菜单
Delegate deep domain analysis, architecture planning, or complex decisions to your own scope's expert agent (claude-opus). Ensures the expert is running for YOUR scope. Use for architectural decisions, multi-step planning, tradeoff evaluation, domain modeling. Never borrows agents from other scopes.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Full feature development cycle with herdr-managed agent panes. Ensures an ai-workers tab exists with coder, researcher, and critic panes, then orchestrates implement-review loop via pi-link. Use when you want a persistent multi-agent workspace managed by herdr.
Delegate a research task to your own scope's researcher agent. Ensures ai-workers panes are running for YOUR scope, then sends the request to <scope>@researcher. Use for codebase exploration, external references, pattern lookup. Never borrows agents from other scopes.
Delegate a code review to your own scope's critic agent. Ensures ai-workers panes are running for YOUR scope, then sends the request to <scope>@critic. Use for code review, diff review, quality checks. Never borrows agents from other scopes.
Analyze colleague feedback for relevance, objectivity, and practical value. Use when evaluating code review comments, architectural feedback, or any critique from a peer before deciding what to act on.
Full feature development cycle with multi-agent collaboration — researcher, coder, and reviewer. Use when implementing a non-trivial feature that benefits from research, iterative coding, and independent review.
Delegate a task to the most suitable connected agent via link_prompt and return the result to the user. Use when you want to route a request to a specialist colleague on the pi-link network.
基于 SOC 职业分类
| name | team-expert |
| description | Delegate deep domain analysis, architecture planning, or complex decisions to your own scope's expert agent (claude-opus). Ensures the expert is running for YOUR scope. Use for architectural decisions, multi-step planning, tradeoff evaluation, domain modeling. Never borrows agents from other scopes. |
| argument-hint | <question, plan request, or domain to analyze> |
Your scope comes from YOUR pi-link name, not from what agents are visible in link_list.
Never send to kaizen@expert if your scope is nix. Never skip setup because a foreign expert is already idle.
The expert runs on models.expert (claude-opus) — optimized for:
Not for: writing code (→ team-implement), quick lookups (→ team-research), code review (→ team-review).
Call link_list. Find the entry marked (you). Scope = the part before @.
Example: nix@lead → scope = nix. You will use nix@expert, not any other.
Check if <scope>@expert is in link_list and idle:
Yes → proceed to Step 3.
No → run:
ai-workers-setup "<scope>" "$PWD"
ai-workers-setup is on PATH (installed to ~/.config/scripts/).
If command not found:
python3 ~/.agents/skills/team-implement/scripts/ai-workers-setup "<scope>" "$PWD"
Note:
ai-workers-setupcreates coder/researcher/critic. The expert pane is separate. If the expert is still absent after setup, tell the user to run:pi-link <scope>@expert --model anthropic/claude-opus-4-8
Before delegating, collect what the expert needs:
Quality of the expert's output scales directly with context depth.
Send to <scope>@expert via link_prompt. Structure the prompt:
## Context
<codebase structure, existing decisions, constraints>
## Goal
<what needs to be planned or decided>
## Already considered
<options evaluated, with reasons accepted/rejected>
## Expected output
<plan / architecture doc / decision + rationale / task breakdown>
link_prompt is synchronous — wait for [<scope>@expert] response.
<scope>@coder via team-implementjj desc / docs), then proceedteam-research or team-implementThe expert's decisions are authoritative. Do not override them silently.