@thinkingai/ae-cli 6.0.31 → 6.0.33

package/skills/ae-generate-tracking-plan/references/business-dimension-mapping.md

@@ -10,20 +10,20 @@
 
 ## 一、Revenue Model → Required Events
 
-| 收入模型 | 注入事件 | 事件显示名 | platform | 必带属性 |
-|---|---|---|---|---|
-| `IAA` | `ad_show` | 广告展示 | client | `ad_type`、`ad_placement`、`is_filled` |
-| `IAA` | `ad_click` | 广告点击 | client | `ad_type`、`ad_placement`、`ad_network` |
-| `IAA` | `ad_reward_get` | 激励广告奖励领取 | client | `ad_type`、`ad_placement`、`reward_type`、`reward_amount` |
-| `IAP` | `payment` | 支付成功 | server | `order_id`、`pay_amount`、`currency_type`、`payment_name`、`payment_type` |
-| `IAP` | `payment_fail` | 支付失败 | server | `order_id`、`fail_reason`、`payment_name` |
-| `mixed` | 同 IAA + IAP 所有事件 | | | |
-| `subscription` | `subscription_start` | 订阅开始 | server | `subscription_id`、`plan_name`、`start_time` |
-| `subscription` | `subscription_renew` | 订阅续费 | server | `subscription_id`、`renew_amount`、`currency_type` |
-| `subscription` | `subscription_cancel` | 订阅取消 | server | `subscription_id`、`cancel_time`、`cancel_reason` |
-| `commission` | `order_create` | 订单创建 | server | `order_id`、`order_amount`、`commission_rate` |
-| `commission` | `order_paid` | 订单支付 | server | `order_id`、`pay_amount`、`commission_amount` |
-| `commission` | `commission_settled` | 佣金结算 | server | `settlement_id`、`commission_amount`、`settle_time` |
+| 收入模型 | 注入事件 | 事件显示名 | event_tag | platform | 必带属性 |
+|---|---|---|---|---|---|
+| `IAA` | `ad_show` | 广告展示 | 广告 | client | `ad_type`、`ad_placement`、`is_filled` |
+| `IAA` | `ad_click` | 广告点击 | 广告 | client | `ad_type`、`ad_placement`、`ad_network` |
+| `IAA` | `ad_reward_get` | 激励广告奖励领取 | 广告 | client | `ad_type`、`ad_placement`、`reward_type`、`reward_amount` |
+| `IAP` | `payment` | 支付成功 | 支付 | server | `order_id`、`pay_amount`、`currency_type`、`payment_name`、`payment_type` |
+| `IAP` | `payment_fail` | 支付失败 | 支付 | server | `order_id`、`fail_reason`、`payment_name` |
+| `mixed` | 同 IAA + IAP 所有事件 | | | | |
+| `subscription` | `subscription_start` | 订阅开始 | 订阅 | server | `subscription_id`、`plan_name`、`start_time` |
+| `subscription` | `subscription_renew` | 订阅续费 | 订阅 | server | `subscription_id`、`renew_amount`、`currency_type` |
+| `subscription` | `subscription_cancel` | 订阅取消 | 订阅 | server | `subscription_id`、`cancel_time`、`cancel_reason` |
+| `commission` | `order_create` | 订单创建 | 交易 | server | `order_id`、`order_amount`、`commission_rate` |
+| `commission` | `order_paid` | 订单支付 | 交易 | server | `order_id`、`pay_amount`、`commission_amount` |
+| `commission` | `commission_settled` | 佣金结算 | 交易 | server | `settlement_id`、`commission_amount`、`settle_time` |
 
 ---
 
@@ -52,17 +52,19 @@
 **解析结果**：
 
 ```
-节点1: 刷关卡 → stage_start / stage_complete / stage_fail
-节点2: 获得金币 → token_get (token_type=gold, source=关卡)
-节点3: 抽卡 → gacha_draw (pool_type, draw_count)
-节点4: 获取角色 → hero_get (hero_id, hero_star)
+节点1: 刷关卡 → stage_start / stage_complete / stage_fail  [event_tag: 关卡/Stage]
+节点2: 获得金币 → token_get (token_type=gold, source=关卡)  [event_tag: 资源/Resource]
+节点3: 抽卡 → gacha_draw (pool_type, draw_count)  [event_tag: 抽卡/Gacha]
+节点4: 获取角色 → hero_get (hero_id, hero_star)  [event_tag: 养成/Growth]
 ```
 
