Menu
用于 ugk-pi 项目的快速上手、/init、方案收敛和实施前规划。适用于需要先搞清楚项目现状、边界、目录职责、运行方式和后续执行顺序的任务。
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Guided Team Console Task design advisor and creation/update helper. Use when the user says "/team-task" or asks in natural-language to create, update, design, or complete a Team Console Task, WorkUnit, Discovery Task, reusable/template task, worklist-producing task, split-task, 任务卡片, 发现任务, 分片任务, or a multi-source research workflow. Helps non-expert users turn fuzzy goals into the right Task shape, asks plain-language questions, previews full JSON, and writes only through /v1/team/tasks after confirmation. Do not use for running, observing, or debugging Tasks.
Creates repo-local requirement/step plans and ready-to-send messages for a separate GLM/coding agent. Use when the user says to call glm-plan, asks to hand work to another agent, or wants a detailed plan/message/file for an external agent to implement.
Use this skill for web browsing, logged-in websites, social platforms, dynamic pages, screenshots, downloads, and any task that needs a real browser session.
Use when and only when the user message contains the explicit keyword "/team-plan". This skill guides the Agent through creating TeamUnit presets and Plans via the /v1/team REST API. If the user merely mentions "team plan", "团队计划", Team Runtime, or planning without "/team-plan", do not use this skill automatically; ask whether they want to start with "/team-plan".
无浏览器实体的 HTTP(S) 网络访问技能。Use when an agent needs lightweight network requests such as public web pages, JSON APIs, RSS, sitemap, metadata checks, redirects, static HTML extraction, or file downloads without browser interaction.
Use when the user asks to view, list, create, configure, switch, verify, archive, delete, or reason about independent agent profiles / operation windows in ugk-pi, including Chinese requests like “我有哪些agent”, “有哪些 agent”, “创建 agent”, “切换 agent”, “删除 agent”, “给 search agent 安装技能”, “给其他 agent 安装技能”, or “搜索 Agent 有哪些技能”. Do not use for legacy .pi/agents subagent files unless the user explicitly says subagent.
| name | project-planning |
| description | 用于 ugk-pi 项目的快速上手、/init、方案收敛和实施前规划。适用于需要先搞清楚项目现状、边界、目录职责、运行方式和后续执行顺序的任务。 |
当任务处于下面这些场景时使用本技能：
/init 或要求“先了解项目”优先读取这些文件，不要一上来乱翻整个仓库：
AGENTS.mdREADME.md.codex/plans/ 下最新相关计划src/server.tssrc/agent/agent-service.tssrc/agent/agent-session-factory.tssrc/routes/chat.tssrc/ui/playground.tsreferences/pi-mono/packages/coding-agent/README.mdreferences/pi-mono/packages/coding-agent/docs/settings.mdreferences/pi-mono/AGENTS.md如果用户问“当前有哪些技能”或“某个 skill 是否生效”，优先看：
GET /v1/debug/skills不要把模型自述当成事实源。
在没有更新信息前，先按下面这些事实理解项目：
pi-coding-agent 的自定义 HTTP agent 原型，不是完整业务产品自定义 agent + HTTP API + playground + 后续 IM 接入GET /healthzGET /playgroundGET /v1/debug/skillsPOST /v1/chatPOST /v1/chat/streamsrc/server.tssrc/agent/src/routes/src/ui/playground.tsreferences/pi-mono/.pi/skillsruntime/skills-userruntime/skills-user 后，下一条消息即可生效，不需要重启 Docker先判断这次任务属于哪类：
如果只是 /init、方案对齐或项目理解，不要一上来改业务代码。
至少要搞清楚这些问题：
给用户的总结至少应包含：
如果用户要执行计划，再补：
如果任务明显是多步骤实施，不要只在聊天里空口白话，写到：
.codex/plans/YYYY-MM-DD-<topic>.md计划文档里至少写清：
references/pi-mono/，除非用户明确要求同步参考镜像/v1/debug/skillsruntime/skills-user