manager-agent-start

Initialize or load a file-based project memory directory with six files.

Updated Jun 6, 2026
One-click install
npx skills add https://github.com/ClementHW/manager-agent --skill manager-agent-start
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: manager-agent-start
Source: https://github.com/ClementHW/manager-agent/tree/main/manager-agent-start
Command: npx skills add https://github.com/ClementHW/manager-agent --skill manager-agent-start

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Initialize or load a persistent, file-based project memory before starting a task to preserve context across sessions.

Core Features & Use Cases

  • Initialize or load the .manager-agent/ memory directory with 6 files on first run (MEMORY.md, PROJECT_STATE.md, TODO.md, BUG_HISTORY.md, DECISION_LOG.md, RISK_REGISTER.md) and add it to .gitignore.
  • Support lightweight layered loading to speed initial responses; on first load, interview the user and create a project snapshot.
  • Coordinate with the paired skill manager-agent-update to sync memory after work.

Quick Start

Trigger the workflow by saying '/manager-agent-start' to initialize or load project memory before beginning work.

Frequently Asked Questions about manager-agent-start

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

FAQPage Schema
How do I preserve coding context across sessions in a repository?

To preserve coding context across sessions, initialize a file-based project memory to save repository state, decisions, and history into a dedicated directory. This lightweight snapshot loads automatically on subsequent visits.

What is the best way to initialize project memory before starting a coding task?

The best way to initialize project memory is to trigger a workflow that interviews you about the project, explores the repository, and creates a memory directory containing six tracking files for state, history, and risks.

How does a file-based project memory workflow operate?

A file-based project memory workflow operates by creating a directory with six files to track memory, project state, todos, bugs, decisions, and risks. It loads a project snapshot for context before enforcing a deterministic workflow.

Do I need to manually manage project memory files after initialization?

You do not need to manually manage project memory files after initialization. The workflow coordinates with a paired update skill to sync changes back to memory and produce a task-focused summary after work is complete.

Can I use project memory snapshots for large repository collaboration?

Yes, you can use project memory snapshots for large repository collaboration. The system uses lightweight layered loading to speed initial responses and adds the memory directory to gitignore to prevent conflicts.