 ---
 
 ## 三、功能入口 → 模块事件组
 
-| 功能入口 | 事件名 | 显示名 | platform | 典型属性 |
+> 第一列"模块"即该事件的 `event_tag` 值。注入时翻译为用户语言。
+
+| 模块 (event_tag) | 事件名 | 显示名 | platform | 典型属性 |
 |---|---|---|---|---|
 | 关卡 | `stage_start` | 关卡开始 | client | `stage_id`、`stage_type`、`difficulty` |
 | 关卡 | `stage_complete` | 关卡完成 | server | `stage_id`、`star_rating`、`score` |
@@ -200,26 +202,36 @@
 
 > 根据应用类型/游戏品类，自动注入对应模块的事件组。
 > 品类由 Phase 0 的 `meta.scenario` 或用户描述推断。
+>
+> **event_tag 规则**：本表中每行的"模块"列即该事件的 `event_tag` 值。注入时需翻译为用户语言。
+> 例如 战斗→`Battle`, 养成→`Growth`, 抽卡→`Gacha`, 资源→`Resource`, 广告→`Ads`, 支付→`Payment`。
 
-### 8.1 游戏类 — 通用基础模块（所有游戏必选）
+### 8.0 通用基础模块（所有品类适用）
+
+> 以下事件不属于任何具体功能模块（关卡/商城/抽卡等），统一使用 `基础事件`（Basic）标签。
+> 区别于 `系统事件`（System Event，SDK 自动采集的 `ta_*` 事件）。
 
 **用户生命周期**：
 
-| 事件名 | 显示名 | platform | 必带属性 |
-|---|---|---|---|
-| `new_device` | 设备激活 | client | `channel` |
-| `register` | 用户注册 | server | `register_type` |
-| `login` | 用户登录 | both | `account_id` |
-| `logout` | 用户登出 | both | `session_duration` |
+| 模块 | 事件名 | 显示名 | platform | 必带属性 |
+|---|---|---|---|---|
+| 基础事件 | `new_device` | 设备激活 | client | `channel` |
+| 基础事件 | `register` | 用户注册 | server | `register_type` |
+| 基础事件 | `login` | 用户登录 | both | `account_id` |
+| 基础事件 | `logout` | 用户登出 | both | `session_duration` |
 
 **成长模块**：
 
-| 事件名 | 显示名 | platform | 必带属性 |
-|---|---|---|---|
-| `create_role` | 创建角色 | server | `role_id`、`role_name`、`server_id` |
-| `guide_complete` | 完成新手引导 | client | `guide_id`、`guide_step` |
-| `level_up` | 升级 | server | `level`、`level_before` |
-| `vip_levelup` | VIP升级 | server | `vip_level` |
+| 模块 | 事件名 | 显示名 | platform | 必带属性 |
+|---|---|---|---|---|
+| 基础事件 | `create_role` | 创建角色 | server | `role_id`、`role_name`、`server_id` |
+| 基础事件 | `guide_complete` | 完成新手引导 | client | `guide_id`、`guide_step` |
+| 基础事件 | `level_up` | 升级 | server | `level`、`level_before` |
+| 基础事件 | `vip_levelup` | VIP升级 | server | `vip_level` |
+
+### 8.1 游戏类 — 通用基础模块（所有游戏必选）
+
+> 以下为游戏品类通用的基础事件，所有游戏品类均应包含。详见 8.0 通用基础模块。
 
