diff --git a/SKILL.md b/SKILL.md
index 9e5ad1b..a3225d7 100644
--- a/SKILL.md
+++ b/SKILL.md
@@ -1,7 +1,7 @@
 ---
 name: 账号管理
 description: 多平台多账号管理。管理各平台账号与Chrome Profile的对应关系，供publisher类Skill调用获取账号信息。
-version: 1.0.1
+version: 1.0.2
 author: 深圳匠厂科技有限公司
 metadata:
   openclaw:
@@ -23,6 +23,12 @@ allowed-tools:
 
 ## 执行步骤
 
+### 添加账号（仅需平台，可选手机号；ID 数据库自增，名称自动生成如「搜狐1号」）
+```bash
+python3 {baseDir}/scripts/account.py add sohu
+python3 {baseDir}/scripts/account.py add sohu 189xxxxxxxx
+```
+
 ### 列出某平台所有账号
 ```bash
 python3 {baseDir}/scripts/account.py list <platform>
\ No newline at end of file
diff --git a/scripts/__pycache__/account.cpython-312.pyc b/scripts/__pycache__/account.cpython-312.pyc
index 741a4cd..dbd6524 100644
Binary files a/scripts/__pycache__/account.cpython-312.pyc and b/scripts/__pycache__/account.cpython-312.pyc differ
diff --git a/scripts/account.py b/scripts/account.py
index d25318f..0e36a16 100644
--- a/scripts/account.py
+++ b/scripts/account.py
@@ -2,29 +2,42 @@ import sys
 import json
 import os
 import sqlite3
+import subprocess
+import tempfile
+import time
 from datetime import datetime
 
 # Windows GBK 编码兼容修复
 if sys.platform == "win32":
     import io
-    sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8', errors='replace')
-    sys.stderr = io.TextIOWrapper(sys.stderr.buffer, encoding='utf-8', errors='replace')
+    sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding="utf-8", errors="replace")
+    sys.stderr = io.TextIOWrapper(sys.stderr.buffer, encoding="utf-8", errors="replace")
 BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 SKILL_SLUG = "account-manager"
 
 PLATFORM_URLS = {
-    # 自媒体/图文平台
     "sohu": "https://mp.sohu.com",
     "zhihu": "https://www.zhihu.com",
     "wechat": "https://mp.weixin.qq.com",
-    
-    # 大模型平台
     "kimi": "https://kimi.moonshot.cn",
     "deepseek": "https://chat.deepseek.com",
     "doubao": "https://www.doubao.com",
     "qianwen": "https://tongyi.aliyun.com",
     "yiyan": "https://yiyan.baidu.com",
-    "yuanbao": "https://yuanbao.tencent.com"
+    "yuanbao": "https://yuanbao.tencent.com",
+}
+
+# 新账号默认名称：搜狐1号 / sohu_2 等同平台序号
+_PLATFORM_NAME_CN = {
+    "sohu": "搜狐",
+    "zhihu": "知乎",
+    "wechat": "微信",
+    "kimi": "Kimi",
+    "deepseek": "DeepSeek",
+    "doubao": "豆包",
+    "qianwen": "通义",
+    "yiyan": "文心",
+    "yuanbao": "元宝",
 }
 
 
@@ -53,7 +66,7 @@ def get_db_path():
 
 
 def get_default_profile_dir(account_id):
-    path = os.path.join(get_skill_data_dir(), "profiles", account_id)
+    path = os.path.join(get_skill_data_dir(), "profiles", str(account_id))
     os.makedirs(path, exist_ok=True)
     return path
 
@@ -62,33 +75,6 @@ def get_conn():
     return sqlite3.connect(get_db_path())
 
 
-def init_db():
-    conn = get_conn()
-    try:
-        cur = conn.cursor()
-        cur.execute(
-            """
-            CREATE TABLE IF NOT EXISTS accounts (
-                id TEXT PRIMARY KEY,
-                name TEXT NOT NULL,
-                platform TEXT NOT NULL,
-                phone TEXT,
-                profile_dir TEXT,
-                login_status INTEGER DEFAULT 0,
-                last_login_at TEXT,
-                extra_json TEXT,
-                created_at TEXT NOT NULL,
-                updated_at TEXT NOT NULL
-            )
-            """
-        )
-        _ensure_column(cur, "accounts", "login_status", "INTEGER DEFAULT 0")
-        _ensure_column(cur, "accounts", "last_login_at", "TEXT")
-        conn.commit()
-    finally:
-        conn.close()
-
-
 def _ensure_column(cur, table_name, col_name, ddl):
