teamai-cli 0.19.0 → 0.20.0-beta.0

package/README.md

@@ -34,6 +34,8 @@ Create a shared-experience repo on your git host (GitHub, TGit, or CNB), **grant
 
 > Solo use needs no separate repo setup: `teamai init` checks the target repo and creates it automatically if it doesn't exist.
 
+> **No team repo yet?** Start from a template pre-loaded with production-ready skills, rules, and review agents. Browse the [teamai-hub](https://github.com/teamai-hub) org, click **Use this template**, then `teamai init` against your new repo.
+
 ### Team members
 
 ```bash
@@ -52,6 +54,22 @@ teamai init https://github.com/yourorg/project-repo --inherit-user-scope
 
 Once initialized, every AI session automatically pulls the latest skills / rules and other Harness updates published by admins — no manual sync needed.
 
+### Single-repo mode (the business repo *is* the team repo)
+
+No separate team repo. Run `teamai init .` inside an existing project and its own git repo becomes the team repo:
+
+```bash
+cd /path/to/my-project
+teamai init .          # or: teamai init --self
+```
+
+- **Knowledge** (skills / rules / docs / learnings) is committed to your repo's **main branch** under `.teamai/`, so a plain `git clone` already carries the whole team setup.
+- **Reports** (member registrations, session summaries, votes, usage stats) go to a separate **`teamai-reports` orphan branch** — they never touch main.
+- **Clone = initialized.** When a teammate clones the repo, the next `teamai` command (or AI session) auto-detects the `mode: self` marker in `.teamai/teamai.yaml` and finishes local setup automatically — no need to re-type repo/role.
+- All of teamai's git operations run in isolated worktrees, so your working tree and current branch are never touched.
+
+After `teamai init .`, commit `.teamai/` (skills, rules, docs, learnings, `teamai.yaml`, `.gitignore`) and `.claude/settings.json` to main so teammates get auto-initialized on clone.
+
 > **Full usage guide:** [docs/usage-guide.md](docs/usage-guide.md) ([中文版](docs/usage-guide.zh-CN.md)) — covers everything from team creation to day-to-day use.
 
 ## Harness Management & Distribution

package/README.zh-CN.md

@@ -34,6 +34,8 @@ npm install -g teamai-cli
 
 > 个人使用无需单独建仓：`teamai init` 会检查目标仓库，不存在时自动创建。
 
+> **还没有团队仓库？** 可以从内置了成套 skills、rules、review agents 的模板起步。浏览 [teamai-hub](https://github.com/teamai-hub) org，点 **Use this template** 生成自己的仓库，再对它执行 `teamai init`。
+
 ### 团队成员
 
 ```bash
@@ -52,6 +54,22 @@ teamai init https://github.com/yourorg/project-repo --inherit-user-scope
 
 初始化完成后，每次开启 AI 会话时都会自动拉取管理员发布的 skills / rules 等 Harness 更新，无需手动同步。
 
+### 单仓模式（业务仓即团队仓）
+
+无需单独的团队仓库。在已有项目里运行 `teamai init .`，让它自己的 git 仓库直接充当团队仓：
+
+```bash
+cd /path/to/my-project
+teamai init .          # 或：teamai init --self
+```
+
+- **知识资产**（skills / rules / docs / learnings）提交到仓库 **main 分支**的 `.teamai/` 目录，因此一次普通 `git clone` 就带上了整套团队配置。
+- **上报数据**（成员注册、会话摘要、投票、使用统计）走独立的 **`teamai-reports` 孤儿分支** —— 永不污染 main。
+- **克隆即初始化。** 团队成员 clone 仓库后，下一条 `teamai` 命令（或 AI 会话）会自动识别 `.teamai/teamai.yaml` 里的 `mode: self` 标记并自动完成本机初始化 —— 无需手抄 repo/role 参数。
+- teamai 的所有 git 操作都在隔离的 worktree 中进行，绝不触碰你的工作区和当前分支。
+
+执行 `teamai init .` 后，把 `.teamai/`（skills、rules、docs、learnings、`teamai.yaml`、`.gitignore`）和 `.claude/settings.json` 提交到 main，团队成员 clone 后即可自动初始化。
+
 > **完整使用指南**：[docs/usage-guide.zh-CN.md](docs/usage-guide.zh-CN.md)（[English](docs/usage-guide.md)）— 涵盖从团队创建到日常使用的全流程。
 
 ## Harness 管理和分发