 ### 8.2 游戏类 — 按品类
 
@@ -422,4 +434,57 @@
 
 - 必须有 ≥2 个自定义属性
 - 必须标注事件标签（模块归属）和采集端
-- 命名符合 snake_case
+- 命名符合 snake_case
+
+---
+
+## 附录：event_tag 多语言对照表
+
+> 生成 event_tag 时，根据用户语言从本表选取对应翻译。
+> 代码层（`src/xlsx/write.ts` 的 `CANONICAL_TAG`）也同步维护此表，用于 xlsx 输出时按业务重要性排序。
+
+| 中文 | English | 日本語 | 한국어 |
+|---|---|---|---|
+| 基础事件 | Basic | 基本イベント | 기본 이벤트 |
+| 系统事件 | System Event | システムイベント | 시스템 이벤트 |
+| 战斗 | Battle | 戦闘 | 전투 |
+| 关卡 | Stage | ステージ | 스테이지 |
+| 副本 | Dungeon | ダンジョン | 던전 |
+| 抽卡 | Gacha | ガチャ | 가챠 |
+| 养成 | Growth | 育成 | 육성 |
+| 资源 | Resource | リソース | 리소스 |
+| 广告 | Ads | 広告 | 광고 |
+| 支付 | Payment | 支払い | 결제 |
+| 订阅 | Subscription | サブスクリプション | 구독 |
+| 商城 | Shop | ショップ | 상점 |
+| 任务 | Quest | クエスト | 퀘스트 |
+| 成就 | Achievement | 実績 | 업적 |
+| 签到 | Check-in | チェックイン | 출석체크 |
+| 排行榜 | Leaderboard | ランキング | 리더보드 |
+| 公会 | Guild | ギルド | 길드 |
+| 社交 | Social | ソーシャル | 소셜 |
+| 建筑 | Building | 建築 | 건설 |
+| 联盟 | Alliance | 同盟 | 연맹 |
+| 装备 | Equipment | 装備 | 장비 |
+| 交易 | Trade | トレード | 거래 |
+| 复活 | Revive | 復活 | 부활 |
+| Slots | Slots | スロット | 슬롯 |
+| 抽奖 | Lottery | 抽選 | 추첨 |
+| 奖励 | Reward | 報酬 | 보상 |
+| 提现 | Withdraw | 引き出し | 출금 |
+| 发现 | Discovery | 発見 | 발견 |
+| 商品 | Product | 商品 | 상품 |
+| 订单 | Order | 注文 | 주문 |
+| 售后 | After-sales | アフターサービス | A/S |
+| 内容 | Content | コンテンツ | 콘텐츠 |
+| 互动 | Interaction | インタラクション | 인터랙션 |
+| 关系 | Relationship | 関係 | 관계 |
+| 直播 | Live | ライブ | 라이브 |
+| 引导 | Onboarding | オンボーディング | 온보딩 |
+| 课程 | Course | コース | 코스 |
+| 报名 | Enrollment | 申し込み | 신청 |
+| 测验 | Quiz | クイズ | 퀴즈 |
+| 创作 | Creation | 創作 | 창작 |
+| 素材 | Material | 素材 | 소재 |
+| 导出 | Export | エクスポート | 내보내기 |
+| 内容播放 | Playback | 再生 | 재생 |

