init

立项 - 从想法创建项目,自动在相关 Agent 的 Discord 频道创建 Thread 并下发初始任务。Triggers: '立项', '创建项目', '新项目', 'create project', 'init project', '开个项目', '组个项目组'

3,891 stars

Best use case

init is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

立项 - 从想法创建项目,自动在相关 Agent 的 Discord 频道创建 Thread 并下发初始任务。Triggers: '立项', '创建项目', '新项目', 'create project', 'init project', '开个项目', '组个项目组'

Teams using init should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/init/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/alexxxiong/inspirai-project/skills/init/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/init/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How init Compares

Feature / AgentinitStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

立项 - 从想法创建项目,自动在相关 Agent 的 Discord 频道创建 Thread 并下发初始任务。Triggers: '立项', '创建项目', '新项目', 'create project', 'init project', '开个项目', '组个项目组'

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# /project:init - 立项

从一个想法出发,分析需要哪些 Agent 参与,批量在 Discord 频道创建项目 Thread,并给每个 Agent 下发初始任务指令。

## 使用方式

```
/project:init <项目名> [--agents <agent1,agent2,...>] [--team <产品开发|运行分析|营销发布|AI漫剧|全部>]

示例:
/project:init 互动漫画MVP
/project:init 数据看板重构 --team 产品开发
/project:init 春节营销活动 --agents yangjian,libai,yuelao,guanyin
```

## 团队花名册

读取项目目录下的 `AGENTS.md` 获取完整团队信息。如果不存在,使用以下默认编制:

| 团队 | 成员 |
|------|------|
| 产品开发 | laojun(架构) wukong(速攻) luban(实现) zhongkui(测试) zhuge(需求) |
| 运行分析 | yuantg(数据) baozheng(审查) nvwa(运维) jiangzy(调度) |
| 营销发布 | yangjian(营销) libai(文案) yuelao(洞察) guanyin(协调) |
| AI漫剧 | caoxq(原著) tangxz(编剧) yangyr(导演) gongsb(分镜) feitian(特效) wudaozi(美术) nezha(创意) |

## 执行步骤

### Step 1: 分析项目需要哪些 Agent

根据用户描述的项目内容,智能判断需要哪些 Agent 参与:

- 如果用户指定了 `--agents`,直接使用
- 如果用户指定了 `--team`,使用该团队全员
- 否则,根据项目描述自动推荐:
  - 技术/产品类 → 产品开发团队核心成员 + 相关支援
  - 内容/创作类 → AI漫剧团队 + 李白(文案)
  - 营销/增长类 → 营销发布团队 + 袁天罡(数据)
  - 综合大项目 → 跨团队组合

输出推荐的参与 Agent 列表,**等用户确认后再继续**。

### Step 2: 读取配置

读取 `~/.claude/project-skill.json`(如果存在):

```json
{
  "discord_bot_token": "Bot Token",
  "guild_id": "服务器 ID",
  "channel_map": {
    "laojun": "channel_id",
    "wukong": "channel_id"
  }
}
```

如果配置不存在,从 `~/.openclaw/openclaw.json` 中提取 Discord 配置:
- `channels.discord.accounts.default.token` → Bot Token
- `channels.discord.accounts.default.guilds.<id>.channels` → channel map
- `bindings` → agent ↔ channel 映射

### Step 3: 在 Discord 批量创建项目 Thread

对每个参与的 Agent,在其对应的 Discord Channel 中创建 Thread:

```bash
# 使用 Discord API 创建 Thread
curl -X POST "https://discord.com/api/v10/channels/{channel_id}/threads" \
  -H "Authorization: Bot {token}" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "[{项目名}] {agent职能}",
    "type": 11,
    "auto_archive_duration": 10080
  }'
```

Thread 命名规范:`[项目名] 职能描述`,例如:
- `[互动漫画] 架构设计` → laojun
- `[互动漫画] 需求文档` → zhuge
- `[互动漫画] 快速原型` → wukong

### Step 4: 向每个 Thread 发送初始任务

创建 Thread 后,用 Bot 在每个 Thread 中发送一条初始消息,内容是该 Agent 在此项目中的任务简报:

```bash
curl -X POST "https://discord.com/api/v10/channels/{thread_id}/messages" \
  -H "Authorization: Bot {token}" \
  -H "Content-Type: application/json" \
  -d '{
    "content": "📋 **项目**: {项目名}\n\n**你的任务**: {根据 agent 职能生成的具体任务描述}\n\n**项目背景**: {用户的原始想法描述}\n\n**协作成员**: {其他参与 agent 列表}\n\n请开始工作,有问题随时沟通。"
  }'
```

任务描述应根据 Agent 角色自动生成,例如:
- laojun → "请从架构层面分析技术可行性,给出技术选型建议和系统设计草案"
- zhuge → "请梳理核心需求,定义 MVP 范围,列出功能优先级"
- wukong → "待架构和需求明确后,快速搭建 POC 原型"

### Step 5: 生成项目摘要

输出项目创建摘要:

```
✅ 项目「{项目名}」已创建

参与成员:
- 太上老君(laojun) → Thread: [互动漫画] 架构设计
- 诸葛亮(zhuge) → Thread: [互动漫画] 需求文档
- ...

项目 Thread 已创建,各 Agent 已收到初始任务。
去 Discord 各频道的 Thread 里跟进讨论。
```

### Step 6: 记录项目信息

将项目信息保存到 `~/.claude/projects.json`(追加):

```json
{
  "projects": [
    {
      "name": "互动漫画MVP",
      "created_at": "2026-03-15T...",
      "agents": ["laojun", "zhuge", "wukong", "luban"],
      "threads": {
        "laojun": { "thread_id": "xxx", "name": "[互动漫画] 架构设计" },
        "zhuge": { "thread_id": "xxx", "name": "[互动漫画] 需求文档" }
      },
      "status": "active"
    }
  ]
}
```

## 注意事项

- Thread 创建后,OpenClaw 的 `threadBindings` 会自动将后续消息路由到对应 Agent 的 session
- 每个 Thread 的上下文独立,不会互相干扰
- Bot 发送的初始消息会触发 Agent 开始工作
- 如果 Agent 未响应,可能需要先 approve pairing

Related Skills

avenger-initiative

3891
from openclaw/skills

Encrypted GitHub backup and restore for any OpenClaw agent system. Creates branch-per-night backups with smart retention (7 daily, 8 weekly, 12 monthly branches). Backs up openclaw.json (AES-256 encrypted), agent memories, SOUL/IDENTITY files, cron jobs, and custom skills to a private GitHub vault. Triggers on phrases like "avenger backup", "backup system", "push to vault", "sync vault", "avenger restore", "restore from vault", "setup avenger", "avenger status", "avenger init", "configure backup", "set up backup". Also auto-runs after any critical config change.

med-initial-record-gen

3891
from openclaw/skills

从中文医患对话文本生成门诊初诊病历,输出结构化分段的病历正文(文本)。

metric-definition-catalog

3891
from openclaw/skills

把散落指标统一整理成口径、公式、归属、例外情况与常见误用。;use for metrics, catalog, analytics workflows;do not use for 编造指标来源, 替代 BI 平台配置.

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891
from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891
from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure