git:20261009.d901896 to git:20261012.df6701c

15 added, 15 removed. Audit A to A.

# TeamAI CLI

- CLI for syncing team skills, rules, docs, and env across AI coding tools. Package: [`teamai-cli`](https://www.npmjs.com/package/teamai-cli).

+ CLI for managing a team's skills, rules, agents, learnings, models, MCP, and other AI assets in a git repo, and syncing them into AI coding tools. Package: [`teamai-cli`](https://www.npmjs.com/package/teamai-cli).

TypeScript, Node 20+ (`npm run lint` needs ^20.19 or >=22.12), tsup (ESM), Vitest. Commands: `npm run build`, `npx tsc --noEmit`, `npm run lint`, `npx vitest run`, `npm run test:e2e`.

## Git

- Default branch: `main`. Worktrees and PRs based on `origin/main`.

- PR only to `Tencent/teamai-cli`. Before push, check `git log origin/main..HEAD`; rebase or cherry-pick if unrelated commits appear.

- - **必须使用 Worktree**：改代码前先 `EnterWorktree`，禁止在主工作目录修改。

+ - **Use a worktree**: call `EnterWorktree` before changing code. Do not edit the main working directory.

## Rules

+ - **Occam's razor**: do not add a new CLI command early. Skip it unless it is necessary. Reuse or extend an existing command or option.

- CLI user-facing output must be English. No Chinese in production code. Tests assert English output.

- - **文档结构**：`docs/README.md` 是总目录，新增或移动文档必须同步登记。面向用户的文档中英双版：顶层 `name.md` / `name.zh-CN.md`，使用指南分页为 `docs/guide/<page>.md`（英文）与 `docs/guide/zh-CN/<page>.md`（中文），行为变更时两版同步改。`docs/designs/`（设计稿，开头一行 `> Status:`，并在 `docs/designs/README.md` 登记状态）与 `docs/dev/`（维护者文档）只写英文。Behavior changes must update every affected doc; grep old wording before opening the PR.

- - 文档不抄命令用法：命令与 flag 链接到 `teamai --help` / `skill-data/core/references/commands.md`，不要手工维护命令表。

- - **README 精简**：尽量少改动 README，保持简洁。确需改动时，所有语言版本（`README.md` 及全部 `README.*.md`，改前先 `ls README*` 确认清单）必须全部改完并保持一致。

- - **`skill-data/` 与文档同等对待**：那是 agent 真正读到的内容。行为变更必须同步更新受影响的 skill（`core` / `setup` / `wiki` / `share`），并在 PR 前 grep 旧措辞。

- - `skill-data/core/references/commands.md` 由 Commander 命令表生成，改动命令或 flag 后运行 `npx vitest run commands-reference -u` 重新生成。

- - **尽量不改 teamai skill 正文**：用法与 flag 的真源是 CLI 自己的 help（`teamai --help`、`teamai <cmd> --help`）和由它生成的 `commands.md`。想让 agent 更会用某命令，先把命令的 `description` / `option` help 文本写清楚，让 skill 指向 help，而不是把用法抄进 skill；只有工作流本身变化时才动 skill 正文。

- - 部署到 agent 的只有 `skills/teamai/SKILL.md`（发现入口），保持与版本无关：新增工作流是在 `skill-data/` 下加目录 + 在 stub 里加一行，不要把内容写进 stub。

- - **奥卡姆剃刀**：避免过早添加新 CLI 命令；非必要不加；优先复用或扩展现有命令与选项。

+ - **Doc layout**: user-facing docs are bilingual. Top-level files are `name.md` / `name.zh-CN.md`. Guide pages are `docs/guide/<page>.md` (English) and `docs/guide/zh-CN/<page>.md` (Chinese). A behavior change updates both. `docs/designs/` (design notes: a `> Status:` line at the top, and a status entry in `docs/designs/README.md`) and `docs/dev/` (maintainer docs) are English only. Behavior changes must update every affected doc; grep old wording before opening the PR.

+ - **Change docs rarely**: leave them alone when you can. A bugfix that does not change behavior a user runs into does not need a doc change. When you do edit docs, write them so you can understand them. Do not make them complicated.

+ - **Keep the README short**: change it as little as possible. When a change is required, update every language (`README.md` and every `README.*.md`; run `ls README*` first) and keep them consistent.

+ - **Treat `skill-data/` like docs**: that is what the agent actually reads. A behavior change must update the affected skills (`core` / `setup` / `wiki` / `share`), and grep the old wording before the PR.

