decision-logger

Parse decisions.md to log board decisions and detect conflicts.

Updated Apr 16, 2026
One-click install
npx skills add https://github.com/devCharuzu/philfida-taskmanage --skill decision-logger-devcharuzu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: decision-logger
Source: https://github.com/devCharuzu/philfida-taskmanage/tree/main/.windsurf/skills/decision-logger
Command: npx skills add https://github.com/devCharuzu/philfida-taskmanage --skill decision-logger-devcharuzu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill offers a two-layer memory system to log and manage board meeting decisions: Layer 1 captures raw transcripts (not auto-loaded, only on explicit founder request) and Layer 2 stores founder-approved decisions to ensure future meetings read Layer 2 rather than past debates.

Core Features & Use Cases

  • Two-layer memory architecture: Layer 1 stores raw transcripts while Layer 2 holds only founder-approved decisions, which are loaded automatically in Phase 1 of every board meeting.
  • Decision logging and retrieval: Access the most recent decisions, full history, and actionable items; surface overdue items with /cs:review and search by owner or topic with /cs:decisions.
  • Conflict detection and governance: Detect DO_NOT_RESURFACE violations and topic/owner conflicts; support conflict resolution workflows.

Quick Start

Run the Python CLI to load decisions.md, generate a summary, and show overdue items.

Frequently Asked Questions about decision-logger

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

FAQPage Schema
How do I log and track board meeting decisions and action items?

You can log board meeting decisions using a two-layer memory architecture that stores raw transcripts in Layer 1 and founder-approved decisions in Layer 2. It parses decisions.md to generate summaries, track overdue action items, and format actionable post-meeting reports.

What is a two-layer memory system for board meeting governance?

A two-layer memory system separates raw meeting transcripts in Layer 1 from founder-approved decisions in Layer 2. This ensures future meetings automatically load only finalized decisions rather than past debates, streamlining governance and preventing revisited topics.

How do I detect conflicts and enforce DO_NOT_RESURFACE rules in meeting minutes?

Conflict detection and DO_NOT_RESURFACE enforcement are handled by a self-contained CLI that parses decisions.md. It identifies topic and owner conflicts, flags violations, and supports structured conflict resolution workflows for board governance.

How do I retrieve overdue action items and search past decisions by owner or topic?

You can retrieve overdue action items using the /cs:review command and search historical decisions by owner or topic with /cs:decisions. These commands query the approved decision layer to surface relevant governance history.

Can I manage board meeting decisions without automatically loading raw transcripts?

Yes, raw transcripts are stored in Layer 1 but are never auto-loaded; they are accessed only on explicit founder request. The system automatically loads Layer 2 founder-approved decisions during Phase 1 of every board meeting instead.

Do I need any external dependencies to run the decision logging CLI?

No external dependencies are required. The Skill relies on a self-contained Python CLI script that directly parses decisions.md, enforces DO_NOT_RESURFACE rules, detects conflicts, and outputs formatted reports without additional packages.