     cur.execute(f"PRAGMA table_info({table_name})")
     cols = [row[1] for row in cur.fetchall()]
@@ -96,14 +82,123 @@ def _ensure_column(cur, table_name, col_name, ddl):
         cur.execute(f"ALTER TABLE {table_name} ADD COLUMN {col_name} {ddl}")
 
 
+def _has_text_primary_id(cur):
+    cur.execute("PRAGMA table_info(accounts)")
+    for row in cur.fetchall():
+        if row[1] == "id":
+            t = (row[2] or "").upper()
+            return "TEXT" in t or "CHAR" in t
+    return False
+
+
+def _migrate_text_id_to_integer(conn):
+    cur = conn.cursor()
+    cur.execute(
+        """
+        CREATE TABLE accounts_new (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            name TEXT NOT NULL,
+            platform TEXT NOT NULL,
+            phone TEXT,
+            profile_dir TEXT,
+            url TEXT,
+            login_status INTEGER DEFAULT 0,
+            last_login_at TEXT,
+            extra_json TEXT,
+            created_at TEXT NOT NULL,
+            updated_at TEXT NOT NULL
+        )
+        """
+    )
+    cur.execute(
+        "SELECT name, platform, phone, profile_dir, login_status, last_login_at, extra_json, created_at, updated_at FROM accounts ORDER BY rowid"
+    )
+    rows = cur.fetchall()
+    for row in rows:
+        name, platform, phone, profile_dir, login_status, last_login_at, extra_json, created_at, updated_at = row
+        plat = (platform or "").strip().lower()
+        url = PLATFORM_URLS.get(plat, "")
+        cur.execute(
+            """
+            INSERT INTO accounts_new
+            (name, platform, phone, profile_dir, url, login_status, last_login_at, extra_json, created_at, updated_at)
+            VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
+            """,
+            (
+                name,
+                plat,
+                phone or "",
+                profile_dir or "",
+                url,
+                int(login_status or 0),
+                last_login_at,
+                extra_json,
+                created_at,
+                updated_at,
+            ),
+        )
+    cur.execute("DROP TABLE accounts")
+    cur.execute("ALTER TABLE accounts_new RENAME TO accounts")
+
+
+def init_db():
+    conn = get_conn()
+    try:
+        cur = conn.cursor()
+        cur.execute("SELECT name FROM sqlite_master WHERE type='table' AND name='accounts'")
+        if not cur.fetchone():
+            cur.execute(
+                """
+                CREATE TABLE accounts (
+                    id INTEGER PRIMARY KEY AUTOINCREMENT,
+                    name TEXT NOT NULL,
+                    platform TEXT NOT NULL,
+                    phone TEXT,
+                    profile_dir TEXT,
+                    url TEXT,
+                    login_status INTEGER DEFAULT 0,
+                    last_login_at TEXT,
+                    extra_json TEXT,
+                    created_at TEXT NOT NULL,
+                    updated_at TEXT NOT NULL
+                )
+                """
+            )
+        else:
+            if _has_text_primary_id(cur):
+                _migrate_text_id_to_integer(conn)
+                cur = conn.cursor()
+            _ensure_column(cur, "accounts", "url", "TEXT")
+            cur.execute(
+                "SELECT id, platform FROM accounts WHERE url IS NULL OR TRIM(COALESCE(url,'')) = ''"
+            )
+            for rid, plat in cur.fetchall():
+                pu = PLATFORM_URLS.get((plat or "").strip().lower(), "")
+                if pu:
+                    cur.execute("UPDATE accounts SET url = ? WHERE id = ?", (pu, rid))
+        conn.commit()
+    finally:
