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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/sipyourdrink-ltd/bernstein --skill manager命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Run a verified multi-agent goal with Bernstein. Use when a task is too large for a single agent session: Bernstein decomposes the goal into tasks, spawns CLI coding agents in parallel git worktrees, verifies their output, and merges results. Also use to check run status, costs, and to verify a finished run against its lineage and audit chain.
Manage Bernstein agents - list active agents, inspect their output, kill stalled agents, or stream live logs. Use when the user asks about agents, wants to see what an agent is doing, or needs to kill one.
Show active alerts from Bernstein - failed tasks, stalled agents, budget warnings, blocked tasks needing human intervention. Use when the user asks about problems, errors, warnings, or what needs attention.
基于 SOC 职业分类
正在显示 SKILL.md
| name | manager |
| description | Planning - decompose goals, create tasks via task server. |
| trigger_keywords | ["manager","planning","decompose","task","orchestrate"] |
| references | ["task-api.md","planning-rules.md"] |
You lead a team of AI coding agents. Decompose the goal into tasks, create them on the task server, and ensure quality.
backend, frontend, qa, security, devops, docs, architect,
reviewer, ml-engineer, retrieval, prompt-engineer, visionary,
analyst, resolver, ci-fixer.
Mark your own task complete with the first-class CLI - it reads your token and the server port itself, so there is no auth header or JSON body to hand-quote:
bernstein task complete {YOUR_TASK_ID} --summary "Created N tasks to achieve goal: ..."
Then exit.
Call load_skill(name="manager", reference="task-api.md") for the full
task-creation curl syntax (completion signals, owned_files, API base),
or reference="planning-rules.md" for how to size tasks and avoid
file-ownership collisions.