synthesis-project-management

Manage multi-session projects with index.yaml, CONTEXT.md, REFERENCE.md, and sessions/.

15|2|Updated Mar 17, 2026
One-click install
npx skills add https://github.com/rajivpant/synthesis-skills --skill synthesis-project-management
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: synthesis-project-management
Source: https://github.com/rajivpant/synthesis-skills/tree/main/synthesis-project-management
Command: npx skills add https://github.com/rajivpant/synthesis-skills --skill synthesis-project-management

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides a lightweight, convention-first project management system that preserves conversational context across AI-human sessions, prevents information loss from context compaction, and centralizes project state for discoverability and continuity.

Core Features & Use Cases

  • Three-tier context model: Working memory (CONTEXT.md), semantic memory (REFERENCE.md), and episodic memory (sessions/) to keep active work concise and searchable.
  • Single source of truth index: projects/index.yaml stores project metadata and status so folders remain stable regardless of lifecycle changes.
  • Archival and session protocol: Line-count budgets, two-phase archival commit, and session start/end checklists that prevent lost details during compaction and multi-session handoffs.
  • Cross-project lessons: _lessons/ with date-prefixed files for discoverable patterns and incident reports that agents can grep and reuse.

Quick Start

Create a new project by adding an entry to projects/index.yaml, creating the project folder with a CONTEXT.md summary, and run the session start checklist to capture initial state.

Frequently Asked Questions about synthesis-project-management

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

FAQPage Schema
How do I preserve context across AI sessions when working on multi-session projects?

To preserve context across AI sessions, use a three-tier context model with working memory in CONTEXT.md, semantic memory in REFERENCE.md, and episodic memory in sessions/ directories to prevent information loss during compaction.

What is the best way to maintain a project registry for human-agent collaboration?

The best way to maintain a project registry for human-agent collaboration is using a single index.yaml file to store project metadata and status, ensuring folders remain stable regardless of lifecycle changes.

How do I set up a context-preserving project management workspace for AI collaboration?

Set up a context-preserving workspace by adding an entry to projects/index.yaml, creating a project folder with a CONTEXT.md summary, and running the session start checklist to capture initial state.

Does this project management convention work for cross-project lessons and incident reports?

Yes, this project management convention works for cross-project lessons by using a _lessons/ directory with date-prefixed files, making patterns and incident reports discoverable so agents can grep and reuse them.

Why does context compaction cause lost details in AI-assisted projects, and how do I prevent it?

Context compaction causes lost details when active working memory exceeds limits; prevent this using line-count budgets, a two-phase archival commit, and session start/end checklists designed to protect multi-session handoffs.