+        conn.close()
+
+
+def _normalize_account_id(account_id):
+    if account_id is None:
+        return None
+    s = str(account_id).strip()
+    if s.isdigit():
+        return int(s)
+    return s
+
+
 def get_account_by_id(account_id):
     init_db()
+    aid = _normalize_account_id(account_id)
     conn = get_conn()
     try:
         cur = conn.cursor()
         cur.execute(
-            "SELECT id, name, platform, phone, profile_dir, login_status, last_login_at, extra_json FROM accounts WHERE id = ?",
-            (account_id,),
+            "SELECT id, name, platform, phone, profile_dir, url, login_status, last_login_at, extra_json FROM accounts WHERE id = ?",
+            (aid,),
         )
         row = cur.fetchone()
         if not row:
@@ -114,12 +209,13 @@ def get_account_by_id(account_id):
             "platform": row[2],
             "phone": row[3] or "",
             "profile_dir": row[4] or get_default_profile_dir(row[0]),
-            "login_status": int(row[5] or 0),
-            "last_login_at": row[6],
+            "url": row[5] or PLATFORM_URLS.get(row[2], ""),
+            "login_status": int(row[6] or 0),
+            "last_login_at": row[7],
         }
-        if row[7]:
+        if row[8]:
             try:
-                extra = json.loads(row[7])
+                extra = json.loads(row[8])
                 if isinstance(extra, dict):
                     acc.update(extra)
             except Exception:
@@ -128,14 +224,17 @@ def get_account_by_id(account_id):
     finally:
         conn.close()
 
+
+def _default_name_for_platform(platform: str, index: int) -> str:
+    cn = _PLATFORM_NAME_CN.get(platform)
+    if cn:
+        return f"{cn}{index}号"
+    return f"{platform}_{index}"
+
+
 def cmd_list(platform="all"):
-    """
-    修改后的 list 功能，能直观打出带着【手机号】的详细台账供AI查询匹配！
-    支持查全部(all)，或指定(sohu)
-    """
     init_db()
     conn = get_conn()
-    found = False
     try:
         cur = conn.cursor()
         if platform == "all":
@@ -159,7 +258,8 @@ def cmd_list(platform="all"):
         found = True
 
     if not found:
-        print(f"ERROR:NO_ACCOUNTS_FOUND")
+        print("ERROR:NO_ACCOUNTS_FOUND")
+
 
 def cmd_get(account_id):
     acc = get_account_by_id(account_id)
@@ -169,133 +269,272 @@ def cmd_get(account_id):
     print("ERROR:ACCOUNT_NOT_FOUND")
 
 
-def cmd_add(account_id, name, platform, phone="", profile_dir=""):
+def cmd_add(platform: str, phone: str = ""):
+    """添加账号：仅平台 + 可选手机号；ID 自增，名称按平台序号自动生成。"""
     init_db()
     platform = (platform or "").strip().lower()
     if platform not in PLATFORM_URLS:
         print(f"ERROR:INVALID_PLATFORM (支持: {', '.join(sorted(PLATFORM_URLS.keys()))})")
         return
 
-    account_id = (account_id or "").strip()
-    name = (name or "").strip() or account_id
-    if not account_id:
-        print("ERROR:INVALID_ACCOUNT_ID")
-        return
-
-    profile_dir = (profile_dir or "").strip() or get_default_profile_dir(account_id)
-    os.makedirs(profile_dir, exist_ok=True)
+    phone = (phone or "").strip()
+    url = PLATFORM_URLS[platform]
     now = datetime.now().isoformat(timespec="seconds")
 
     conn = get_conn()
     try:
         cur = conn.cursor()
+        cur.execute("SELECT COUNT(*) FROM accounts WHERE platform = ?", (platform,))
+        next_idx = cur.fetchone()[0] + 1
+        name = _default_name_for_platform(platform, next_idx)
         cur.execute(
             """
-            INSERT INTO accounts (id, name, platform, phone, profile_dir, login_status, last_login_at, extra_json, created_at, updated_at)
-            VALUES (?, ?, ?, ?, ?, 0, NULL, NULL, ?, ?)
