project-management

Coordinate project state and ready-node selection for HiClaw multi-agent workflows.

5.3k|652|Updated Feb 21, 2026
One-click install
npx skills add https://github.com/agentscope-ai/HiClaw --skill project-management-agentscope-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: project-management
Source: https://github.com/agentscope-ai/HiClaw/tree/main/manager/agent/team-leader-agent/skills/project-management
Command: npx skills add https://github.com/agentscope-ai/HiClaw --skill project-management-agentscope-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It solves the problem of keeping multi-agent project execution consistent, recoverable, and auditable by managing the project’s lifecycle state and execution plan.

Core Features & Use Cases

  • Project lifecycle control: Pause, resume, and complete projects through projectflow without mutating execution graphs directly.
  • Execution planning for DAG and Loop: Create or refresh plan graphs (plan_dag, plan_loop) with explicit dependencies and iteration templates.
  • Ready-node resolution and progress reporting: Use ready_nodes / ready_loop_nodes to identify what to delegate next and generate project-level status reports for the requester.

Quick Start

Use the project-management skill to run a full projectflow plan and ready-node resolution for a new project using your selected team-coordination strategy.

Frequently Asked Questions about project-management

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

FAQPage Schema
How do I manage multi-agent project lifecycle states without mutating execution graphs directly?

Manage multi-agent project lifecycle states by applying projectflow transitions like pause, resume, and complete. This controls lifecycle phases directly without mutating the underlying execution graphs.

What is ready-node resolution in DAG planning and how does it identify the next task?

Ready-node resolution in DAG planning identifies which nodes have satisfied their explicit dependencies and are ready to execute. It selects these ready nodes to determine what to delegate next to worker agents.

How do I create execution plans with explicit dependencies for Loop planning?

Create Loop planning execution plans by refreshing plan_loop graphs with iteration templates. This establishes explicit dependencies and structured iteration logic for multi-agent workflows.

What shared project files are required to orchestrate auditable multi-agent workflows?

Orchestrating auditable multi-agent workflows requires strict use of shared project files: meta.json for state, plan.md for execution graphs, and result.md for result aggregation.

How does heartbeat recovery work when coordinating multi-agent project execution?

Heartbeat recovery checks monitor multi-agent project execution consistency by verifying active-project states. It ensures execution remains recoverable and auditable across workflow lifecycle transitions.

Can I use task delegation to handle worker tasks during project-level status reporting?

Yes, task delegation handles worker tasks by delegating them to task-management. The project-management skill aggregates results and generates project-level status reports for the requester.