tree/main/productivity/decision-log
Command: npx skills add https://github.com/moonlight-lupin/agent-skills --skill decision-log-moonlight-lupin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and templates (resource) components.

What problem does it solve?

This Skill provides a durable, searchable decision journal to help agents and teams avoid re-litigating settled questions and maintain a clear record of decisions, rationale, and consequences.

Core Features & Use Cases

  • Decision Records: Create numbered records for decisions, including status, context, options considered, decision, consequences, and review metadata.
  • ADR Format: Follows the Architecture Decision Record (ADR) pattern for clarity and maintainability.
  • Search & Review: Search across all decisions and set up review schedules to keep decisions up-to-date.
  • Use Case: When a team needs to remember what was decided, why it was decided, what alternatives were considered, and when the decision should be reviewed, this Skill provides a comprehensive solution.

Quick Start

Create a new decision with the command: python scripts/decision_log.py new --title "Use SQLite for source-tracker" --context "Single-user local index, low write volume, simple backup needs."

Frequently Asked Questions about decision-log

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

FAQPage Schema
What is an Architecture Decision Record and how does a decision journal work?

An Architecture Decision Record (ADR) is a structured text document that captures a decision's context, options, and consequences. A decision journal maintains these numbered Markdown records to help teams avoid re-litigating settled questions and track review schedules.

How do I create a decision record for my team using the ADR pattern?

To create a decision record, run a Python script command specifying the title and context. The system generates a numbered Markdown document following the ADR pattern, documenting the status, alternatives considered, final decision, and consequences for team review.

Can I manage team decision records using only Python without external dependencies?

Yes, you can manage team decision records using only Python 3.11 or higher. This decision journal requires no external dependencies, handling text and Markdown-based decision documents natively to ensure records are searchable and self-contained.

What's the best way to search past decisions and schedule reviews in a decision journal?

The best way to search past decisions is using the built-in search functionality across all Markdown decision records. You can set up review schedules within the decision metadata to ensure past decisions are periodically evaluated and kept up-to-date.

When do I need to start documenting decisions in an ADR format?

You need to document decisions in an ADR format when a team requires a durable record of what was decided, the rationale behind it, alternatives considered, and when the decision should be reviewed. This prevents knowledge loss and recurring debates.

Does this decision management tool work for both AI agents and human teams?

Yes, this decision management tool works for both AI agents and human teams. It maintains a searchable, structured record of decisions that integrates into automated workflows while remaining readable as standard Markdown text for human collaborators.