package/skills/ae-generate-tracking-plan/references/te-api.md

@@ -99,7 +99,7 @@ Upload is a two-step capability-gateway flow:
 { "project_id": 1603, "input_file_id": "...", "lang": "zh" }
 ```
 
-- `lang` is optional for backward compatibility, but Agents should pass the generated xlsx language (`zh` / `en` / `ja` / `ko`) so the backend resolves localized sheet names and headers consistently.
+- Agents MUST pass `lang` with the generated xlsx language (`zh` / `en` / `ja` / `ko`) so the backend resolves localized sheet names and headers consistently.
 - Response: `{ return_code: 0, return_message: "success" }` on success.
 
 **合并语义**：对事件走 **merge-by-name**（同名不覆盖、新名新增）。若要完全替换，

package/skills/ae-generate-tracking-plan/references/xlsx-schema.md

@@ -95,20 +95,22 @@ A-E 在 writer 里用 `mergeCells` 合并。
 
 ## 类型枚举
 
-### PropType（xlsx 中文值 ↔ canonical）
-
-| canonical（draft.json） | xlsx 写入值 | xlsx 读取可接受值（含行业 alias） |
-|---|---|---|
-| `string` | `文本` | `文本` / `字符串` |
-| `number` | `数值` | `数值` |
-| `bool` | `布尔` | `布尔` |
-| `datetime` | `时间` | `时间` |
-| `object` | `对象` | `对象` |
-| `array_row` | `对象组` | `对象组` |
-| `array_string` | `列表` | `列表` |
-
-Writer 方向统一用第二列（官方中文正式名），不输出 alias。
-Reader 方向对 alias / 未知值做 fallback 并打 stderr warning。
+### PropType（canonical ↔ 各语言显示值）
+
+> Writer 按 `draft.meta.lang` 输出对应语言列的值。
+
+| canonical（draft.json） | zh | en | ja | ko | 读取额外兼容（alias） |
+|---|---|---|---|---|---|
+| `string` | `文本` | `String` | `ストリング` | `String` | `字符串` / `string` / `文字列` / `テキスト` / `텍스트` / `문자열` |
+| `number` | `数值` | `Number` | `数値` | `Number` | `number` / `숫자` |
+| `bool` | `布尔` | `Boolean` | `ブール値` | `Boolean` | `boolean` / `Bool` / `ブール` / `부울` |
+| `datetime` | `时间` | `Date` | `時間` | `Date` | `datetime` / `DateTime` / `Time` / `日時` / `날짜시간` / `time` |
+| `object` | `对象` | `Row` | `オブジェクト` | `Row` | `object` / `Object` |
+| `array_row` | `对象组` | `Array Row` | `オブジェクトグループ` | `Array Row` | `object[]` / `Object Array` / `オブジェクト配列` / `object_array` / `객체 배열` |
+| `array_string` | `列表` | `List` | `リスト` | `List` | `string[]` / `String Array` / `配列` / `string_array` / `리스트` |
+
+> 旧值兼容（2026-07-15 前生成的 xlsx）：`en` 旧值 `string`/`number`/`boolean`/`datetime`/`object`/`object[]`/`string[]`，
+> `ja` 旧值 `オブジェクト配列`/`配列`，`ko` 旧值 `time`/`object_array`/`string_array` 在 reader 中仍可识别。
 
 ### UpdateType（用户属性 `更新方式`）
 

package/skills/ae-kb/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: ae-kb
 version: 1.0.0
-description: "AE/TE knowledge base CLI manual for creating, querying, LLM-powered ask, deterministic index/grep/read retrieval, checking status, uploading, compiling, schema generation, URL sources, source deletion, and knowledge base deletion. Use when the user asks to manage TE/AE/ThinkingEngine knowledge bases, upload documents or URLs to a knowledge base, query knowledge, ask knowledge bases with an LLM, inspect knowledge base indexes, search knowledge base pages, read a specific knowledge base page, check knowledge base status, generate schemas, compile knowledge, remove sources, or delete a knowledge base. Must use ae-cli kb commands and must not guess knowledge base names, scopes, page paths, source display names, JSON payload shapes, or URL formats."
+description: "AE/TE knowledge base CLI manual for creating, querying, LLM-powered ask, listing accessible knowledge bases, deterministic index/grep/read retrieval, checking status, uploading, compiling, schema generation, URL sources, source deletion, and knowledge base deletion. Use when the user asks to manage TE/AE/ThinkingEngine knowledge bases, upload documents or URLs to a knowledge base, query knowledge, ask knowledge bases with an LLM, list accessible knowledge bases, inspect knowledge base indexes, search knowledge base pages, read a specific knowledge base page, check knowledge base status, generate schemas, compile knowledge, remove sources, or delete a knowledge base. Must use ae-cli kb commands and must not guess knowledge base names, scopes, page paths, source display names, JSON payload shapes, or URL formats."
 ---
 
 # ae-kb
@@ -14,13 +14,14 @@ ae-cli kb +<command> [options]
 
 ## Global Rules
 
-- Use this skill for TE/AE knowledge base tasks: create, query, ask with LLM, inspect indexes, grep pages, read pages, check status, upload sources, add URL sources, generate schema, compile, remove source files, and delete knowledge bases.
-- Read and ordinary `write` operations can run directly after required inputs and user intent are known. Only `high-risk-write` operations use the confirmation gate.
+- Use this skill for TE/AE knowledge base tasks: create, query, ask with LLM, list accessible knowledge bases, inspect indexes, grep pages, read pages, check status, upload sources, add URL sources, generate schema, compile, remove source files, and delete knowledge bases.
+- Read operations can run directly after required inputs are known. Write operations require explicit user intent and normally keep the confirmation prompt unless the user asks to bypass it.
 - Prefer `--dry-run` before destructive or broad writes when the user has not already validated the target.
 - Do not invent knowledge base names, scopes, source display names, or JSON payloads. Ask the user or query known context when values are missing.
 - JSON flags must be valid JSON strings, usually wrapped in single quotes in shell commands.
-- Successful commands return JSON by default. Use `--format table` only when a table is easier for a human to scan.
+- Successful commands return JSON by default. Use `--format table` only when a table is easier for a human to scan. Envelope may include optional `_notice.host_compat`.
 - `--host <url>` overrides the active AE host. It is available on every command and may be placed after the subcommand, e.g. `ae-cli kb +<command> --host <url>`.
+- **CRITICAL — Host compat (do this first):** After each `ae-cli` run, check stderr and `_notice.host_compat`. If either is present, open the user reply with a short ⚠️ version warning and **quote the `npm i -g` / `npx skills add` (or update-cluster) lines verbatim**, then present the business result. Soft tip; `ok: true` can still carry the notice.
 - For external-agent retrieval, prefer the deterministic flow `+index` -> `+grep` -> `+read`: inspect navigation, locate candidate pages, then open the exact page or line window. Use `+ask` only when the user wants an LLM-synthesized answer and accepts token consumption.
 
 ## Commands
@@ -29,6 +30,7 @@ ae-cli kb +<command> [options]
 |---|---:|---|
 | `+query` | read | Query one or more knowledge bases with a natural-language question. |
 | `+ask` | read | LLM-powered Q&A over knowledge bases. Consumes platform tokens. |
+| `+list` | read | List accessible knowledge bases filtered by buildStatus (default: compiled). |
 | `+index` | read | List accessible knowledge bases and their `index.md` navigation maps. |
 | `+grep` | read | Keyword-search knowledge base pages and return matched lines with context. |
 | `+read` | read | Read a full knowledge base page or a line window. |
@@ -145,21 +147,35 @@ ae-cli kb +ask \
   --question "How do we troubleshoot payment alerts?" \
   --sources '[{"scope":"company","name":"engineering-handbook"}]' \
   --model-id claude-sonnet-4-6 \
-  --max-turns 10 \
+  --max-turns 50 \
   --locale zh
 ```
 
