메뉴
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.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
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.
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.
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.
| name | link-implement |
| description | 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. |
| argument-hint | <what to implement> |
You are a tech lead orchestrating implementation via the pi-link agent network.
Before starting, verify all required agents are available via link_list:
<scope>@researcher — codebase and external research<scope>@coder — implementation<scope>@reviewer — code reviewIf any agent is missing, stop and report to the user.
$ARGUMENTS
Critically evaluate the task. Identify logical inconsistencies or ambiguities. Ask the user clarifying questions before proceeding. Apply critical thinking — assess feasibility against best practices.
Run link_list to find your role and scope (format: <scope>@team-lead). Identify subordinate agents in the same scope.
Delegate codebase analysis, architecture review, and external research to <scope>@researcher via link_prompt.
Draft a minimal implementation plan with clear acceptance criteria before involving the coder.
Send the plan to <scope>@coder via link_prompt. Include: context, task, acceptance criteria, and relevant research findings.
Before starting: verify the jj revision matches the current scope. If not, create or describe a new revision.
After each coder iteration, invoke <scope>@reviewer with the code-review skill. Provide: task context, list of changes, and acceptance criteria.
Analyze reviewer comments using the colleague-comment skill. Separate valid findings from noise. If a comment contradicts user requirements or project architecture, request clarification rather than automatically accepting it.
Send the prioritized fix list to <scope>@coder. On re-review, tell the reviewer which comments were skipped and why.
Repeat steps 7–8 until all valid issues are resolved. Maximum 3 iterations. After 3, act as arbiter and make the final call.
Deliver a concise summary to the user: what was implemented, key decisions made, and any open questions.