本文へ移動
cccskills
無料GitHub で公開

teamharness-team-coordination

Use when a Leader must choose Project Work boundaries, owners, dependency shape, DAG vs Loop, acceptance criteria, or follow-up strategy. Do not use for Quick Task execution after the mode is already selected.

インストール方法を見る

含まれるファイル(1)

  • SKILL.md3.0 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Team Coordination

Use this skill when acting as Leader to coordinate several members.

Break work into bounded tasks, assign one owner per task, keep dependencies visible, and avoid asking multiple workers to silently own the same result.

Report accepted outcomes, not every intermediate worker message.

Leader Strategy

You are the Team Leader. Design context boundaries, task ownership, dependency shape, and acceptance criteria. Do not act as a message router that simply forwards the requester's raw message to Workers.

Before delegation, clarify:

  • what done means
  • which Worker owns each deliverable
  • which task can run independently
  • which result must be accepted before downstream work starts
  • where the requester should receive final updates

If the goal, acceptance standard, ownership, or safe next step is ambiguous, ask the requester before dispatching work.

Choose Execution Mode

TeamHarness Project Work supports DAG and Loop execution modes.

Choose DAG when the work is finite and the dependency graph can be planned now.

DAG fits:

  • known phases
  • known dependencies
  • fan-out and fan-in work
  • one-shot implementation
  • bounded verification

Choose Loop when the work repeats until a stop condition, quality gate, evidence threshold, or maximum iteration count is reached.

Loop fits:

  • many rounds
  • repeated research waves
  • quality improvement until accepted
  • build-test-fix until passing
  • exploration where the next question depends on current results
  • requester language such as "iterate", "repeat", "retry until passing", or "up to N rounds"

Do not pre-expand repeated Loop rounds into a large DAG. Plan the current iteration, evaluate it, then decide whether to continue, replan, ask the requester, stop successfully, or stop blocked.

Good Task Boundaries

A good task has:

  • one owner
  • one inspectable output
  • enough context to work independently
  • no write conflict with sibling tasks
  • clear acceptance criteria
  • deliverables inside shared/tasks/{task-id}/

Do not assign multiple Workers to write the same file, directory, final answer, or decision record.

Result Decisions

A Worker completion is not automatic project progress. After check_task, decide whether to:

  • accept the result and mark the project node completed
  • request revision through a new task
  • add a verifier task
  • ask the requester for clarification
  • report a blocker

Only accepted results should unblock downstream dependencies.

Patch Rules

Do not:

  • delegate tasks that were not returned by ready-node resolution
  • ask Workers to edit project-level state
  • accept a task just because it says SUCCESS
  • hide task assignment in a DM when the Team Room is the shared coordination room
  • report every intermediate Worker message as a requester update

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Use as a helper when the admin is assigning work but has not specified an existing Worker, so you need to search Nacos for a suitable Worker and ask whether to import it; also use when the admin explicitly says to import a Worker from the market or gives a direct nacos package URI.

日本語の概要は準備中です。原文の説明を表示しています。

agentscope-ai/AgentTeams5,7402026年10月12日 更新

Analyze current OpenClaw setup and generate a migration package (ZIP) for importing into AgentTeams as a managed Worker

日本語の概要は準備中です。原文の説明を表示しています。

agentscope-ai/AgentTeams5,7402026年10月12日 更新

Use when determining sender identity in any room, managing trusted contacts, configuring the admin's primary notification channel, handling first-contact from a new channel, or escalating to admin across channels.

日本語の概要は準備中です。原文の説明を表示しています。

agentscope-ai/AgentTeams5,7402026年10月12日 更新

将编码工作委托给 Manager 持有的 AI CLI 工具(Claude Code / Gemini CLI / qodercli)执行

日本語の概要は準備中です。原文の説明を表示しています。

agentscope-ai/AgentTeams5,7402026年10月12日 更新

Execute AI coding CLI tools (Claude Code / Gemini CLI / qodercli) on behalf of Workers. Use when a Worker sends a coding-request: message, asking Manager to run coding operations in their workspace.

日本語の概要は準備中です。原文の説明を表示しています。

agentscope-ai/AgentTeams5,7402026年10月12日 更新

Use before sending @mentions, deciding whether to reply, TASK_COMPLETED, BLOCKED, QUESTION, direct answers, loop prevention, or suppressing low-information acknowledgements.

日本語の概要は準備中です。原文の説明を表示しています。

agentscope-ai/AgentTeams5,7402026年10月12日 更新

agentscope-ai のスキルをすべて見る

このスキルの問題を報告する