 - `--question`, alias `-q`: required natural-language question (1-2000 characters).
 - `--sources`: optional JSON array of knowledge base refs. Omit to search all accessible knowledge bases.
 - `--model-id`: optional LLM model ID. Omit to use the platform default.
-- `--max-turns`: optional agent turn limit (1-20, server default 10).
+- `--max-turns`: optional agent turn limit (1-100, server default 50).
 - `--locale`: optional locale: `zh`, `en`, `ja`, or `ko`.
 
+### List Accessible Knowledge Bases
+
+Use `+list` when you only need accessible knowledge base metadata without loading `index.md` navigation maps. By default it returns knowledge bases with `buildStatus: compiled`:
+
+```bash
+ae-cli kb +list
+ae-cli kb +list --locale zh
+ae-cli kb +list --build-status compiled
+```
+
 ### Explore Knowledge Base Pages
 
 Use the deterministic retrieval primitives when an agent needs to explore knowledge base content like a code repository. These endpoints do not call an LLM on the server side.
 
-Start with `+index` to see accessible knowledge bases and navigation maps:
+Start with `+list` or `+index` to discover accessible knowledge bases. Use `+index` when you also need navigation maps:
+
+```bash
+ae-cli kb +list
+```
 
 ```bash
 ae-cli kb +index \
@@ -187,6 +203,7 @@ ae-cli kb +read \
 
 Retrieval rules:
 
+- `+list` accepts optional `--build-status` (default `compiled`) and `--locale`. Returns accessible knowledge base metadata including `buildStatus`, without `index.md` navigation maps.
 - `+index` accepts optional `--sources` and `--locale`; omit `--sources` to list all accessible knowledge bases.
 - `+grep` requires `--query` / `-q`; optional `--sources`, `--top-k` (1-50, default 10), and `--locale`.
 - `+read` requires `--source` pointing to exactly one knowledge base and `--path` relative to the knowledge base root; optional `--offset`, `--limit` (1-10000), and `--locale`.
@@ -226,16 +243,26 @@ ae-cli kb +query --query "<question>" --sources '[{"scope":"company","name":"kb-
 ### `+ask`
 