+ - `skill-data/core/references/commands.md` is generated from the Commander command table. After changing a command or flag, regenerate it with `npx vitest run commands-reference -u`.

+ - **Leave the teamai skill body alone**: the source of truth for usage and flags is the CLI help (`teamai --help`, `teamai <cmd> --help`) and the generated `commands.md`. To make an agent better at a command, clarify that command's `description` and option help, and point the skill at help, instead of copying usage into the skill. Edit the skill body only when the workflow itself changes.

+ - Only `skills/teamai/SKILL.md` (the discovery entry) is deployed to the agent. Keep it version-independent: a new workflow is a directory under `skill-data/` plus one line in the stub. Do not put the content in the stub.

- ## PR 前测试

+ ## Testing before a PR

- 改动运行时行为的 PR（docs-only / tests-only 之外），`npm run build` 后必须用真实 CLI 对本次改动做端到端验证，不能只跑 type check / unit test；**一次代表性的 real-CLI 运行即可**，把实际通过的验证记录贴进 PR。docs-only / tests-only 的改动无需 e2e 记录。

+ A PR that changes runtime behavior (anything other than docs-only / tests-only) must, after `npm run build`, verify the change end to end with the real CLI. Type check and unit tests are not enough. **One representative real-CLI run is enough.** Paste the record of what actually passed into the PR. A docs-only or tests-only change needs no e2e record.

Iterate with `npm run test:e2e -- <test-file>`; run the full suite only when changing the E2E runner, shared fixtures, or test isolation ([CONTRIBUTING.md](.github/CONTRIBUTING.md#testing-guidelines)).

- 不要求覆盖下面的完整 provider × agent 矩阵——额外 provider / agent 的覆盖交给 CI，或在本地环境不具备时说明即可：

+ Do not cover the full provider × agent matrix below. Leave extra providers and agents to CI, or say so when the local environment cannot run them:

- - Agent：Claude、Codex、CodeBuddy、OpenCode

- - Provider：`git`、`gitlab`、`github`

+ - Agents: Claude, Codex, CodeBuddy, OpenCode

+ - Providers: `git`, `gitlab`, `github`

## Self review before push

Review the whole branch diff, not only the last change. For every piece of

shared state, list every reader and every writer.

## Code Review Rules

- The PR description must document sufficient testing. For a PR that changes

runtime behavior (anything beyond a docs-only or tests-only diff), that

includes an end-to-end / real-CLI verification record, not only unit tests

or type checks — flag such a PR that lacks one as `[P1 blocking]`. A

docs-only or tests-only PR needs no e2e record; do not flag it for that.

Do NOT require a full provider × agent matrix — one representative real-CLI

run is enough. Missing coverage of extra providers (`gitlab`/`github`) or

agents (`Codex`/`CodeBuddy`/`OpenCode`) is at most `[P3 nit]` when the author

has flagged it as untestable in this environment or deferred to CI, never

`[P1 blocking]`. A test record naming an older commit than the head is a

note, not a blocking finding; the body may have been edited after the review

pass started.

- Do not over-review. Report only findings you are confident are real in the

current diff. Do not cap how many findings you report: every real bug should

surface in one pass, not be deferred to a later one. Instead, gate severity

by evidence — every `[P1 blocking]` must cite either a concrete failure

scenario (the input or state that triggers it and the resulting misbehavior)

or the exact `## Code Review Rules` item it breaks. A finding that can cite

neither is at most `[P2 non-blocking]`; a speculative or theoretical risk

that needs an unlikely precondition to trigger is at most `[P3 nit]`. Never

restate a finding already resolved in the current diff.

- Reject over-engineering. Favor the smallest code that solves the problem;

flag speculative abstractions, unused flexibility or config, error handling

for cases that cannot occur, and new CLI commands added where an existing

command could be reused or extended.

- Changes must be surgical. Every changed line should trace directly to the

PR's stated goal; flag unrelated drive-by edits.

- Label every finding with an explicit severity a first-time reader can

understand — never a bare `P1`/`P2`/`P3` code. Keep the `P` marker but spell

out what it means inline on each finding, using the PR author's language:

`[P1 blocking]` for issues that must be fixed before merge,

`[P2 non-blocking]` for suggestions that do not block merge, and `[P3 nit]`

for minor or optional polish, theoretical edge cases, and coverage deferred

to CI. (In Chinese, `[P1 阻断]` / `[P2 非阻断]` / `[P3 可选]`.)