重新调整模板

2026-06-07 11:28:45 +08:00
parent ae5466854f
commit 1bbcc65cf3
31 changed files with 448 additions and 1525 deletions
--- a/README.md
+++ b/README.md
@@ -5,7 +5,7 @@
 ## 模板目标

 - 对齐当前规范 skill 的目录结构：`assets/`、`references/`、`scripts/`、`tests/`、`evals/`
- 对齐当前规范脚手架分层：`scripts/cli`、`scripts/db`、`scripts/service`、`scripts/util`、`scripts/jiangchang_skill_core`
+- 对齐当前规范脚手架分层：`scripts/cli`、`scripts/db`、`scripts/service`、`scripts/util`；公共能力从共享 runtime 的 `jiangchang-platform-kit` 引用
 - 提供最小可运行入口：`python scripts/main.py health` / `version`，以及通用任务命令骨架 `run` / `logs` / `log-get`
 - 内置 **隔离测试体系**：`IsolatedDataRoot`、双键环境、`OPENCLAW_TEST_TARGET` 档位与 adapter profile 策略（详见 [`references/TESTING.md`](references/TESTING.md)）
 - 让新技能从一开始就按规范落地，不再沿用旧模板的 `docs/`、`optional/`、`skill_main.py` 结构
@@ -56,9 +56,22 @@ python scripts/main.py version

 ## Python 依赖（requirements.txt）

- 在技能**根目录**维护 `requirements.txt`，声明本技能特有的 Python 三方包。
+- 模板默认声明 `jiangchang-platform-kit>=1.0.11` 作为公共 SDK 依赖；`jiangchang_skill_core` 来自共享 runtime，**不在技能仓库内复制**。
+- 新技能**不得 vendored** `scripts/jiangchang_skill_core/`；复制模板后若发现该目录，应删除并改为依赖共享 venv。
+- 在技能**根目录**维护 `requirements.txt`，声明本技能特有的 Python 三方包（在 platform-kit 之外按需追加）。
 - 匠厂宿主在**安装或更新**技能后，会将该文件中的依赖安装到共享 Python runtime：
  `{JIANGCHANG_DATA_ROOT}/python-runtime/.venv`（Windows 示例：`D:\jiangchang-data\python-runtime\.venv`）。
- 平台通用依赖由宿主 `resources/jiangchang-python-runtime/pyproject.toml` 维护；**不要**把业务依赖写进宿主 pyproject。
 - **Skill 业务代码不得自动 `pip install`**；缺依赖时应在 `health` / preflight 中给出清晰错误。
 - **系统级组件**（如 Microsoft Visual C++ Redistributable）**不要**写进 `requirements.txt`；仅在 `health` / preflight 中提示用户自行安装。
+
+## 公共能力边界
+
+以下能力均由 `jiangchang-platform-kit`（共享 runtime 的 `jiangchang_skill_core`）提供，技能只写业务逻辑与薄封装，**不要**在技能内复制实现：
+
+- `config` — `.env` 三级优先级读取与首次落盘
+- `runtime_env` — 数据根、用户 ID、兄弟技能根解析
+- `unified_logging` — 统一日志与 trace
+- `rpa` — 浏览器/桌面/手机 RPA 共享库
+- `media_assets` — 共享媒体资源探测与路径解析
+- `video_session` — RPA 录屏成片（ffmpeg、字幕、背景音乐）
+- `runtime_diagnostics` — `health` 统一 runtime 诊断
--- a/SKILL.md
+++ b/SKILL.md
@@ -6,6 +6,7 @@ author: 深圳匠厂科技有限公司
 metadata:
  openclaw:
    slug: your-skill-slug
+    platform_kit_min_version: "1.0.11"
    emoji: "📦"
    category: "通用"
    developer_ids:
@@ -29,7 +30,7 @@ allowed-tools:

 - 根目录结构参考现有规范技能：`assets/`、`references/`、`scripts/`、`tests/`、`evals/`。
 - CLI 入口固定为 `scripts/main.py`。
- 业务逻辑按 `cli / db / service / util / jiangchang_skill_core` 分层。
+- 业务逻辑按 `cli / db / service / util` 分层；公共能力从 `jiangchang-platform-kit` 提供的 `jiangchang_skill_core` 引用。

 ## 最小命令

@@ -40,9 +41,12 @@ python {baseDir}/scripts/main.py version

 ## 运行依赖

- Python 运行环境由匠厂宿主注入共享 runtime：`{JIANGCHANG_DATA_ROOT}/python-runtime/.venv`。
- 本技能**特有**的 Python 三方依赖请声明在根目录 `requirements.txt`；宿主安装/更新技能后会自动安装到共享 venv。
+- Python 运行环境由匠厂宿主注入**共享 runtime**：`{JIANGCHANG_DATA_ROOT}/python-runtime/.venv`。
+- 公共能力来自共享 runtime 安装的 `jiangchang-platform-kit>=1.0.11`（`jiangchang_skill_core` 包）；**新技能不得**在仓库内保留 `scripts/jiangchang_skill_core/` 副本。
+- config、logging、runtime_env、rpa、media-assets、video_session、runtime_diagnostics 等均从共享 venv 的 `jiangchang_skill_core` import，而非技能目录副本。
+- 本技能**特有**的 Python 三方依赖请声明在根目录 `requirements.txt`（默认已含 `jiangchang-platform-kit>=1.0.11`）；宿主安装/更新技能后会自动安装到共享 venv。
 - Skill 代码**不要**自行 `pip install`；系统级依赖（如 VC++ Runtime）仅在 `health` / preflight 中提示用户安装。
+- `health` 使用 `collect_runtime_diagnostics` 输出统一 runtime 诊断（只读，不下载/修复 media-assets）。

 ## 重要说明

--- a/references/CLI.md
+++ b/references/CLI.md
@@ -9,6 +9,20 @@ python {baseDir}/scripts/main.py health
 python {baseDir}/scripts/main.py version
 ```

+## health 标准输出（runtime diagnostics）
+
+`health` 委托 `jiangchang_skill_core.collect_runtime_diagnostics`，输出统一 runtime 诊断。典型字段：
+
+- `python_executable` — 当前 Python 解释器路径
+- `platform_kit_version` / `platform_kit_min_version` — 已安装与要求的 platform-kit 版本
+- `jiangchang_skill_core_file` — 公共库加载来源（若来自技能目录副本会报 warning）
+- `media_assets_root` — 共享媒体资源根目录
+- `ffmpeg_path` / `ffmpeg_available` — ffmpeg 探测结果
+- `background_music_mp3_count` — 可用背景音乐数量
+- `runtime_issue[warning|error]` — 非致命/致命问题列表
+
+`health` **只读诊断**，不下载、不修复 media-assets，不执行业务 DB / 邮箱 / 订单等检查。
+
 ## 通用业务命令骨架

 模板默认提供以下命令（复制后按需保留或扩展）：
--- a/references/CONFIG.md
+++ b/references/CONFIG.md
@@ -69,7 +69,7 @@ config.ensure_env_file()                   # 首次把 .env.example copy 到数

 ### 引用方式

-实现位于 `jiangchang-platform-kit` 的 `jiangchang_skill_core.config`；模板 vendor 拷贝在 `scripts/jiangchang_skill_core/config.py`：
+`jiangchang_skill_core.config` 来自共享 runtime 安装的 `jiangchang-platform-kit`；业务代码统一 `from jiangchang_skill_core import config`，**不要在技能内复制 config.py**：

 ```python
 from jiangchang_skill_core import config
--- a/references/DEVELOPMENT.md
+++ b/references/DEVELOPMENT.md
@@ -97,7 +97,6 @@ your-skill/
 ├─ scripts/
 │  ├─ cli/
 │  ├─ db/
-│  ├─ jiangchang_skill_core/
 │  ├─ service/
 │  └─ util/
 ├─ tests/
@@ -125,7 +124,6 @@ scripts/
 ├─ main.py
 ├─ cli/
 ├─ db/
-├─ jiangchang_skill_core/
 ├─ service/
 └─ util/
 ```
@@ -151,9 +149,7 @@ scripts/
 - `util/`
  作用：常量、日志、路径、时间工具、通用帮助函数

- `jiangchang_skill_core/`
-  作用：运行时环境、统一日志、配置读取、RPA 共享库（vendor 自 platform-kit）
-  一般按现有规范技能复制，不要自己乱改结构
+公共能力（config、logging、runtime_env、rpa、media_assets、video_session、runtime_diagnostics）从共享 runtime 的 `jiangchang-platform-kit>=1.0.11` import，**不得**在 `scripts/` 下保留 `jiangchang_skill_core/` 副本。

 ## 3.2 开发 RPA 类 skill

@@ -168,7 +164,7 @@ scripts/
   from jiangchang_skill_core import config
   from jiangchang_skill_core.rpa import launch_persistent_browser, anti_detect, wait_for_captcha_pass
   ```
-   vendor 源码在 `scripts/jiangchang_skill_core/rpa/`（与 `jiangchang-platform-kit` 保持同步拷贝）。
+   上述 import 来自宿主共享 runtime 安装的 `jiangchang-platform-kit`，不是技能目录副本。
 4. **mock 档必须离线可跑**（`OPENCLAW_TEST_TARGET=mock`）；sim_rpa / real_* 按需单独测。
 5. **桌面/手机**：本期标准见 RPA.md 第 2/3 节，复用 `jiangchang_desktop_sdk` / `screencast`，**不要在新 skill 里重复造包**（尚待实战验证）。

@@ -176,8 +172,9 @@ scripts/

 ### 3.1 `requirements.txt` 依赖规范

-技能根目录的 `requirements.txt` 是**标准文件**，用于声明本技能特有的 Python 三方依赖。
+技能根目录的 `requirements.txt` 是**标准文件**，用于声明本技能 Python 三方依赖。

+- 模板默认包含 `jiangchang-platform-kit>=1.0.11`（公共 SDK）；复制后保留该行，再按需追加技能特有依赖。
 - 匠厂宿主安装/更新技能后，会将其安装到共享 venv：`{JIANGCHANG_DATA_ROOT}/python-runtime/.venv`。
 - **不要**在业务代码中 `subprocess` / `pip install`；缺依赖由 `health` 报错，由宿主负责安装。
 - **版本约束尽量收窄**，降低多技能共享 venv 时的冲突风险。推荐范围写法：
@@ -186,7 +183,23 @@ scripts/
  - 不推荐：`chromadb>=0.5.0`
  - 推荐：`chromadb>=0.5.23,<0.6`
 - **不要**把系统组件（VC++ Runtime、浏览器安装包等）写进 `requirements.txt`；这类前置条件写在 `health` / preflight 文档与错误提示中。
- 若技能无额外 Python 依赖，可保留仅含注释的 `requirements.txt`（宿主会识别为 empty 并跳过安装）。
+- 若技能无额外 Python 依赖，可保留仅含 `jiangchang-platform-kit>=1.0.11` 的最小 `requirements.txt`。
+
+### 3.3 公共能力不要复制
+
+以下模块由 platform-kit 提供，技能内**不要**重复实现或 vendored 拷贝：
+
+| 能力 | 导入方式 |
+|------|----------|
+| config | `from jiangchang_skill_core import config` |
+| logging | `from jiangchang_skill_core.unified_logging import ...` 或 `util.logging_config` 薄封装 |
+| runtime_env | `from jiangchang_skill_core.runtime_env import ...` 或 `util.runtime_paths` 薄封装 |
+| rpa | `from jiangchang_skill_core.rpa import ...` |
+| media_assets | `from jiangchang_skill_core.media_assets import ...` |
+| video_session | `from jiangchang_skill_core.rpa.video_session import RpaVideoSession` |
+| runtime_diagnostics | `from jiangchang_skill_core import collect_runtime_diagnostics, format_runtime_health_lines` |
+
+`health` 应委托 `collect_runtime_diagnostics`，不要在 `scripts/util/` 自建 `runtime_diagnostics.py`。