 ```bash
-ae-cli kb +ask --question "<question>" [--sources '[{"scope":"company","name":"kb-name"}]'] [--model-id claude-sonnet-4-6] [--max-turns 10] [--locale zh|en|ja|ko]
+ae-cli kb +ask --question "<question>" [--sources '[{"scope":"company","name":"kb-name"}]'] [--model-id claude-sonnet-4-6] [--max-turns 50] [--locale zh|en|ja|ko]
 ```
 
 - `--question`, alias `-q`: required natural-language question (1-2000 characters).
 - `--sources`: optional JSON array of knowledge base refs. Omit to search all accessible knowledge bases.
 - `--model-id`: optional LLM model ID. Omit to use the platform default.
-- `--max-turns`: optional agent turn limit, 1-20, server default 10.
+- `--max-turns`: optional agent turn limit (1-100, server default 50).
 - `--locale`: optional locale: `zh`, `en`, `ja`, or `ko`.
 - **Token cost**: this command invokes an LLM on the server and consumes platform tokens. Prefer `+index` -> `+grep` -> `+read` for token-free deterministic retrieval.
 
+### `+list`
+
+```bash
+ae-cli kb +list [--build-status compiled] [--locale zh|en|ja|ko]
+```
+
+- `--build-status`: optional build status filter (default: `compiled`).
+- `--locale`: optional locale: `zh`, `en`, `ja`, or `ko`.
+- Response items include `buildStatus`.
+
 ### `+index`
 
 ```bash

package/skills/ae-metadata/SKILL.md

@@ -21,8 +21,9 @@ Parallel to **`ae-analysis`** (MCP `analysis_meta` for metadata lists/governance
 | `--dry-run` | Optional: confirm ready to run (`/dry-run`). Alone for risk/output preview. Do not stack with `--validate`. |
 
 Output and errors:
-- Success: JSON envelope (default).
+- Success: JSON envelope (default). May include optional `_notice.host_compat`.
 - Failure: `{ "ok": false, "error": { "type", "message", "hint" } }`, non-zero exit.
+- **CRITICAL — Host compat (do this first):** After each `ae-cli` run, check stderr and `_notice.host_compat`. If either is present, open the user reply with a short ⚠️ version warning and **quote the `npm i -g` / `npx skills add` (or update-cluster) lines verbatim**, then present the business result. Soft tip; `ok: true` can still carry the notice.
 
 Safety:
 - Read-only commands can run directly after IDs/names are verified.
@@ -87,5 +88,5 @@ ae-cli analysis input-file purpose list --project-id 1
 
 ## Related Skills
 
-- **`ae-analysis`**: `analysis_meta +list_events` / `+list_properties` to discover names before detail get.
+- **`ae-analysis`**: `analysis-meta event list` / `analysis-meta property list` to discover names before detail get.
 - **Dev workflow**: `.cursor/skills/te-cli-capability-gateway` — inspect gateway schema when adding new metadata capabilities.

package/skills/ae-metadata/references/metadata_event_get.md

@@ -35,18 +35,18 @@ Gateway request body uses snake_case `input`:
 
 ## Decision Rules
 
-- Prefer **`metadata event get`** over `analysis_meta +list_events` when you need **full detail + virtual definition**, not browsing or fuzzy search.
-- Use `ae-analysis` → `analysis_meta +list_events` first when the event name is unknown or you need keyword search / pagination.
+- Prefer **`metadata event get`** over `analysis-meta event list` when you need **full detail + virtual definition**, not browsing or fuzzy search.
+- Use `ae-analysis` → `analysis-meta event list` first when the event name is unknown or you need keyword search / pagination.
 - If the gateway returns `EVENT_NOT_FOUND`, verify `event_name` spelling and `project_id`; do not invent names.
 - Auth: `cli-token` header (ae-cli injects automatically in sandbox; local CLI uses `getCliToken()`).
 
