# Teamharness Project Management

Use when you act as Leader and maintain durable TeamHarness project state for Quick...

- Repository: https://github.com/agentscope-ai/AgentTeams (5913 stars)
- Category: Engineering
- License: Apache-2.0
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add agentscope-ai/AgentTeams --skill teamharness-project-management -g -a claude-code -y`
Codex: `npx skills add agentscope-ai/AgentTeams --skill teamharness-project-management -g -a codex -y`
Cursor: `npx skills add agentscope-ai/AgentTeams --skill teamharness-project-management -g -a cursor -y`
Gemini CLI: `npx skills add agentscope-ai/AgentTeams --skill teamharness-project-management -g -a gemini-cli -y`

## Description

Use when you act as Leader and maintain durable TeamHarness project state for Quick Task or Project Work: create_quick_project, create_project, plan_dag, plan_loop, ready_nodes, resolve_project, accept_task_result, project completion, and requester report state. Do not use to create Matrix task rooms or send messages.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Project Management

Use this skill when maintaining durable project state.

A project owns the plan, context, dependencies, and accepted progress. Keep the
project plan separate from individual task execution logs.

Only advance a dependency after you accept the submitted result as the trusted
Leader runtime.
Do not use this skill for ordinary direct replies or lightweight one-off
actions.

## Scope

Use this skill when acting as Leader for:

- `projectflow` calls
- project creation
- quick single-task project creation
- DAG planning
- Loop planning
- ready-node resolution
- Loop iteration recording
- accepting checked Worker results into project progress
- project-level status reports

For Project Work, use `teamharness-team-coordination` first to decide task
boundaries. If no task room exists yet, use `teamharness-roomflow` and
`teamharness-communication` before this skill. Use
`teamharness-task-delegation` for individual task specs, assignment messages,
and Worker result checks.

## Project Files

Project files live under:

```text
shared/projects/{project-id}/
```

TeamHarness writes CoPaw-compatible task runtime files:

```text
shared/projects/{project-id}/meta.json
shared/projects/{project-id}/plan.md
```

Write a final project result, when needed, to:

```text
shared/projects/{project-id}/result.md
```

You own this project result file as Leader. Build it from accepted project state
and accepted task deliverables; do not ask Workers to write or submit it as a
task deliverable.

Use `projectflow` to change `meta.json` and `plan.md`; do not hand-edit
project state unless a tool failure leaves no safe alternative.

## ID Rules

Use safe IDs only:

```text
[A-Za-z0-9][A-Za-z0-9._-]*
```

Do not use colons, slashes, spaces, or Matrix IDs as project or task IDs.

Suggested formats:

```text
projectId: {short-description}-YYYYMMDD-HHMMSS
taskId: {projectId}-{seq}
```

If a user or test provides explicit IDs, preserve them when they are already
safe.

The rest: https://github.com/agentscope-ai/AgentTeams/blob/HEAD/plugins/agentteams-teamharness/skills/team/project-management/SKILL.md