 ## 4. 开发一个新 skill 的标准步骤

--- a/references/RPA.md
+++ b/references/RPA.md
@@ -62,10 +62,9 @@ pip install playwright   # 仅装包；用系统 Chrome，无需 playwright inst

 ### 引用方式

-共享实现位于 `jiangchang-platform-kit` 的 `jiangchang_skill_core.rpa`；模板通过 vendor 拷贝引用：
+共享实现位于宿主共享 runtime 安装的 `jiangchang-platform-kit`（`jiangchang_skill_core.rpa`）。复制后的业务技能直接 import，**技能仓库不得保留 rpa 公共代码副本**：

 ```python
-# scripts/jiangchang_skill_core/rpa/ — vendored from platform-kit
 from jiangchang_skill_core.rpa import (
    launch_persistent_browser,
    anti_detect,
@@ -76,6 +75,9 @@ from jiangchang_skill_core.rpa import (
 from jiangchang_skill_core.rpa.stealth import stealth_enabled, STEALTH_INIT_SCRIPT
 ```

+- `RpaVideoSession` 来自 platform-kit；ffmpeg、背景音乐、media-assets 由 platform-kit 统一解析。
+- `health` 对上述资源做只读诊断，不下载、不修复。
+
 完整示例见 `scripts/service/example_browser_rpa.py` 与 `scripts/service/example_adapter/sim_rpa.py`。

 ---
--- a/references/RUNTIME.md
+++ b/references/RUNTIME.md
@@ -1,5 +1,51 @@
 # 运行时约定

+## 共享 Python Runtime
+
+**skill-template** 及复制出的新技能，公共能力均来自宿主匠厂安装的共享 Python Runtime（`jiangchang-platform-kit>=1.0.11` 及其传递依赖）。`jiangchang_skill_core` **不得**在技能仓库内 vendored，应由共享 venv 的 site-packages 提供。
+
+| 场景 | 推荐做法 |
+|------|----------|
+| 日常运行 | 由宿主匠厂触发技能 |
+| 手工排查 / 测试机 | 使用共享 runtime 的 `python.exe` 执行 `scripts/main.py` |
+| **不推荐** | 在技能目录内 `uv run python …` — 可能创建临时 venv，加载不到宿主共享 runtime |
+
+占位命令（路径因环境而异，勿写死本机目录）：
+
+```text
+Windows:
+  {JIANGCHANG_DATA_ROOT}\python-runtime\.venv\Scripts\python.exe {baseDir}\scripts\main.py health
+
+通用:
+  <shared-python> {baseDir}/scripts/main.py health
+```
+
+`<shared-python>` 通常位于 `{JIANGCHANG_DATA_ROOT}/python-runtime/.venv`。数据根由宿主注入；开发模式下也可能通过 `CLAW_DATA_ROOT` 解析（见 `jiangchang_skill_core.runtime_env`）。
+
+## Runtime 诊断（platform-kit 1.0.11+）
+
+`health` 命令通过 **`jiangchang_skill_core.collect_runtime_diagnostics`** 输出共享 runtime 诊断，**不在技能内重复实现**。典型字段：
+
+- `skill_slug`、`python_executable`、`platform_kit_version`、`platform_kit_min_version`
+- `jiangchang_skill_core_file` — 若从技能目录加载会输出 `runtime_issue[warning]`
+- `CLAW_DATA_ROOT` / `JIANGCHANG_DATA_ROOT` / `resolved_data_root`
+- `media_assets_root`、`ffmpeg_path`、`background_music_*`
+- `record_video_enabled`、`runtime_issue[warning|error]`
+
+`health` 是**只读诊断**，**不会**触发 media-assets 下载或修复。
+
+## media-assets / ffmpeg / 背景音乐
+
+背景音乐、ffmpeg 等共享资源由 platform-kit 统一解析，默认路径：
+
+```text
+{JIANGCHANG_DATA_ROOT}/shared/media-assets
+```
+
+（与 `CLAW_DATA_ROOT` 解析规则一致，由宿主注入。）
+
+RPA 录屏成片（`RpaVideoSession`）、ffmpeg 路径、背景音乐探测均由 platform-kit 提供；技能只 import，不重复实现。
+
 ## 目录结构

 新技能建议采用以下根目录结构：
@@ -10,14 +56,13 @@
 - `tests/`
 - `evals/`

-## `scripts/` 分层
+**标准 `scripts/` 分层（不含 `jiangchang_skill_core/` 副本）：**

 - `scripts/main.py`：唯一 CLI 入口
 - `scripts/cli/`：参数解析与命令分发
 - `scripts/db/`：SQLite 或本地持久化层
 - `scripts/service/`：业务用例与外部交互
- `scripts/util/`：通用工具、常量、日志、路径
- `scripts/jiangchang_skill_core/`：运行时与统一日志副本
+- `scripts/util/`：通用工具、常量、日志、路径薄封装

 ## 数据路径

@@ -33,6 +78,12 @@
 {...}/{skill_slug}.db
 ```

+## 明确禁止
+
+- **不得** vendored `scripts/jiangchang_skill_core/`
+- **不得**在技能内本地重复实现 `RuntimeDiagnostics` / `collect_runtime_diagnostics`
+- **不得**写死开发机绝对路径作为运行时约定
+
 ## 测试时的运行时隔离

 本模板的 `tests/_support.IsolatedDataRoot` 会在测试期间同时设置：
--- a/references/TESTING.md
+++ b/references/TESTING.md
@@ -22,7 +22,8 @@

 必跑套件要像一个紧张的守门员：**快、确定、离线**。典型覆盖：

- CLI：导入 [`cli.app`](../scripts/cli/app.py) 走解析链路、`health` / `version` / `logs` / `log-get` 冒烟；
+- CLI：导入 [`cli.app`](../scripts/cli/app.py) 走解析链路、`health`（runtime diagnostics）/ `version` / `logs` / `log-get` 冒烟；
+- 架构守护：无 `scripts/jiangchang_skill_core/`、`platform-kit>=1.0.11` 导入来源、文档/runtime 标准（见 `test_platform_import.py` 等）；
 - **真实 subprocess**：[`tests/test_entrypoint_subprocess.py`](../tests/test_entrypoint_subprocess.py) 再调用一遍 `python scripts/main.py`，防路径漂移；
 - 运行时：`runtime_paths` 与 **`CLAW_*` / `JIANGCHANG_*` 并发兜底；
 - `SKILL.md` YAML slug vs [`constants.SKILL_SLUG`](../scripts/util/constants.py)；
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,7 +1,9 @@
 # Skill-specific Python dependencies.
 # Keep this file minimal.
-# Platform-provided shared dependencies are installed by Jiangchang runtime.
-# Add only dependencies required by this skill.
+# Platform shared APIs are provided by jiangchang-platform-kit from Jiangchang shared runtime.
 #
-# Browser RPA: uses system Chrome/Edge; no `playwright install chromium` needed.
+# Required platform SDK. Do not vendor jiangchang_skill_core inside a skill.
+jiangchang-platform-kit>=1.0.11
+
+# Browser RPA example: uses system Chrome/Edge; no `playwright install chromium` needed.
 playwright>=1.42.0,<2
--- a/scripts/jiangchang_skill_core/init.py
+++ b/scripts/jiangchang_skill_core/init.py
@@ -1,16 +0,0 @@
-# Vendored from jiangchang-platform-kit/sdk/jiangchang_skill_core/ — keep runtime_env + unified_logging + config + rpa in sync.
-from .config import ensure_env_file, get, get_bool, get_float, get_int
-
-try:
-    from . import rpa
-except ImportError:
-    rpa = None  # type: ignore[assignment,misc]
-
-__all__ = [
-    "ensure_env_file",
-    "get",
-    "get_bool",
-    "get_float",
-    "get_int",
-    "rpa",
-]
--- a/scripts/jiangchang_skill_core/config.py
+++ b/scripts/jiangchang_skill_core/config.py
@@ -1,126 +0,0 @@
-# vendored from jiangchang-platform-kit; do not edit here, edit the kit.
-"""三级优先级配置读取 + 首次 .env 落盘（进程 env > 数据目录 .env > .env.example）。"""
-
-from __future__ import annotations
-
-import os
-import shutil
-from typing import Any
-
-from .runtime_env import get_data_root, get_user_id
-
-_skill_slug: str | None = None
-_example_path: str | None = None
-_env_file_path: str | None = None
-_user_env_cache: dict[str, str] | None = None
-_example_defaults_cache: dict[str, str] | None = None
-
-
-def _parse_env_file(path: str) -> dict[str, str]:
-    """标准库手写 .env 解析（不引 python-dotenv）。"""
-    result: dict[str, str] = {}
-    if not path or not os.path.isfile(path):
-        return result
-    with open(path, encoding="utf-8") as f:
-        for raw_line in f:
-            line = raw_line.strip()
-            if not line or line.startswith("#"):
-                continue
-            if "=" not in line:
-                continue
-            key, _, value = line.partition("=")
-            key = key.strip()
-            value = value.strip()
-            if not key:
-                continue
-            if len(value) >= 2 and value[0] == value[-1] and value[0] in ('"', "'"):
-                value = value[1:-1]
-            elif " #" in value:
-                value = value.split(" #", 1)[0].strip()
-            result[key] = value
-    return result
-
-
-def _get_user_env() -> dict[str, str]:
-    global _user_env_cache
-    if _user_env_cache is not None:
-        return _user_env_cache
-    if _env_file_path and os.path.isfile(_env_file_path):
-        _user_env_cache = _parse_env_file(_env_file_path)
-    else:
-        _user_env_cache = {}
-    return _user_env_cache
-
-
-def _get_example_defaults() -> dict[str, str]:
-    global _example_defaults_cache
-    if _example_defaults_cache is not None:
-        return _example_defaults_cache
-    if _example_path and os.path.isfile(_example_path):
-        _example_defaults_cache = _parse_env_file(_example_path)
-    else:
-        _example_defaults_cache = {}
-    return _example_defaults_cache
-
-
-def reset_cache() -> None:
-    """测试用：清空解析缓存。"""
-    global _user_env_cache, _example_defaults_cache
-    _user_env_cache = None
-    _example_defaults_cache = None
-
-
-def ensure_env_file(skill_slug: str, example_path: str) -> str:
-    """首次把 .env.example copy 到 {data_root}/{user}/{slug}/.env（已存在不覆盖），返回路径。"""
-    global _skill_slug, _example_path, _env_file_path
-    _skill_slug = skill_slug
-    _example_path = os.path.abspath(example_path)
-    dest_dir = os.path.join(get_data_root(), get_user_id(), skill_slug)
-    os.makedirs(dest_dir, exist_ok=True)
-    dest = os.path.join(dest_dir, ".env")
-    _env_file_path = dest
-    if not os.path.isfile(dest) and os.path.isfile(_example_path):
-        shutil.copy2(_example_path, dest)
-    reset_cache()
-    return dest
-
-
-def get(key: str, default: Any = None) -> str | None:
-    """进程环境变量 > 数据目录 .env > .env.example 默认值。"""
-    env_val = os.environ.get(key)
-    if env_val is not None and env_val != "":
-        return env_val
-    user_val = _get_user_env().get(key)
-    if user_val is not None and user_val != "":
-        return user_val
-    example_val = _get_example_defaults().get(key)
-    if example_val is not None and example_val != "":
-        return example_val
-    return default
-
-
-def get_bool(key: str, default: bool = False) -> bool:
-    val = get(key)
-    if val is None:
-        return default
-    return str(val).strip().lower() in ("1", "true", "yes", "on")
-
-
-def get_float(key: str, default: float) -> float:
-    val = get(key)
-    if val is None:
-        return default
-    try:
-        return float(val)
-    except (TypeError, ValueError):
-        return default
-
-
-def get_int(key: str, default: int) -> int:
-    val = get(key)
-    if val is None:
-        return default
-    try:
-        return int(val)
-    except (TypeError, ValueError):
-        return default
--- a/scripts/jiangchang_skill_core/rpa/init.py
+++ b/scripts/jiangchang_skill_core/rpa/init.py
@@ -1,66 +0,0 @@
-# vendored from jiangchang-platform-kit; do not edit here, edit the kit.
-"""浏览器 RPA 共享库：stealth、拟人操作、启动封装、HITL 等待、失败存证。"""
-
-from __future__ import annotations
-
-from . import anti_detect, artifacts, errors, human_login, stealth
-
-try:
-    from .browser import launch_persistent_browser
-except ImportError:
-    launch_persistent_browser = None  # type: ignore[misc, assignment]
-
-try:
-    from .video_session import RpaVideoSession
-except ImportError:
-    RpaVideoSession = None  # type: ignore[misc, assignment]
-
-__all__ = [
-    "anti_detect",
-    "artifacts",
-    "errors",
-    "human_login",
-    "stealth",
-    "launch_persistent_browser",
-    "RpaVideoSession",
-    # re-export common anti_detect helpers
-    "random_delay",
-    "human_delay_short",
-    "human_delay_page",
-    "human_delay_batch",
-    "human_mouse_move",
-    "human_mouse_wiggle",
-    "human_click",
-    "human_type",
-    "human_scroll",
-    # human_login
-    "wait_for_captcha_pass",
-    "wait_for_login",
-    "DEFAULT_CAPTCHA_MARKERS",
-    # artifacts
-    "artifact_path",
-    "capture_failure",
-    # stealth
-    "STEALTH_INIT_SCRIPT",
-    "stealth_enabled",
-    "persistent_context_launch_parts",
-]
-
-from .anti_detect import (
-    human_click,
-    human_delay_batch,
-    human_delay_page,
-    human_delay_short,
-    human_mouse_move,
-    human_mouse_wiggle,
-    human_scroll,
-    human_type,
-    random_delay,
-)
-from .artifacts import artifact_path, capture_failure
-from .human_login import DEFAULT_CAPTCHA_MARKERS, wait_for_captcha_pass, wait_for_login
-from .stealth import (
-    STEALTH_INIT_SCRIPT,
-    persistent_context_launch_parts,
-    stealth_enabled,
-)
--- a/scripts/jiangchang_skill_core/rpa/anti_detect.py
+++ b/scripts/jiangchang_skill_core/rpa/anti_detect.py
@@ -1,216 +0,0 @@
-# vendored from jiangchang-platform-kit; do not edit here, edit the kit.
-"""防反爬：随机延迟、人工鼠标轨迹模拟、拟人滚动。
-
-所有延迟使用 random.uniform() + asyncio.sleep()。
-鼠标移动使用三次贝塞尔曲线 + 随机抖动，避免机械直线轨迹。
-"""
-
-from __future__ import annotations
-
-import asyncio
-import math
-import random
-from typing import Optional
-
-
-# ── 随机延迟 ────────────────────────────────────────────────
-
-
-async def random_delay(min_s: float, max_s: float) -> float:
-    """随机延迟 min_s ~ max_s 秒，返回实际延迟秒数。"""
-    delay = random.uniform(min_s, max_s)
-    await asyncio.sleep(delay)
-    return delay
-
-
-async def human_delay_short() -> float:
-    """页面内操作间短延迟 0.5~2 秒（点击/滚动）。"""
-    return await random_delay(0.5, 2.0)
-
-
-async def human_delay_page(min_s: float = 2, max_s: float = 8) -> float:
-    """页面间/店铺间切换延迟（可配置范围）。"""
-    return await random_delay(min_s, max_s)
-
-
-async def human_delay_batch(min_s: float = 5, max_s: float = 15) -> float:
-    """批次间/翻页间长延迟。"""
-    return await random_delay(min_s, max_s)
-
-
-# ── 鼠标轨迹 ────────────────────────────────────────────────
-
-
-async def human_mouse_move(
-    page,
-    target_x: float,
-    target_y: float,
-    steps: Optional[int] = None,
-) -> None:
-    """模拟人工鼠标移动到目标坐标。
-
-    使用三次贝塞尔曲线生成 S/C 形路径，中间控制点随机偏移，
-    每步添加微小随机抖动，避免完美直线移动。
-
-    Args:
-        page: Playwright Page 对象。
-        target_x: 目标 X 坐标。
-        target_y: 目标 Y 坐标。
-        steps: 移动步数（None 时按距离自动计算）。
-    """
-    if steps is None:
-        dist = math.hypot(target_x, target_y)
-        steps = max(8, int(dist / 15))
-
-    # 随机起始点（模拟鼠标从页面其他位置移动过来）
-    start_x = target_x + random.uniform(-300, 300)
-    start_y = target_y + random.uniform(-200, 200)
-
-    # 两个贝塞尔控制点（制造弯曲路径）
-    dx = target_x - start_x
-    dy = target_y - start_y
-
-    cp1_x = start_x + dx * random.uniform(0.2, 0.5) + random.uniform(-120, 120)
-    cp1_y = start_y + dy * random.uniform(0.1, 0.4) + random.uniform(-100, 100)
-    cp2_x = start_x + dx * random.uniform(0.5, 0.8) + random.uniform(-100, 100)
-    cp2_y = start_y + dy * random.uniform(0.4, 0.7) + random.uniform(-80, 80)
-
-    for i in range(steps + 1):
-        t = i / steps
-        # 三次贝塞尔: B(t) = (1-t)³·P0 + 3(1-t)²·t·P1 + 3(1-t)·t²·P2 + t³·P3
-        u = 1 - t
-        x = (
-            (u ** 3) * start_x
-            + 3 * (u ** 2) * t * cp1_x
-            + 3 * u * (t ** 2) * cp2_x
-            + (t ** 3) * target_x
-        )