 ## Recommended Chaining
 
-- `ae-analysis`: `analysis_meta +list_events` (discover name) → `metadata event get` (detail)
+- `ae-analysis`: `analysis-meta event list` (discover name) → `metadata event get` (detail)
 - `metadata event get` → `metadata property get` (inspect properties listed in response)
 
 ## Next Steps After Failure
 
-- Empty or not found: confirm project id and exact `event_name` from `+list_events`.
+- Empty or not found: confirm project id and exact `event_name` from `analysis-meta event list`.
 - Permission error: confirm metadata view permission in the project.
 - Gateway unavailable: confirm nginx routes `/api/cli/metadata/` and backend capability catalog is deployed.

package/skills/ae-metadata/references/metadata_property_dimension_table_bind_existing.md

@@ -22,6 +22,6 @@ ae-cli metadata property bind-existing-dimension-table --project-id <project_id>
 
 ## Decision Rules
 
-- Confirm the property with `metadata property get` or `analysis_meta +list_properties`.
+- Confirm the property with `metadata property get` or `analysis-meta property list`.
 - Confirm the data table with `metadata data-table get`.
 - This is an ordinary `write` command and does not require CLI confirmation.

package/skills/ae-metadata/references/metadata_property_get.md

@@ -37,18 +37,18 @@ Gateway request body uses snake_case `input`:
 
 ## Decision Rules
 
-- Prefer **`metadata property get`** over `analysis_meta +list_properties` when you need **full detail + virtual definition**, not browsing or fuzzy search.
-- Use `ae-analysis` → `analysis_meta +list_properties` first when the property name is unknown or you need keyword search / pagination.
+- Prefer **`metadata property get`** over `analysis-meta property list` when you need **full detail + virtual definition**, not browsing or fuzzy search.
+- Use `ae-analysis` → `analysis-meta property list` first when the property name is unknown or you need keyword search / pagination.
 - `property_scope` must be exactly `event` or `user` (backend accepts case-insensitive).
 - Virtual / dict / exchange-rate properties are addressed by `property-name` only; do not pass legacy `prop_name`.
 - Event-scoped names like `#account_id` must be passed literally (quote in shell when `#` is present).
 
 ## Recommended Chaining
 
-- `ae-analysis`: `analysis_meta +list_properties` (discover name + scope) → `metadata property get` (detail)
+- `ae-analysis`: `analysis-meta property list` (discover name + scope) → `metadata property get` (detail)
 - `metadata event get` → `metadata property get` (follow properties from event detail)
 
 ## Next Steps After Failure
 
-- Not found: confirm scope (`event` vs `user`) and exact name from `+list_properties`.
+- Not found: confirm scope (`event` vs `user`) and exact name from `analysis-meta property list`.
 - Permission error: confirm metadata view permission in the project.

package/skills/ae-team/SKILL.md

@@ -25,8 +25,9 @@ Global parameters:
 | `--dry-run` | Show request details without executing. |
 
 Output and errors:
-- Successful commands return machine-readable JSON by default.
+- Successful commands return machine-readable JSON by default. Envelope may include optional `_notice.host_compat`.
 - Failed commands return `{ "ok": false, "error": { "type": "...", "message": "...", "hint": "..." } }` and exit non-zero.
+- **CRITICAL — Host compat (do this first):** If stderr or `_notice.host_compat` has a version warning, open the user reply with ⚠️ and **quote `npm i -g` / `npx skills add` (or update-cluster) lines verbatim**, then list projects/results. Never omit when summarizing. Soft tip; `ok: true` may still include the notice.
 