-        y = (
-            (u ** 3) * start_y
-            + 3 * (u ** 2) * t * cp1_y
-            + 3 * u * (t ** 2) * cp2_y
-            + (t ** 3) * target_y
-        )
-
-        # 微小随机抖动
-        x += random.uniform(-1.5, 1.5)
-        y += random.uniform(-1.5, 1.5)
-
-        await page.mouse.move(x, y)
-        await asyncio.sleep(random.uniform(0.003, 0.015))
-
-    # 最终精确到位
-    await page.mouse.move(target_x, target_y)
-
-
-async def human_click(
-    page,
-    selector: Optional[str] = None,
-    *,
-    x: Optional[float] = None,
-    y: Optional[float] = None,
-) -> None:
-    """拟人点击：贝塞尔轨迹移动 → 微延迟 → 点击。
-
-    支持两种定位方式：
-    - selector: CSS 选择器，自动取元素中心附近随机偏移
-    - x, y: 直接指定坐标（自动加微小随机偏移）
-
-    Args:
-        page: Playwright Page 对象。
-        selector: CSS 选择器（与 x/y 二选一）。
-        x: 目标 X 坐标。
-        y: 目标 Y 坐标。
-    """
-    if selector:
-        locator = page.locator(selector).first
-        box = await locator.bounding_box()
-        if box is None:
-            raise ValueError(f"无法获取元素边界: {selector}")
-        target_x = box["x"] + box["width"] * random.uniform(0.3, 0.7)
-        target_y = box["y"] + box["height"] * random.uniform(0.3, 0.7)
-    elif x is not None and y is not None:
-        target_x = x + random.uniform(-3, 3)
-        target_y = y + random.uniform(-3, 3)
-    else:
-        raise ValueError("必须提供 selector 或 (x, y) 坐标")
-
-    await human_mouse_move(page, target_x, target_y)
-    await human_delay_short()
-    await page.mouse.click(target_x, target_y)
-
-
-# ── 滚动模拟 ────────────────────────────────────────────────
-
-
-async def human_scroll(
-    page, direction: str = "down", amount: Optional[int] = None
-) -> None:
-    """模拟人工滚动（分段 + 变速 + 微延迟）。
-
-    Args:
-        page: Playwright Page 对象。
-        direction: "up" 或 "down"。
-        amount: 滚动像素总量，默认随机 300~800。
-    """
-    if amount is None:
-        amount = random.randint(300, 800)
-
-    sign = -1 if direction == "up" else 1
-    remaining = amount
-    step_count = random.randint(3, 7)
-
-    for i in range(step_count):
-        step = remaining // (step_count - i) + random.randint(-30, 30)
-        step = max(10, min(step, remaining))
-        remaining -= step
-
-        await page.mouse.wheel(0, sign * step)
-        await asyncio.sleep(random.uniform(0.05, 0.2))
-
-    if remaining > 0:
-        await page.mouse.wheel(0, sign * remaining)
-
-    await human_delay_short()
-
-
-# ── 进场鼠标随机晃动 ────────────────────────────────────────
-
-
-async def human_mouse_wiggle(page) -> None:
-    """页面进入后随机移动鼠标 2~4 次（贝塞尔轨迹），模拟真人到场环顾。"""
-    try:
-        vp = page.viewport_size or {"width": 1280, "height": 800}
-    except Exception:
-        vp = {"width": 1280, "height": 800}
-    w, h = vp.get("width", 1280), vp.get("height", 800)
-    for _ in range(random.randint(2, 4)):
-        tx = random.uniform(w * 0.2, w * 0.8)
-        ty = random.uniform(h * 0.2, h * 0.7)
-        await human_mouse_move(page, tx, ty)
-        await asyncio.sleep(random.uniform(0.2, 0.8))
-
-
-# ── 拟人逐字输入 ────────────────────────────────────────────
-
-
-async def human_type(page, locator, text: str) -> None:
-    """真人式输入：贝塞尔移动到输入框 → 真实点击聚焦 → 逐字符 keyboard.type。
-
-    全程使用 isTrusted=true 的可信事件，绝不用 JS 设置 value。
-    """
-    box = await locator.bounding_box()
-    if box is None:
-        raise ValueError("human_type: 无法获取输入框边界")
-    tx = box["x"] + box["width"] * random.uniform(0.3, 0.7)
-    ty = box["y"] + box["height"] * random.uniform(0.3, 0.7)
-    await human_mouse_move(page, tx, ty)
-    await asyncio.sleep(random.uniform(0.15, 0.5))
-    await page.mouse.click(tx, ty)
-    await asyncio.sleep(random.uniform(0.2, 0.6))
-    # 清空已有内容（用键盘，不用 JS）
-    await page.keyboard.press("Control+A")
-    await page.keyboard.press("Delete")
-    await asyncio.sleep(random.uniform(0.2, 0.5))
-    for ch in text:
-        await page.keyboard.type(ch, delay=random.uniform(90, 240))
--- a/scripts/jiangchang_skill_core/rpa/artifacts.py
+++ b/scripts/jiangchang_skill_core/rpa/artifacts.py
@@ -1,29 +0,0 @@
-# vendored from jiangchang-platform-kit; do not edit here, edit the kit.
-"""RPA 失败存证路径与截图。"""
-
-from __future__ import annotations
-
-import os
-from datetime import datetime
-
-
-def _artifacts_enabled() -> bool:
-    v = (os.environ.get("OPENCLAW_ARTIFACTS_ON_FAILURE") or "1").strip().lower()
-    return v not in ("0", "false", "no", "off")
-
-
-def artifact_path(data_dir: str, batch_id: str, tag: str, ext: str = "png") -> str:
-    """返回 {data_dir}/rpa-artifacts/{batch_id}/{tag}_{timestamp}.{ext}"""
-    ts = datetime.now().strftime("%Y%m%d_%H%M%S")
-    directory = os.path.join(data_dir, "rpa-artifacts", batch_id)
-    os.makedirs(directory, exist_ok=True)
-    return os.path.join(directory, f"{tag}_{ts}.{ext}")
-
-
-async def capture_failure(page, data_dir: str, batch_id: str, tag: str) -> str:
-    """受 OPENCLAW_ARTIFACTS_ON_FAILURE 控制，截图并返回路径；禁用时返回空字符串。"""
-    if not _artifacts_enabled():
-        return ""
-    path = artifact_path(data_dir, batch_id, tag, ext="png")
-    await page.screenshot(path=path, full_page=True)
-    return path
--- a/scripts/jiangchang_skill_core/rpa/browser.py
+++ b/scripts/jiangchang_skill_core/rpa/browser.py
@@ -1,58 +0,0 @@
-"""统一 persistent context 启动封装（仅浏览器自动化，不负责录屏）。"""
-
-from __future__ import annotations
-
-import os
-from typing import TYPE_CHECKING
-
-from ..runtime_env import find_chrome_executable
-from .stealth import (
-    STEALTH_INIT_SCRIPT,
-    persistent_context_launch_parts,
-    stealth_enabled,
-)
-
-if TYPE_CHECKING:
-    from playwright.async_api import BrowserContext
-
-
-async def launch_persistent_browser(
-    playwright,
-    *,
-    profile_dir: str,
-    channel: str = "chrome",
-    executable_path: str | None = None,
-    headless: bool | None = None,
-    extra_args: list[str] | None = None,
-) -> "BrowserContext":
-    """用 stealth 参数启动 persistent context + 注入 STEALTH_INIT_SCRIPT。
-
-    headless=None 时读 OPENCLAW_BROWSER_HEADLESS。
-    录屏由 RpaVideoSession（ffmpeg）负责，本函数不向 Playwright 传递任何录屏参数。
-    """
-    if headless is None:
-        v = (os.environ.get("OPENCLAW_BROWSER_HEADLESS") or "0").strip().lower()
-        headless = v in ("1", "true", "yes", "on")
-
-    chrome = executable_path or find_chrome_executable()
-    if not chrome:
-        raise RuntimeError(
-            "ERROR:MISSING_BROWSER 未检测到 Chrome 或 Edge 浏览器，请安装后重试。"
-        )
-
-    args, ignore = persistent_context_launch_parts(extra_args=extra_args)
-    launch_kwargs: dict = dict(
-        user_data_dir=profile_dir,
-        headless=headless,
-        executable_path=chrome,
-        locale="zh-CN",
-        no_viewport=True,
-        args=args,
-    )
-    if ignore is not None:
-        launch_kwargs["ignore_default_args"] = ignore
-
-    context = await playwright.chromium.launch_persistent_context(**launch_kwargs)
-    if stealth_enabled():
-        await context.add_init_script(STEALTH_INIT_SCRIPT)
-    return context
--- a/scripts/jiangchang_skill_core/rpa/errors.py
+++ b/scripts/jiangchang_skill_core/rpa/errors.py
@@ -1,20 +0,0 @@
-# vendored from jiangchang-platform-kit; do not edit here, edit the kit.
-"""RPA 场景统一错误码（stdout / 异常消息前缀）。"""
-
-ERR_REQUIRE_LOGIN = "ERROR:REQUIRE_LOGIN"
-ERR_LOGIN_TIMEOUT = "ERROR:LOGIN_TIMEOUT"
-ERR_CAPTCHA_NEED_HUMAN = "ERROR:CAPTCHA_NEED_HUMAN"
-ERR_RATE_LIMITED = "ERROR:RATE_LIMITED"
-ERR_MISSING_BROWSER = "ERROR:MISSING_BROWSER"
-ERR_DEVICE_NOT_READY = "ERROR:DEVICE_NOT_READY"
-ERR_WINDOW_NOT_FOUND = "ERROR:WINDOW_NOT_FOUND"
-
-__all__ = [
-    "ERR_REQUIRE_LOGIN",
-    "ERR_LOGIN_TIMEOUT",
-    "ERR_CAPTCHA_NEED_HUMAN",
-    "ERR_RATE_LIMITED",
-    "ERR_MISSING_BROWSER",
-    "ERR_DEVICE_NOT_READY",
-    "ERR_WINDOW_NOT_FOUND",
-]
--- a/scripts/jiangchang_skill_core/rpa/human_login.py
+++ b/scripts/jiangchang_skill_core/rpa/human_login.py
@@ -1,97 +0,0 @@
-# vendored from jiangchang-platform-kit; do not edit here, edit the kit.
-"""验证码/登录 HITL 等待（站点无关通用部分）。"""
-
-from __future__ import annotations
-
-import asyncio
-
-DEFAULT_CAPTCHA_MARKERS = (
-    "punish",
-    "baxia",
-    "nc_login",
-    "tmd",
-    "x5sec",
-    "安全验证",
-    "请按住滑块",
-    "拖动到最右边",
-)
-
-
-async def wait_for_captcha_pass(
-    page,
-    captcha_markers: tuple[str, ...] = DEFAULT_CAPTCHA_MARKERS,
-    timeout_sec: int = 120,
-) -> bool:
-    """
-    检测到验证码/拦截页时，暂停等待用户手工完成验证。
-    每 3 秒轮询一次页面状态，直到页面不再是拦截状态或超时。
-
-    Returns:
-        True  — 验证码已通过，可以继续
-        False — 超时，用户未在规定时间内完成验证
-    """
-    print(
-        f"[验证码] 检测到安全拦截，请在浏览器中手工完成验证。"
-        f"等待最多 {timeout_sec} 秒..."
-    )
-
-    elapsed = 0
-    while elapsed < timeout_sec:
-        await asyncio.sleep(3)
-        elapsed += 3
-        try:
-            url = page.url or ""
-            text = ""
-            try:
-                text = await page.locator("body").inner_text(timeout=2_000)
-            except Exception:
-                pass
-            haystack = (url + " " + text[:1000]).lower()
-            still_blocked = any(m.lower() in haystack for m in captcha_markers)
-            if not still_blocked:
-                print(f"[验证码] 已通过！({elapsed}s 后检测到正常页面)")
-                return True
-        except Exception:
-            pass
-
-    print(f"[验证码] 超时 {timeout_sec}s，用户未完成验证")
-    return False
-
-
-async def wait_for_login(
-    page,
-    success_selectors: list[str],
-    timeout_sec: int = 180,
-) -> bool:
-    """
-    轮询等待登录成功标志出现（站点专属选择器由调用方传入）。
-
-    Args:
-        page: Playwright Page 对象。
-        success_selectors: 登录成功后应出现的 CSS 选择器列表。
-        timeout_sec: 最长等待秒数。
-
-    Returns:
-        True  — 检测到登录成功标志
-        False — 超时
-    """
-    print(
-        f"[登录] 请在浏览器中完成登录。等待最多 {timeout_sec} 秒，"
-        "期间程序不会操作页面..."
-    )
-
-    elapsed = 0
-    while elapsed < timeout_sec:
-        await asyncio.sleep(2)
-        elapsed += 2
-        for selector in success_selectors:
-            try:
-                el = await page.query_selector(selector)
-                if el is not None:
-                    print("[登录] 检测到登录成功！")
-                    return True
-            except Exception:
-                pass
-
-    print(f"[登录] 超时 {timeout_sec}s，未完成登录")
-    return False
--- a/scripts/jiangchang_skill_core/rpa/stealth.py
+++ b/scripts/jiangchang_skill_core/rpa/stealth.py
@@ -1,67 +0,0 @@
-# vendored from jiangchang-platform-kit; do not edit here, edit the kit.
-"""淡化 Playwright 自动化指纹，降低 baxia/x5sec 风控命中率。
-
-关闭：环境变量 OPENCLAW_PLAYWRIGHT_STEALTH=0（或 false/off/no）。
-"""
-
-from __future__ import annotations
-
-import os
-
-STEALTH_INIT_SCRIPT = """
-(() => {
-  try { Object.defineProperty(navigator, 'webdriver', { get: () => undefined }); } catch (e) {}
-  try {
-    window.chrome = window.chrome || {};
-    window.chrome.runtime = window.chrome.runtime || {};
-  } catch (e) {}
-  try {
-    const orig = navigator.permissions && navigator.permissions.query;
-    if (orig) {
-      navigator.permissions.query = (p) =>
-        p && p.name === 'notifications'
-          ? Promise.resolve({ state: Notification.permission })
-          : orig(p);
-    }
-  } catch (e) {}
-  try {
-    Object.defineProperty(navigator, 'plugins', { get: () => [1, 2, 3, 4, 5] });
-  } catch (e) {}
-  try {
-    Object.defineProperty(navigator, 'languages', { get: () => ['zh-CN', 'zh'] });
-  } catch (e) {}
-  try {
-    Object.defineProperty(navigator, 'hardwareConcurrency', { get: () => 8 });
-  } catch (e) {}
-  try {
-    Object.defineProperty(navigator, 'deviceMemory', { get: () => 8 });
-  } catch (e) {}
-  try {
-    const getParameter = WebGLRenderingContext.prototype.getParameter;
-    WebGLRenderingContext.prototype.getParameter = function (p) {
-      if (p === 37445) return 'Intel Inc.';
-      if (p === 37446) return 'Intel Iris OpenGL Engine';
-      return getParameter.call(this, p);
-    };
-  } catch (e) {}
-})();
-"""
-
-
-def stealth_enabled() -> bool:
-    v = (os.environ.get("OPENCLAW_PLAYWRIGHT_STEALTH") or "1").strip().lower()
-    return v not in ("0", "false", "no", "off")
-
-
-def persistent_context_launch_parts(
-    *, extra_args: list[str] | None = None
-) -> tuple[list[str], list[str] | None]:
-    """返回 (args, ignore_default_args)。ignore_default_args 为 None 时不要传给 launch。"""
-    args = ["--start-maximized"]
-    if extra_args:
-        args = args + list(extra_args)
-    if not stealth_enabled():
-        return args, None
-    if "--disable-blink-features=AutomationControlled" not in args:
-        args.append("--disable-blink-features=AutomationControlled")
-    return args, ["--enable-automation"]
--- a/scripts/jiangchang_skill_core/rpa/video_session.py
+++ b/scripts/jiangchang_skill_core/rpa/video_session.py
@@ -1,461 +0,0 @@
-"""RPA 运行录屏会话：ffmpeg 桌面录制 → 字幕 + 背景音乐 → 最终 MP4。"""
-
-from __future__ import annotations
-
-import asyncio
-import os
-import random
-import shutil
-import subprocess
-import sys
-import time
-from dataclasses import dataclass
-from datetime import datetime
-from pathlib import Path
-from typing import Any, Dict, IO, List, Optional
-
-from .. import config
-
-_JIANGCHANG_SUBTITLE_STYLE = (
-    "FontName=Arial,FontSize=14,"
-    "PrimaryColour=&H00FFFFFF,OutlineColour=&H00000000,"
-    "Outline=2,Shadow=1,Alignment=2"
-)
-
-_DEFAULT_MUSIC_ROOT = os.environ.get(
-    "MEDIA_ASSETS_ROOT",
-    r"D:\OpenClaw\client-commons\media-assets",
-)
-
-_CAPTURE_FRAMERATE = 15
-
-
-def _record_video_enabled() -> bool:
-    return config.get_bool("OPENCLAW_RECORD_VIDEO", default=False)
-
-
-def _resolve_music_file() -> Optional[Path]:
-    music_dir = Path(_DEFAULT_MUSIC_ROOT) / "music"
-    if not music_dir.is_dir():
-        return None
-    files = list(music_dir.rglob("*.mp3"))
-    if not files:
-        return None
-    return random.choice(files)
-
-
-@dataclass
-class _StepEntry:
-    start: float
-    text: str
-    duration: float = 4.0
-
-
-def _generate_srt(entries: List[_StepEntry], output_path: str) -> None:
-    MIN_DURATION = 1.0
-    GAP = 0.1
-    steps = sorted(entries, key=lambda e: e.start)
-    if not steps:
-        steps = [_StepEntry(0.0, "任务执行中", 4.0)]
-
-    for i in range(len(steps) - 1):
-        cur, nxt = steps[i], steps[i + 1]
-        max_end = nxt.start - GAP
-        new_dur = max_end - cur.start
-        if new_dur < MIN_DURATION:
-            cur.duration = MIN_DURATION
-            nxt.start = cur.start + MIN_DURATION + GAP
-        else:
-            cur.duration = min(cur.duration, new_dur)
-
-    def _fmt(s: float) -> str:
-        h = int(s // 3600)
-        m = int((s % 3600) // 60)
-        sec = int(s % 60)
-        ms = int((s % 1) * 1000)
-        return f"{h:02d}:{m:02d}:{sec:02d},{ms:03d}"
-
-    Path(output_path).parent.mkdir(parents=True, exist_ok=True)
-    with open(output_path, "w", encoding="utf-8") as f:
-        for i, e in enumerate(steps, 1):
-            f.write(f"{i}\n")
-            f.write(f"{_fmt(e.start)} --> {_fmt(e.start + e.duration)}\n")
-            f.write(f"{e.text}\n\n")
-
-
-def _escape_srt_path(path: str) -> str:
-    return path.replace("\\", "/").replace(":", "\\:")
-
-
-def _run_ffmpeg(cmd: List[str]) -> tuple[bool, str]:
-    try:
-        result = subprocess.run(
-            cmd,
-            capture_output=True,
-            text=True,
-            encoding="utf-8",
-            errors="replace",
-        )
-    except FileNotFoundError:
-        return False, "ffmpeg not found"
-    if result.returncode != 0:
-        err = (result.stderr or result.stdout or "").strip()
-        return False, err[:500] if err else f"exit {result.returncode}"
-    return True, ""
-
-
-def _build_desktop_record_cmd(capture_path: str) -> Optional[List[str]]:
-    """Windows gdigrab 全桌面录制；非 Windows 返回 None。"""
-    if sys.platform != "win32":
-        return None
-    return [
-        "ffmpeg",
-        "-y",
-        "-f",
-        "gdigrab",
-        "-framerate",
-        str(_CAPTURE_FRAMERATE),
-        "-i",
-        "desktop",
-        "-c:v",
-        "libx264",
-        "-preset",
-        "ultrafast",
-        "-pix_fmt",
-        "yuv420p",
-        capture_path,
-    ]
-
-
-def _compose_capture_mp4(
-    capture_path: Path,
-    srt_path: Path,
-    output_path: Path,
-    *,
-    music_file: Optional[Path] = None,
-    music_volume: float = 0.15,
-) -> tuple[bool, str]:
-    output_path.parent.mkdir(parents=True, exist_ok=True)
-    srt_esc = _escape_srt_path(str(srt_path.resolve()))
-    subtitle_filter = (
-        f"subtitles='{srt_esc}'"
-        f":force_style='{_JIANGCHANG_SUBTITLE_STYLE}'"
-    )
-
-    if music_file and music_file.is_file():
-        filter_complex = (
-            f"[0:v]{subtitle_filter}[vout];"
-            f"[1:a]volume={music_volume},apad[aout]"
-        )
-        cmd = [
-            "ffmpeg",
-            "-y",
-            "-i",
-            str(capture_path),
-            "-i",
-            str(music_file),
-            "-filter_complex",
-            filter_complex,
-            "-map",
-            "[vout]",
-            "-map",
-            "[aout]",
-            "-c:v",
-            "libx264",
-            "-preset",
-            "fast",
-            "-crf",
-            "23",
-            "-c:a",
-            "aac",
-            "-b:a",
-            "128k",
-            "-shortest",
-            "-pix_fmt",
-            "yuv420p",
-            str(output_path),
-        ]
-    else:
-        cmd = [
-            "ffmpeg",
-            "-y",
-            "-i",
-            str(capture_path),
-            "-vf",
-            subtitle_filter,
-            "-c:v",
-            "libx264",
-            "-preset",
-            "fast",
-            "-crf",
-            "23",
-            "-c:a",
-            "aac",
-            "-b:a",
-            "128k",
-            "-pix_fmt",
-            "yuv420p",
-            str(output_path),
-        ]
-    return _run_ffmpeg(cmd)
-
-
-class RpaVideoSession:
-    """Service/RPA 层统一 ffmpeg 桌面录屏；OPENCLAW_RECORD_VIDEO=1 时启用成片流程。"""
-
-    def __init__(
-        self,
-        *,
-        skill_slug: str,
-        skill_data_dir: str,
-        batch_id: str,
-        title: str = "",
-    ) -> None:
-        self.skill_slug = skill_slug
-        self.skill_data_dir = os.path.abspath(skill_data_dir)
-        self.batch_id = batch_id
-        self.title = title
-        self.enabled = _record_video_enabled()
-        self.warnings: List[str] = []
-        self.output_video_path: Optional[str] = None
-        self.capture_path: Optional[str] = None
-        self.artifacts: Dict[str, Any] = {}
-
-        ts = datetime.now().strftime("%Y%m%d_%H%M%S")
-        safe_batch = "".join(c if c.isalnum() or c in "-_" else "_" for c in batch_id)
-        self._video_stem = f"{skill_slug}_{ts}_{safe_batch}"
-
-        self._videos_dir = os.path.join(self.skill_data_dir, "videos")
-        self._artifact_root = os.path.join(
-            self.skill_data_dir, "rpa-artifacts", batch_id
-        )
-        self._subtitles_dir = os.path.join(self._artifact_root, "subtitles")
-        self._logs_dir = os.path.join(self._artifact_root, "logs")
-        self._ffmpeg_record_log_path = os.path.join(self._logs_dir, "ffmpeg-record.log")
-        self._capture_path = os.path.join(self._artifact_root, "capture.mp4")
-        self._srt_path = os.path.join(self._subtitles_dir, f"{self._video_stem}.srt")
-        self._planned_output = os.path.join(self._videos_dir, f"{self._video_stem}.mp4")
-
-        self._steps: List[_StepEntry] = []
-        self._t0: Optional[float] = None
-        self._ffmpeg_proc: Optional[subprocess.Popen] = None
-        self._ffmpeg_record_log_file: Optional[IO[str]] = None
-
-        if self.enabled:
-            os.makedirs(self._videos_dir, exist_ok=True)
-            os.makedirs(self._subtitles_dir, exist_ok=True)
-            os.makedirs(self._logs_dir, exist_ok=True)
-            os.makedirs(self._artifact_root, exist_ok=True)
-
-    def _record_log_hint(self) -> str:
-        if self.enabled and self._ffmpeg_record_log_path:
-            return f"; record_log={self._ffmpeg_record_log_path}"
-        return ""
-
-    def _append_warning(self, code: str, detail: str = "") -> None:
-        msg = code if not detail else f"{code}: {detail}"
-        if code in (
-            "ffmpeg_record_start_failed",
-            "ffmpeg_capture_missing",
-            "ffmpeg_compose_failed",
-        ):
-            msg += self._record_log_hint()
-        self.warnings.append(msg)
-
-    def step(self, text: str, *, duration: float = 4.0) -> None:
-        self.add_step(text, duration=duration)
-
-    def add_step(self, text: str, *, duration: float = 4.0) -> None:
-        """记录一步骤字幕（相对录屏开始时间）。"""
-        if not self.enabled:
-            return
-        if self._t0 is None:
-            self._t0 = time.monotonic()
-        elapsed = time.monotonic() - self._t0
-        self._steps.append(_StepEntry(start=elapsed, text=text.strip(), duration=duration))
-
-    def _close_ffmpeg_record_log(self) -> None:
-        fh = self._ffmpeg_record_log_file
-        self._ffmpeg_record_log_file = None
-        if fh is None:
-            return
-        try:
-            fh.close()
-        except Exception:
-            pass
-
-    def _start_ffmpeg_capture(self) -> None:
-        if not self.enabled:
-            return
-        if not shutil.which("ffmpeg"):
-            self.warnings.append("ffmpeg_not_found")
-            return
-
-        cmd = _build_desktop_record_cmd(self._capture_path)
-        if cmd is None:
-            self._append_warning(
-                "ffmpeg_record_start_failed",
-                "desktop capture only supported on Windows",
-            )
-            return
-
-        stderr_target: Any = subprocess.DEVNULL
-        try:
-            os.makedirs(self._logs_dir, exist_ok=True)
-            self._ffmpeg_record_log_file = open(
-                self._ffmpeg_record_log_path, "a", encoding="utf-8"
-            )
-            stderr_target = self._ffmpeg_record_log_file
-        except Exception as exc:
-            self.warnings.append(f"ffmpeg_record_log_open_failed: {exc}")
-
-        try:
-            self._ffmpeg_proc = subprocess.Popen(
-                cmd,
-                stdin=subprocess.PIPE,
-                stdout=subprocess.DEVNULL,
-                stderr=stderr_target,
-            )
-            self.capture_path = self._capture_path
-        except Exception as exc:
-            self._append_warning("ffmpeg_record_start_failed", str(exc))
-            self._ffmpeg_proc = None
-            self._close_ffmpeg_record_log()
-
-    def _stop_ffmpeg_capture(self) -> None:
-        proc = self._ffmpeg_proc
-        if proc is None:
-            self._close_ffmpeg_record_log()
-            return
-        if proc.poll() is None:
-            try:
-                if proc.stdin:
-                    proc.stdin.write(b"q")
-                    proc.stdin.flush()
-            except Exception:
-                try:
-                    proc.terminate()
-                except Exception:
-                    pass
-            try:
-                proc.wait(timeout=20)
-            except subprocess.TimeoutExpired:
-                try:
-                    proc.kill()
-                except Exception:
-                    pass
-                try:
-                    proc.wait(timeout=5)
-                except Exception:
-                    pass
-        self._ffmpeg_proc = None
-        self._close_ffmpeg_record_log()
-        time.sleep(0.3)
-
-    async def __aenter__(self) -> "RpaVideoSession":
-        if self.enabled:
-            self._t0 = time.monotonic()
-            if self.title:
-                self.add_step(self.title, duration=3.0)
-            self._start_ffmpeg_capture()
-        return self
-
-    async def __aexit__(self, exc_type, exc, tb) -> None:
-        if self.enabled:
-            self._stop_ffmpeg_capture()
-            await self.finalize()
-
-    async def finalize(self) -> None:
-        """停止录制后合成最终 MP4；失败只记 warning，不抛异常。"""
-        if not self.enabled:
-            self.artifacts = self.summary()
-            return
-
-        if not self._steps and self.title:
-            self.add_step(self.title)
-
-        try:
-            capture = Path(self._capture_path)
-            if not capture.is_file() or capture.stat().st_size <= 0:
-                self._append_warning("ffmpeg_capture_missing")
-                self.artifacts = self.summary()
-                return
-
-            self.capture_path = str(capture.resolve())
-
-            entries = list(self._steps)
-            if entries:
-                entries[-1].duration = max(entries[-1].duration, 5.0)
-            try:
-                _generate_srt(entries, self._srt_path)
-            except Exception as exc:
-                self.warnings.append(f"subtitle_write_failed: {exc}")
-
-            music = _resolve_music_file()
-            if music is None:
-                self.warnings.append("background_music_missing")
-
-            srt_file = Path(self._srt_path)
-            use_srt = srt_file.is_file() and srt_file.stat().st_size > 0
-
-            ok, err = _compose_capture_mp4(
-                capture,
-                srt_file if use_srt else Path(self._srt_path),
-                Path(self._planned_output),
-                music_file=music,
-            )
-            if not ok and music is not None:
-                self.warnings.append(f"ffmpeg_with_music_failed: {err}")
-                ok, err = _compose_capture_mp4(
-                    capture,
-                    srt_file if use_srt else Path(self._srt_path),
-                    Path(self._planned_output),
-                    music_file=None,
-                )
-            if not ok and not use_srt:
-                ok, err = _run_ffmpeg(
-                    [
-                        "ffmpeg",
-                        "-y",
-                        "-i",
-                        str(capture),
-                        "-c:v",
-                        "libx264",
-                        "-preset",
-                        "fast",
-                        "-crf",
-                        "23",
-                        "-pix_fmt",
-                        "yuv420p",
-                        str(self._planned_output),
-                    ]
-                )
-            if not ok:
-                self._append_warning("ffmpeg_compose_failed", err)
-                self.artifacts = self.summary()
-                return
-
-            self.output_video_path = str(Path(self._planned_output).resolve())
-        except Exception as exc:
-            self.warnings.append(f"video_finalize_error: {exc}")
-
-        self.artifacts = self.summary()
-
-    def summary(self) -> Dict[str, Any]:
-        record_log = (
-            os.path.abspath(self._ffmpeg_record_log_path)
-            if self.enabled and self._ffmpeg_record_log_path
-            else None
-        )
-        return {
-            "enabled": self.enabled,
-            "path": self.output_video_path,
-            "capture_path": self.capture_path,
-            "record_log_path": record_log,
-            "warnings": list(self.warnings),
-        }
-
-    def to_artifact_dict(self) -> Dict[str, Any]:
-        data = self.summary()
-        data["batch_id"] = self.batch_id
-        return data
--- a/scripts/jiangchang_skill_core/runtime_env.py
+++ b/scripts/jiangchang_skill_core/runtime_env.py
@@ -1,109 +0,0 @@
-"""
-JIANGCHANG_* 数据根与用户目录：解析规则 + 可选本地 CLI 默认值。
-
-模板复制后通常无需大改；如组织环境不同，再按项目实际调整。
-"""
-
-from __future__ import annotations
-
-import os
-import sys
-
-CLI_LOCAL_DEV_ENABLED = True
-DEFAULT_LOCAL_USER_ID = "10032"
-WIN_DEFAULT_DATA_ROOT = r"D:\jiangchang-data"
-WIN_DEFAULT_JIANGCHANG_APP_ROOT = r"D:\AI\jiangchang"
-
-
-def platform_default_data_root() -> str:
-    if sys.platform == "win32":
-        return WIN_DEFAULT_DATA_ROOT
-    return os.path.join(os.path.expanduser("~"), ".jiangchang-data")
-
-
-def get_data_root() -> str:
-    env = (
-        os.getenv("CLAW_DATA_ROOT")
-        or os.getenv("JIANGCHANG_DATA_ROOT")
-        or ""
-    ).strip()
-    if env:
-        return env
-    return platform_default_data_root()
-
-
-def get_user_id() -> str:
-    return (
-        os.getenv("CLAW_USER_ID")
-        or os.getenv("JIANGCHANG_USER_ID")
-        or ""
-    ).strip() or "_anon"
-
-
-def _looks_like_skills_root(path: str) -> bool:
-    if not path or not os.path.isdir(path):
-        return False
-    # 通过常见基础技能存在与否，判断这是不是 skills 根目录
-    # 这里列举的是平台基础设施类技能，不包含具体业务技能
-    for marker in (
-        "llm-manager",
-        "skill-template",
-    ):
-        if os.path.isdir(os.path.join(path, marker)):
-            return True
-    return False
-
-
-def get_skills_root() -> str:
-    for key in ("JIANGCHANG_SKILLS_ROOT", "CLAW_SKILLS_ROOT"):
-        v = (os.getenv(key) or "").strip()
-        if v:
-            return os.path.normpath(v)
-
-    app = (os.getenv("JIANGCHANG_APP_ROOT") or "").strip()
-    if sys.platform == "win32" and not app:
-        app = WIN_DEFAULT_JIANGCHANG_APP_ROOT
-    if app:
-        nested = os.path.join(app, "skills")
-        if _looks_like_skills_root(nested):
-            return os.path.normpath(nested)
-        if _looks_like_skills_root(app):
-            return os.path.normpath(app)
-
-    if sys.platform == "win32":
-        nested = os.path.join(WIN_DEFAULT_JIANGCHANG_APP_ROOT, "skills")
-        if _looks_like_skills_root(nested):
-            return os.path.normpath(nested)
-        if _looks_like_skills_root(WIN_DEFAULT_JIANGCHANG_APP_ROOT):
-            return os.path.normpath(WIN_DEFAULT_JIANGCHANG_APP_ROOT)
-
-    return os.path.normpath(os.path.join(os.path.expanduser("~"), ".openclaw", "skills"))
-
-
-def get_sibling_skills_root(skill_scripts_dir: str | None = None) -> str:
-    if skill_scripts_dir:
-        scripts = os.path.abspath(skill_scripts_dir)
-        skill_root = os.path.dirname(scripts)
-        inferred = os.path.dirname(skill_root)
-        if _looks_like_skills_root(inferred):
-            return os.path.normpath(inferred)
-
-    for key in ("JIANGCHANG_SKILLS_ROOT", "CLAW_SKILLS_ROOT"):
-        v = (os.getenv(key) or "").strip()
-        if v:
-            return os.path.normpath(v)
-
-    return get_skills_root()
-
-
-def apply_cli_local_defaults() -> None:
-    enabled = CLI_LOCAL_DEV_ENABLED
-    if not enabled:
-        v = (os.getenv("JIANGCHANG_CLI_LOCAL_DEV") or "").strip().lower()
-        enabled = v in ("1", "true", "yes", "on")
-    if not enabled:
-        return
-    if not (os.getenv("CLAW_DATA_ROOT") or os.getenv("JIANGCHANG_DATA_ROOT") or "").strip():
-        os.environ["JIANGCHANG_DATA_ROOT"] = platform_default_data_root()
-    if not (os.getenv("CLAW_USER_ID") or os.getenv("JIANGCHANG_USER_ID") or "").strip():
-        os.environ["JIANGCHANG_USER_ID"] = DEFAULT_LOCAL_USER_ID.strip()
--- a/scripts/jiangchang_skill_core/unified_logging.py
+++ b/scripts/jiangchang_skill_core/unified_logging.py
@@ -1,213 +0,0 @@
-"""
-统一文件日志：{JIANGCHANG_DATA_ROOT}/{JIANGCHANG_USER_ID}/logs/jiangchang.log
-按日轮转；行内带 trace_id 与 skill_slug，便于跨技能排查。
-"""
-
-from __future__ import annotations
-
-import logging
-import os
-import sys
-import uuid
-from logging.handlers import TimedRotatingFileHandler
-from typing import Optional, Tuple
-
-from .runtime_env import get_data_root, get_user_id
-
-_skill_slug: str = ""
-_logger_name: str = ""
-
-# 避免 logging 内部错误再向 stderr 打印 "--- Logging error ---"
-logging.raiseExceptions = False
-
-
-def get_unified_logs_dir() -> str:
-    path = os.path.join(get_data_root(), get_user_id(), "logs")
-    try:
-        os.makedirs(path, exist_ok=True)
-    except OSError:
-        pass
-    return path
-
-
-def get_skill_log_file_path() -> str:
-    """与 setup 写入的主日志文件一致（供终端提示等）。"""
-    override = (os.getenv("JIANGCHANG_LOG_FILE") or "").strip()
-    if override:
-        parent = os.path.dirname(os.path.abspath(override))
-        if parent:
-            try:
-                os.makedirs(parent, exist_ok=True)
-            except OSError:
-                pass
-        return os.path.abspath(override)
-    return os.path.join(get_unified_logs_dir(), "jiangchang.log")
-
-
-def _can_open_log_file(log_path: str) -> Tuple[bool, str]:
-    """探测日志文件是否可追加写入（真实 open，非 os.access）。"""
-    try:
-        parent = os.path.dirname(os.path.abspath(log_path))
-        if parent:
-            os.makedirs(parent, exist_ok=True)
-        with open(log_path, "a", encoding="utf-8"):
-            pass
-        return True, ""
-    except Exception as exc:
-        return False, str(exc)
-
-
-def ensure_trace_for_process() -> str:
-    """本进程调用链 ID：沿用 JIANGCHANG_TRACE_ID，否则生成并写入环境（子进程可继承）。"""
-    existing = (os.getenv("JIANGCHANG_TRACE_ID") or "").strip()
-    if existing:
-        return existing
-    tid = uuid.uuid4().hex[:12]
-    os.environ["JIANGCHANG_TRACE_ID"] = tid
-    return tid
-
-
-def subprocess_env_with_trace(environ: Optional[dict] = None) -> dict:
-    """subprocess.run(..., env=...) 时使用，保证带上当前 trace。"""
-    ensure_trace_for_process()
-    tid = (os.getenv("JIANGCHANG_TRACE_ID") or "").strip()
-    if not tid:
-        tid = ensure_trace_for_process()
-    base = os.environ if environ is None else environ
-    return {**base, "JIANGCHANG_TRACE_ID": tid}
-
-
-class _SkillContextFilter(logging.Filter):
-    def filter(self, record: logging.LogRecord) -> bool:
-        record.trace_id = (os.getenv("JIANGCHANG_TRACE_ID") or "").strip() or "-"
-        record.skill_slug = _skill_slug or "-"
-        return True
-
-
-_FORMAT = (
-    "%(asctime)s | %(levelname)-8s | %(trace_id)s | %(skill_slug)s | %(name)s | %(message)s"
-)
-_DATEFMT = "%Y-%m-%dT%H:%M:%S"
-
-
-def _log_level_from_env() -> int:
-    v = (os.getenv("JIANGCHANG_LOG_LEVEL") or "INFO").strip().upper()
-    return getattr(logging, v, None) or logging.INFO
-
-
-def _backup_count() -> int:
-    try:
-        n = int((os.getenv("JIANGCHANG_LOG_BACKUP_COUNT") or "30").strip())
-        return max(1, min(n, 365))
-    except ValueError:
-        return 30
-
-
-def _clear_logger_handlers(log: logging.Logger) -> None:
-    for h in list(log.handlers):
-        log.removeHandler(h)
-        try:
-            h.close()
-        except Exception:
-            pass
-
-
-def _attach_fallback_handler(log: logging.Logger) -> None:
-    """文件日志不可用时仅挂 NullHandler，不向 stderr 打印 logging 异常。"""
-    log.addHandler(logging.NullHandler())
-
-
-def setup_skill_logging(skill_slug: str, logger_name: str) -> None:
-    """
-    幂等：为指定 logger 挂载统一文件日志与可选 stderr。
-    须在进程早期调用（如 CLI main 在业务日志之前）。
-    文件日志不可写时降级为 NullHandler，不影响 CLI 返回码。
-    """
-    global _skill_slug, _logger_name
-    logging.raiseExceptions = False
-    ensure_trace_for_process()
-    _skill_slug = skill_slug
-    _logger_name = logger_name
-
-    log = logging.getLogger(logger_name)
-    _clear_logger_handlers(log)
-    log.setLevel(_log_level_from_env())
-    fmt = logging.Formatter(_FORMAT, datefmt=_DATEFMT)
-    filt = _SkillContextFilter()
-
-    log_path = get_skill_log_file_path()
-    ok, _err = _can_open_log_file(log_path)
-    if ok:
-        try:
-            fh = TimedRotatingFileHandler(
-                log_path,
-                when="midnight",
-                interval=1,
-                backupCount=_backup_count(),
-                encoding="utf-8",
-                delay=False,
-            )
-            fh.setFormatter(fmt)
-            fh.addFilter(filt)
-            log.addHandler(fh)
-        except Exception:
-            _attach_fallback_handler(log)
-    else:
-        _attach_fallback_handler(log)
-
-    if (os.getenv("JIANGCHANG_LOG_TO_STDERR") or "").strip().lower() in (
-        "1",
-        "true",
-        "yes",
-        "on",
-    ):
-        try:
-            sh = logging.StreamHandler(sys.stderr)
-            sh.setLevel(logging.WARNING)
-            sh.setFormatter(fmt)
-            sh.addFilter(filt)
-            log.addHandler(sh)
-        except Exception:
-            pass
-    log.propagate = False
-
-
-def get_skill_logger() -> logging.Logger:
-    if not _logger_name:
-        raise RuntimeError("get_skill_logger: call setup_skill_logging first")
-    return logging.getLogger(_logger_name)
-
-
-def attach_unified_file_handler(
-    log_path: str,
-    *,
-    skill_slug: str,
-    logger_name: str,
-    level: int = logging.DEBUG,
-) -> logging.Logger:
-    """
-    独立子进程内追加同一日志文件（如 login 检测子进程），格式与主进程一致。
-    """
-    global _skill_slug
-    logging.raiseExceptions = False
-    ensure_trace_for_process()
-    _skill_slug = skill_slug
-    lg = logging.getLogger(logger_name)
-    _clear_logger_handlers(lg)
-    lg.setLevel(level)
-    fmt = logging.Formatter(_FORMAT, datefmt=_DATEFMT)
-    filt = _SkillContextFilter()
-
-    ok, _err = _can_open_log_file(log_path)
-    if ok:
-        try:
-            fh = logging.FileHandler(log_path, encoding="utf-8", delay=False)
-            fh.setFormatter(fmt)
-            fh.addFilter(filt)
-            lg.addHandler(fh)
-        except Exception:
-            _attach_fallback_handler(lg)
-    else:
-        _attach_fallback_handler(lg)
-    lg.propagate = False
-    return lg
--- a/scripts/main.py
+++ b/scripts/main.py
@@ -5,6 +5,9 @@ skill-template CLI 入口。

 复制为新技能后，请修改注释与常量，但保留当前分层结构：
 cli（argv）→ service（业务编排）→ db（持久化）→ util（通用工具）。
+
+jiangchang_skill_core 来自宿主共享 Python runtime 安装的 jiangchang-platform-kit，
+不在技能仓库内 vendored。
 """
 from __future__ import annotations

--- a/scripts/service/sibling_bridge.py
+++ b/scripts/service/sibling_bridge.py
@@ -1,7 +1,7 @@
-"""兄弟技能 CLI 调用模板。
+"""兄弟技能 CLI 调用工具。

-通用工具：通过子进程调用同级其他 skill 的 main.py，并解析 JSON 输出。
-具体调用哪些兄弟技能，由具体业务 skill 决定（在 task_service.py 中按需 import 调用）。
+通过子进程调用同级其他 skill 的 main.py，并解析 JSON 输出。
+具体调用哪些兄弟技能，由复制后的业务 skill 在 service 层按需决定。
 """

 from __future__ import annotations
@@ -50,16 +50,8 @@ def call_sibling_json(skill_slug: str, args: List[str]) -> Optional[Dict[str, An
 def get_sibling_main_path(skill_slug: str) -> str:
    """获取兄弟技能的 main.py 绝对路径。

-    使用示例（在你的 task_service.py 中）：
+    使用示例（在 task_service.py 中）：
        from service.sibling_bridge import get_sibling_main_path, call_sibling_json
-        # 调用名为 account-manager 的兄弟技能：
        result = call_sibling_json("account-manager", ["list", "--limit", "10"])
    """
    return os.path.join(get_skills_root(), skill_slug, "scripts", "main.py")
-
-
-# ============================================================
-# 复制本模板后，按需在你自己的 task_service.py 中调用上面的工具。
-# 不要在本文件中硬编码具体兄弟技能函数（如 get_account_manager_main_path），
-# 那是发布类技能的特定需求，不属于通用模板。
-# ============================================================
--- a/scripts/service/task_service.py
+++ b/scripts/service/task_service.py
@@ -7,12 +7,14 @@
 from __future__ import annotations

 import json
-import sys
 from typing import Optional

+from jiangchang_skill_core import collect_runtime_diagnostics, format_runtime_health_lines
+
 from db import task_logs_repository as tlr
 from service.entitlement_service import check_entitlement
-from util.constants import SKILL_SLUG, SKILL_VERSION
+from util.constants import PLATFORM_KIT_MIN_VERSION, SKILL_SLUG, SKILL_VERSION
+from util.runtime_paths import get_skill_root
 from util.timeutil import unix_to_iso


@@ -89,7 +91,16 @@ def cmd_log_get(log_id: str) -> int:


 def cmd_health() -> int:
-    return 0 if sys.version_info >= (3, 10) else 1
+    runtime = collect_runtime_diagnostics(
+        skill_slug=SKILL_SLUG,
+        platform_kit_min_version=PLATFORM_KIT_MIN_VERSION,
+        skill_root=get_skill_root(),
+    )
+    status = "failed" if runtime.has_fatal_issues else "ok"
+    print(f"{SKILL_SLUG} health: {status}")
+    for line in format_runtime_health_lines(runtime):
+        print(line)
+    return 1 if runtime.has_fatal_issues else 0


 def cmd_version() -> int:
--- a/scripts/util/constants.py
+++ b/scripts/util/constants.py
@@ -1,5 +1,6 @@
-"""技能标识与版本（复制后请修改）。"""
+"""技能标识、版本与平台公共库约束（复制后请修改 slug/version/logger）。"""

 SKILL_SLUG = "your-skill-slug"
 SKILL_VERSION = "1.0.14"
 LOG_LOGGER_NAME = "openclaw.skill.your_skill_slug"
+PLATFORM_KIT_MIN_VERSION = "1.0.11"
--- a/tests/README.md
+++ b/tests/README.md
@@ -30,8 +30,8 @@

 从本模板复制出新技能仓库后，建议至少逐项确认：

- [ ] `python tests/run_tests.py -v` 能通过。
- [ ] `python scripts/main.py health` 能通过。
+- [ ] `python tests/run_tests.py -v` 能通过（含 platform-kit 导入与无 vendored core 守护）。
+- [ ] `python scripts/main.py health` 能通过（输出 runtime diagnostics；warning 不导致非零退出）。
 - [ ] `python scripts/main.py version` 输出 JSON，且 `skill` 与目录名 / `SKILL.md` / `constants.SKILL_SLUG` 一致。
 - [ ] 所有 DB / 文件写入都在 `IsolatedDataRoot`（或等价隔离）下测试，不写真实数据目录。
 - [ ] 外部系统默认使用 mock / `FakeAdapter`，不访问真实 API，不打开真实 RPA。
@@ -74,6 +74,11 @@ python tests/run_tests.py test_cli_smoke
 | ``SKILL.md`` slug 与 ``constants.SKILL_SLUG`` | ``test_skill_metadata.py`` |
 | DB / ``task_logs`` 骨架冒烟 | ``test_db_smoke.py`` |
 | **adapter profile / 外呼授权策略** | ``test_adapter_profile_policy.py`` + ``adapter_test_utils.py``（非 ``test_`` 前缀，不自动当用例收集） |
+| **无 vendored ``jiangchang_skill_core``** | ``test_platform_import.py`` |
+| **runtime diagnostics 架构守护** | ``test_runtime_diagnostics_integration.py`` |
+| **文档/runtime 标准守护** | ``test_template_runtime_standard.py`` |
+
+复制为新技能后**不得删除**上述架构守护测试，除非同步更新模板标准并理解影响。

 ### 1.3 数据隔离（``_support.IsolatedDataRoot``）

--- a/tests/_support.py
+++ b/tests/_support.py
@@ -39,6 +39,16 @@ def get_skill_root() -> str:
    return _SKILL_ROOT


+def platform_kit_version_patch(version: str = "1.0.11"):
+    """Mock installed jiangchang-platform-kit version for health/diagnostics tests."""
+    from unittest.mock import patch
+
+    return patch(
+        "jiangchang_skill_core.runtime_diagnostics._platform_kit_version",
+        return_value=version,
+    )
+
+
 class IsolatedDataRoot:
    """
    在独立临时目录下模拟数据根，避免污染本机默认数据目录。
--- a/tests/test_cli_smoke.py
+++ b/tests/test_cli_smoke.py
@@ -8,7 +8,7 @@ import os
 import unittest
 from contextlib import redirect_stderr, redirect_stdout

-from _support import IsolatedDataRoot
+from _support import IsolatedDataRoot, platform_kit_version_patch

 # scripts/ 已由 _support 注入 sys.path
 from cli.app import main
@@ -27,10 +27,23 @@ class TestCliSmoke(unittest.TestCase):
        self.assertIn("health", out)

    def test_health_zero(self) -> None:
-        buf = io.StringIO()
-        with redirect_stdout(buf), redirect_stderr(io.StringIO()):
-            rc = main(["health"])
-        self.assertEqual(rc, 0)
+        old_record = os.environ.get("OPENCLAW_RECORD_VIDEO")
+        os.environ["OPENCLAW_RECORD_VIDEO"] = "0"
+        try:
+            buf = io.StringIO()
+            with platform_kit_version_patch(), redirect_stdout(buf), redirect_stderr(io.StringIO()):
+                rc = main(["health"])
+            self.assertEqual(rc, 0)
+            out = buf.getvalue()
+            self.assertIn("health:", out)
+            self.assertIn("python_executable:", out)
+            self.assertIn("platform_kit_version:", out)
+            self.assertIn("jiangchang_skill_core_file:", out)
+        finally:
+            if old_record is None:
+                os.environ.pop("OPENCLAW_RECORD_VIDEO", None)
+            else:
+                os.environ["OPENCLAW_RECORD_VIDEO"] = old_record

    def test_version_json_and_matches_constants_slug(self) -> None:
        buf = io.StringIO()
--- a/tests/test_platform_import.py
+++ b/tests/test_platform_import.py
@@ -0,0 +1,117 @@
+# -*- coding: utf-8 -*-
+"""防回归：公共能力必须从共享 platform-kit 导入，而非技能 vendored 副本。"""
+from __future__ import annotations
+
+import importlib.metadata as metadata
+import os
+import re
+import sys
+import unittest
+
+from _support import get_scripts_dir, get_skill_root
+
+
+def _parse_platform_kit_min_version(skill_md_text: str) -> str:
+    parts = skill_md_text.split("---", 2)
+    if len(parts) < 2:
+        raise ValueError("missing frontmatter")
+    m = re.search(
+        r"platform_kit_min_version:\s*[\"']?([^\"'\s]+)[\"']?",
+        parts[1],
+    )
+    if not m:
+        raise ValueError("platform_kit_min_version not found")
+    return m.group(1).strip()
+
+
+class TestPlatformImportSource(unittest.TestCase):
+    def test_jiangchang_skill_core_not_from_skill_scripts(self) -> None:
+        scripts_dir = os.path.abspath(get_scripts_dir())
+        skill_root = os.path.abspath(get_skill_root())
+        vendored = os.path.join(scripts_dir, "jiangchang_skill_core")
+
+        self.assertFalse(
+            os.path.isdir(vendored),
+            f"vendored package must not exist: {vendored}",
+        )
+
+        import jiangchang_skill_core
+        import jiangchang_skill_core.rpa.video_session as video_session
+
+        core_file = os.path.abspath(jiangchang_skill_core.__file__)
+        video_file = os.path.abspath(video_session.__file__)
+
+        self.assertNotIn(
+            scripts_dir.lower(),
+            core_file.lower(),
+            msg=f"jiangchang_skill_core loaded from skill scripts: {core_file}",
+        )
+        self.assertNotIn(
+            skill_root.lower(),
+            core_file.lower(),
+            msg=f"jiangchang_skill_core loaded from skill tree: {core_file}",
+        )
+        self.assertNotIn(
+            scripts_dir.lower(),
+            video_file.lower(),
+            msg=f"video_session loaded from skill scripts: {video_file}",
+        )
+
+        from jiangchang_skill_core.rpa.video_session import RpaVideoSession
+
+        self.assertTrue(callable(RpaVideoSession))
+
+    def test_skill_tree_load_issue_helper(self) -> None:
+        from jiangchang_skill_core import is_jiangchang_skill_core_from_skill_tree
+
+        skill_root = os.path.abspath(get_skill_root())
+        fake = os.path.join(skill_root, "scripts", "jiangchang_skill_core", "__init__.py")
+        self.assertTrue(
+            is_jiangchang_skill_core_from_skill_tree(skill_root=skill_root, core_file=fake)
+        )
+        self.assertFalse(
+            is_jiangchang_skill_core_from_skill_tree(
+                skill_root=skill_root, core_file=sys.executable
+            )
+        )
+
+    def test_platform_kit_min_version_is_1_0_11(self) -> None:
+        from jiangchang_skill_core import version_ge
+        from util.constants import PLATFORM_KIT_MIN_VERSION
+
+        self.assertEqual(PLATFORM_KIT_MIN_VERSION, "1.0.11")
+
+        md_path = os.path.join(get_skill_root(), "SKILL.md")
+        with open(md_path, encoding="utf-8") as f:
+            md = f.read()
+        self.assertEqual(_parse_platform_kit_min_version(md), "1.0.11")
+
+        req_path = os.path.join(get_skill_root(), "requirements.txt")
+        with open(req_path, encoding="utf-8") as f:
+            req = f.read()
+        self.assertIn("jiangchang-platform-kit>=1.0.11", req)
+
+        installed = metadata.version("jiangchang-platform-kit")
+        self.assertTrue(
+            version_ge(installed, PLATFORM_KIT_MIN_VERSION),
+            msg=f"installed {installed!r} < required {PLATFORM_KIT_MIN_VERSION!r}",
+        )
+
+    def test_collect_runtime_diagnostics_importable(self) -> None:
+        from jiangchang_skill_core import collect_runtime_diagnostics
+
+        self.assertTrue(callable(collect_runtime_diagnostics))
+
+    def test_main_import_smoke(self) -> None:
+        scripts_dir = get_scripts_dir()
+        if scripts_dir not in sys.path:
+            sys.path.insert(0, scripts_dir)
+
+        from cli.app import build_parser
+
+        parser = build_parser()
+        self.assertIsNotNone(parser)
+
+
+if __name__ == "__main__":
+    unittest.main()
--- a/tests/test_runtime_diagnostics_integration.py
+++ b/tests/test_runtime_diagnostics_integration.py
@@ -0,0 +1,72 @@
+# -*- coding: utf-8 -*-
+"""Architecture guard: runtime diagnostics must come from platform-kit."""
+from __future__ import annotations
+
+import os
+import unittest
+
+from _support import get_scripts_dir, get_skill_root
+
+_FORBIDDEN_DEFINITIONS = (
+    "class RuntimeDiagnostics",
+    "class RuntimeIssue",
+    "def collect_runtime_diagnostics",
+    "def format_runtime_health_lines",
+    "def runtime_diagnostics_dict",
+    "def _is_git_lfs_pointer",
+    "def _is_usable_audio_file",
+    "def _probe_background_music",
+)
+
+
+class TestRuntimeDiagnosticsIntegration(unittest.TestCase):
+    def test_no_vendored_jiangchang_skill_core(self) -> None:
+        vendored = os.path.join(get_scripts_dir(), "jiangchang_skill_core")
+        self.assertFalse(os.path.isdir(vendored), vendored)
+
+    def test_runtime_diagnostics_module_removed(self) -> None:
+        legacy = os.path.join(get_scripts_dir(), "util", "runtime_diagnostics.py")
+        self.assertFalse(os.path.isfile(legacy), legacy)
+
+    def test_util_py_files_do_not_reimplement_runtime_diagnostics(self) -> None:
+        util_dir = os.path.join(get_scripts_dir(), "util")
+        for name in os.listdir(util_dir):
+            if not name.endswith(".py"):
+                continue
+            path = os.path.join(util_dir, name)
+            with open(path, encoding="utf-8") as f:
+                text = f.read()
+            for forbidden in _FORBIDDEN_DEFINITIONS:
+                self.assertNotIn(
+                    forbidden,
+                    text,
+                    msg=f"{name} must not define {forbidden}",
+                )
+
+    def test_task_service_imports_platform_kit_diagnostics(self) -> None:
+        path = os.path.join(get_scripts_dir(), "service", "task_service.py")
+        with open(path, encoding="utf-8") as f:
+            text = f.read()
+        self.assertIn("from jiangchang_skill_core import", text)
+        self.assertIn("collect_runtime_diagnostics", text)
+        self.assertIn("format_runtime_health_lines", text)
+        self.assertIn("PLATFORM_KIT_MIN_VERSION", text)
+        self.assertNotIn("from util.runtime_diagnostics import", text)
+
+    def test_collect_runtime_diagnostics_callable_from_platform_kit(self) -> None:
+        from jiangchang_skill_core import collect_runtime_diagnostics
+
+        from util.constants import PLATFORM_KIT_MIN_VERSION, SKILL_SLUG
+        from util.runtime_paths import get_skill_root
+
+        diag = collect_runtime_diagnostics(
+            skill_slug=SKILL_SLUG,
+            platform_kit_min_version=PLATFORM_KIT_MIN_VERSION,
+            skill_root=get_skill_root(),
+        )
+        self.assertEqual(diag.skill_slug, SKILL_SLUG)
+        self.assertEqual(diag.platform_kit_min_version, PLATFORM_KIT_MIN_VERSION)
+
+
+if __name__ == "__main__":
+    unittest.main()
--- a/tests/test_template_runtime_standard.py
+++ b/tests/test_template_runtime_standard.py
@@ -0,0 +1,77 @@
+# -*- coding: utf-8 -*-
+"""Docs guard: template must promote shared runtime, not vendored jiangchang_skill_core."""
+from __future__ import annotations
+
+import os
+import unittest
+
+from _support import get_skill_root
+
+DOC_PATHS = (
+    "README.md",
+    "SKILL.md",
+    "references/RUNTIME.md",
+    "references/CLI.md",
+    "references/DEVELOPMENT.md",
+    "references/RPA.md",
+    "references/CONFIG.md",
+)
+
+FORBIDDEN_PHRASES = (
+    "scripts/jiangchang_skill_core/：运行时",
+    "运行时与统一日志副本",
+    "vendor 源码在 scripts/jiangchang_skill_core",
+    "模板通过 vendor 拷贝引用",
+    "vendor 自 platform-kit",
+    "模板 vendor 拷贝在 scripts/jiangchang_skill_core",
+)
+
+POSITIVE_MARKERS = (
+    "jiangchang-platform-kit",
+    "1.0.11",
+    "共享 runtime",
+)
+
+
+class TestTemplateRuntimeStandard(unittest.TestCase):
+    def _read(self, rel_path: str) -> str:
+        path = os.path.join(get_skill_root(), rel_path)
+        with open(path, encoding="utf-8") as f:
+            return f.read()
+
+    def test_guarded_docs_avoid_vendored_core_guidance(self) -> None:
+        for rel_path in DOC_PATHS:
+            text = self._read(rel_path)
+            for phrase in FORBIDDEN_PHRASES:
+                self.assertNotIn(
+                    phrase,
+                    text,
+                    msg=f"{rel_path} must not contain {phrase!r}",
+                )
+
+    def test_guarded_docs_promote_shared_runtime_standard(self) -> None:
+        combined = "\n".join(self._read(p) for p in DOC_PATHS)
+        for marker in POSITIVE_MARKERS:
+            self.assertIn(
+                marker,
+                combined,
+                msg=f"docs should mention {marker!r}",
+            )
+        self.assertTrue(
+            "不得 vendored" in combined or "不要 vendor" in combined,
+            msg="docs should state skills must not vendor jiangchang_skill_core",
+        )
+
+    def test_runtime_md_mentions_collect_runtime_diagnostics(self) -> None:
+        text = self._read("references/RUNTIME.md")
+        self.assertIn("collect_runtime_diagnostics", text)
+
+    def test_cli_md_mentions_health_runtime_diagnostics(self) -> None:
+        text = self._read("references/CLI.md")
+        self.assertIn("python_executable", text)
+        self.assertIn("platform_kit_version", text)
+        self.assertIn("jiangchang_skill_core_file", text)
+
+
+if __name__ == "__main__":
+    unittest.main()