 Safety constraints:
 - Read commands (`+list`, `+list-templates`, `+list-projects`, `+run-result`, `+run-artifacts`, `+ai-generate`) can execute directly once required IDs are known.

package/dist/chunk-NOO24N7W.js

@@ -1,11 +0,0 @@
-// src/core/errors.ts
-var PermissionError = class extends Error {
-  constructor(message) {
-    super(message);
-    this.name = "PermissionError";
-  }
-};
-
-export {
-  PermissionError
-};

package/dist/chunk-TNW2CI4W.js

@@ -1,129 +0,0 @@
-import {
-  logger
-} from "./chunk-YCLVYFK7.js";
-
-// src/framework/output.ts
-import Table from "cli-table3";
-import { JqError, json as jqJson } from "jq-wasm";
-var KNOWN_ARRAY_FIELDS = [
-  "items",
-  "events",
-  "reports",
-  "dashboards",
-  "tags",
-  "clusters",
-  "flows",
-  "tasks",
-  "channels",
-  "nodes",
-  "members",
-  "records",
-  "entities",
-  "metrics",
-  "tables",
-  "columns",
-  "properties"
-];
-var OUTPUT_METADATA = /* @__PURE__ */ Symbol("ae-cli-output-metadata");
-function withOutputMetadata(data, meta) {
-  if (!meta || Object.keys(meta).length === 0) return data;
-  return {
-    [OUTPUT_METADATA]: true,
-    data,
-    meta
-  };
-}
-function isOutputWithMetadata(value) {
-  return Boolean(value?.[OUTPUT_METADATA]);
-}
-function findArrayField(data) {
-  if (Array.isArray(data)) return data;
-  if (typeof data !== "object" || data === null) return null;
-  for (const key of KNOWN_ARRAY_FIELDS) {
-    if (Array.isArray(data[key])) return data[key];
-  }
-  for (const key of Object.keys(data)) {
-    if (Array.isArray(data[key])) return data[key];
-  }
-  return null;
-}
-function formatTable(data) {
-  const rows = findArrayField(data);
-  if (!rows || rows.length === 0) {
-    return JSON.stringify(data, null, 2);
-  }
-  const allKeys = /* @__PURE__ */ new Set();
-  for (const row of rows) {
-    if (typeof row === "object" && row !== null) {
-      Object.keys(row).forEach((k) => allKeys.add(k));
-    }
-  }
-  const keys = Array.from(allKeys);
-  if (keys.length === 0) return JSON.stringify(rows, null, 2);
-  const table = new Table({ head: keys, wordWrap: true });
-  for (const row of rows) {
-    table.push(keys.map((k) => {
-      const v = row?.[k];
-      if (v === void 0 || v === null) return "";
-      if (typeof v === "object") return JSON.stringify(v);
-      return String(v);
-    }));
-  }
-  return table.toString();
-}
-async function applyJq(data, expr) {
-  const trimmed = expr.trim();
-  if (!trimmed) return data;
-  let results;
-  try {
-    results = await jqJson(data, trimmed);
-  } catch (err) {
-    const message = err instanceof JqError ? err.message : err?.message || String(err);
-    const error = new Error(`Invalid --jq expression: ${message}`);
-    error.type = "validation";
-    error.hint = "Use standard jq syntax, e.g. .status or {status,pendingQuestion}";
-    throw error;
-  }
-  if (results.length === 0) return null;
-  if (results.length === 1) return results[0];
-  return results;
-}
-async function formatOutput(data, format, jqExpr) {
-  const outputData = isOutputWithMetadata(data) ? data.data : data;
-  const meta = isOutputWithMetadata(data) ? data.meta : void 0;
-  let processed = outputData;
-  if (jqExpr) {
-    processed = await applyJq(outputData, jqExpr);
-  }
-  if (format === "table") {
-    return formatTable(processed);
-  }
-  const envelope = {
-    ok: true,
-    data: processed,
-    ...meta ? { meta } : {}
-  };
-  return JSON.stringify(envelope, null, 2);
-}
-function formatError(type, message, hint, code, meta) {
-  const envelope = {
-    ok: false,
-    error: { type, message, hint, code },
-    ...meta && Object.keys(meta).length > 0 ? { meta } : {}
-  };
-  return JSON.stringify(envelope, null, 2);
-}
-function printError(type, message, hint, code, meta) {
-  const formatted = formatError(type, message, hint, code, meta);
-  process.stderr.write(formatted + "\n");
-  logger.error(`[${type}] ${message}${hint ? " | " + hint : ""}`);
-}
-async function printOutput(data, format, jqExpr) {
-  process.stdout.write(await formatOutput(data, format, jqExpr) + "\n");
-}
-
-export {
-  withOutputMetadata,
-  printError,
-  printOutput
-};