-            ON CONFLICT(id) DO UPDATE SET
-                name = excluded.name,
-                platform = excluded.platform,
-                phone = excluded.phone,
-                profile_dir = excluded.profile_dir,
-                updated_at = excluded.updated_at
+            INSERT INTO accounts (name, platform, phone, profile_dir, url, login_status, last_login_at, extra_json, created_at, updated_at)
+            VALUES (?, ?, ?, '', ?, 0, NULL, NULL, ?, ?)
             """,
-            (account_id, name, platform, phone, profile_dir, now, now),
+            (name, platform, phone, url, now, now),
+        )
+        new_id = cur.lastrowid
+        profile_dir = get_default_profile_dir(new_id)
+        cur.execute(
+            "UPDATE accounts SET profile_dir = ?, updated_at = ? WHERE id = ?",
+            (profile_dir, now, new_id),
         )
         conn.commit()
     finally:
         conn.close()
 
-    print(f"✅ 已保存账号：{account_id}（{platform}）")
-    print("ℹ️ 请继续执行登录：python account.py login <账号ID>")
+    print(f"✅ 已保存账号：ID {new_id} | {name} | {platform}")
+    print(f"ℹ️ 登录请执行：python account.py login {new_id}")
+
+
+def _win_find_exe(candidates):
+    for p in candidates:
+        if p and os.path.isfile(p):
+            return p
+    return None
+
+
+def resolve_chromium_channel():
+    """
+    Playwright channel: 'chrome' | 'msedge' | None
+    Windows 优先 Chrome，其次 Edge；其它系统默认 chrome（由 Playwright 解析 PATH）。
+    """
+    if sys.platform != "win32":
+        return "chrome"
+
+    pf = os.environ.get("ProgramFiles", r"C:\Program Files")
+    pfx86 = os.environ.get("ProgramFiles(x86)", r"C:\Program Files (x86)")
+    local = os.environ.get("LocalAppData", "")
+
+    chrome = _win_find_exe(
+        [
+            os.path.join(pf, "Google", "Chrome", "Application", "chrome.exe"),
+            os.path.join(pfx86, "Google", "Chrome", "Application", "chrome.exe"),
+            os.path.join(local, "Google", "Chrome", "Application", "chrome.exe") if local else "",
+        ]
+    )
+    if chrome:
+        return "chrome"
+
+    edge = _win_find_exe(
+        [
+            os.path.join(pfx86, "Microsoft", "Edge", "Application", "msedge.exe"),
+            os.path.join(pf, "Microsoft", "Edge", "Application", "msedge.exe"),
+            os.path.join(local, "Microsoft", "Edge", "Application", "msedge.exe") if local else "",
+        ]
+    )
+    if edge:
+        return "msedge"
+
+    return None
+
+
+def _print_browser_install_hint():
+    print("❌ 未检测到 Google Chrome 或 Microsoft Edge，请先安装后再登录：")
+    print("   • Chrome: https://www.google.com/chrome/")
+    print("   • Edge:   https://www.microsoft.com/zh-cn/edge")
+
+
+def _login_timeout_seconds():
+    try:
+        return max(60, int((os.getenv("JIANGCHANG_LOGIN_TIMEOUT_SECONDS") or "300").strip()))
+    except ValueError:
+        return 300
+
+
+def _verify_login(profile_dir: str, platform: str, start_url: str, channel: str) -> bool:
+    try:
+        from playwright.sync_api import sync_playwright
+    except ImportError:
+        print("⚠️ 未安装 playwright，跳过登录校验（请: pip install playwright && playwright install）")
+        return False
+
+    try:
+        with sync_playwright() as p:
+            ctx = p.chromium.launch_persistent_context(
+                user_data_dir=profile_dir,
+                headless=True,
+                channel=channel,
+                args=["--disable-blink-features=AutomationControlled"],
+            )
+            try:
+                page = ctx.pages[0] if ctx.pages else ctx.new_page()
+                page.goto(start_url, wait_until="domcontentloaded", timeout=45000)
+                time.sleep(2)
+                u = (page.url or "").lower()
+                if platform == "sohu":
+                    if "passport" in u or "/login" in u:
+                        return False
+                    return True
+                if "login" in u or "signin" in u or "passport" in u:
+                    return False
+                return True
+            finally:
+                ctx.close()
+    except Exception:
+        return False
 
 
 def cmd_login(account_id):
-    """首次登录：打开浏览器，用户手动登录，登录态自动保存到Profile目录"""
     target = get_account_by_id(account_id)
-
     if not target:
         print("ERROR:ACCOUNT_NOT_FOUND")
         return
 
+    channel = resolve_chromium_channel()
+    if not channel:
+        _print_browser_install_hint()
+        return
+
+    try:
+        import playwright  # noqa: F401
+    except ImportError:
+        print("ERROR:需要 playwright：pip install playwright && playwright install chromium")
+        return
+
     profile_dir = target["profile_dir"]
     os.makedirs(profile_dir, exist_ok=True)
-    url = PLATFORM_URLS.get(target["platform"], "https://www.google.com")
+    url = (target.get("url") or "").strip() or PLATFORM_URLS.get(target["platform"], "https://www.google.com")
+    platform = (target.get("platform") or "").strip().lower()
+    timeout_sec = _login_timeout_seconds()
 
-    print(f"正在为账号 [{target['name']}] 打开浏览器...")
-    print(f"请在浏览器中完成登录，登录后直接关闭浏览器窗口即可。")
-    print(f"登录态将自动保存到：{profile_dir}")
+    browser_name = "Google Chrome" if channel == "chrome" else "Microsoft Edge"
+    print(f"正在为账号 [{target['name']}] 打开 {browser_name} …")
+    print(f"访问地址：{url}")
+    print("请在窗口内完成登录（扫码/输入密码）。到达等待时间后将自动关闭窗口，您也可提前手动关闭。")
+    print(f"最长等待：{timeout_sec} 秒")
 
-    # 用Playwright打开持久化浏览器，等待用户手动登录
-    login_script = f"""
-import asyncio
-from playwright.async_api import async_playwright
-async def main():
-    async with async_playwright() as p:
-        browser = await p.chromium.launch_persistent_context(
-            user_data_dir=r"{profile_dir}",
-            headless=False,
-            channel="chrome",  # 【修改处】也加上这行
-            no_viewport=True,  # 确保浏览器内容视口也最大化
-            args=["--start-maximized"]
-        )
-        page = browser.pages[0] if browser.pages else await browser.new_page()
-        await page.goto("{url}")
-        print("浏览器已打开，请完成登录后关闭窗口...")
-        # 移除自动超时，无限等待直到用户扫码完手动关闭
-        await browser.wait_for_event("close", timeout=0)
-        print("登录态已保存！")
-asyncio.run(main())
+    # Playwright 同步 API 宜在独立子进程中跑浏览器，避免线程与事件循环问题
+    runner = r"""import json, sys
+from playwright.sync_api import sync_playwright
+with open(sys.argv[1], encoding="utf-8") as f:
+    c = json.load(f)
+with sync_playwright() as p:
+    ctx = p.chromium.launch_persistent_context(
+        user_data_dir=c["profile_dir"],
+        headless=False,
+        channel=c["channel"],
+        no_viewport=True,
+        args=["--start-maximized"],
+    )
+    try:
+        page = ctx.pages[0] if ctx.pages else ctx.new_page()
+        page.goto(c["url"], wait_until="domcontentloaded", timeout=60000)
+        try:
+            ctx.wait_for_event("close", timeout=c["timeout_sec"] * 1000)
+        except Exception:
+            pass
+        try:
+            ctx.close()
+        except Exception:
+            pass
+    except Exception as e:
+        print(e, file=sys.stderr)
+        raise
 """
-    import tempfile
-    with tempfile.NamedTemporaryFile(mode='w', suffix='.py',
-                                     delete=False, encoding='utf-8') as f:
-        f.write(login_script)
-        tmp_path = f.name
+    cfg = {
+        "channel": channel,
+        "profile_dir": profile_dir,
+        "url": url,
+        "timeout_sec": timeout_sec,
+    }
+    with tempfile.NamedTemporaryFile(
+        mode="w", suffix=".json", delete=False, encoding="utf-8"
+    ) as jf:
+        json.dump(cfg, jf, ensure_ascii=False)
+        cfg_path = jf.name
+    with tempfile.NamedTemporaryFile(
+        mode="w", suffix=".py", delete=False, encoding="utf-8"
+    ) as pf:
+        pf.write(runner)
+        py_path = pf.name
+    try:
+        r = subprocess.run(
+            [sys.executable, py_path, cfg_path],
+            timeout=timeout_sec + 180,
+        )
+        if r.returncode != 0:
+            print("⚠️ 浏览器进程异常退出，仍将尝试检测登录状态")
+    except subprocess.TimeoutExpired:
+        print("⚠️ 等待浏览器超时，仍将尝试检测登录状态")
+    finally:
+        try:
+            os.unlink(cfg_path)
+        except OSError:
+            pass
+        try:
+            os.unlink(py_path)
+        except OSError:
+            pass
 
-    exit_code = os.system(f'python "{tmp_path}"')
-    os.unlink(tmp_path)
-    if exit_code == 0:
-        _mark_login_success(account_id)
-        print("✅ 登录状态已标记为已登录")
+    time.sleep(1.5)
+    print("正在检测登录状态…")
+    ok = _verify_login(profile_dir, platform, url, channel)
+    _mark_login_status(target["id"], ok)
+    if ok:
+        print("✅ 检测到已登录，状态已写入数据库")
     else:
-        print("⚠️ 浏览器登录流程异常退出，登录状态未更新")
+        print("⚠️ 未检测到有效登录，状态为未登录。请关闭其他占用该用户目录的浏览器后重试，或延长 JIANGCHANG_LOGIN_TIMEOUT_SECONDS 后再登录。")
 
 
-def _mark_login_success(account_id):
+def _mark_login_status(account_id, success: bool):
     now = datetime.now().isoformat(timespec="seconds")
     conn = get_conn()
     try:
         cur = conn.cursor()
-        cur.execute(
-            "UPDATE accounts SET login_status = 1, last_login_at = ?, updated_at = ? WHERE id = ?",
-            (now, now, account_id),
-        )
+        if success:
+            cur.execute(
+                "UPDATE accounts SET login_status = 1, last_login_at = ?, updated_at = ? WHERE id = ?",
+                (now, now, account_id),
+            )
+        else:
+            cur.execute(
+                "UPDATE accounts SET login_status = 0, updated_at = ? WHERE id = ?",
+                (now, account_id),
+            )
         conn.commit()
     finally:
         conn.close()
 
+
 if __name__ == "__main__":
     if len(sys.argv) < 2:
-        print("用法：python account.py add <id> <name> <platform> [phone] [profile_dir] | list [platform] | get <id> | login <id>")
+        print(
+            "用法：python account.py add <platform> [phone] | list [platform] | get <id> | login <id>"
+        )
         sys.exit(1)
 
     cmd = sys.argv[1]
-    # 兼容写反顺序：python account.py sohu list
     if len(sys.argv) >= 3 and sys.argv[2] == "list" and cmd in PLATFORM_URLS:
         cmd_list(cmd)
     elif cmd in PLATFORM_URLS and len(sys.argv) == 2:
         cmd_list(cmd)
-    elif cmd == "add" and len(sys.argv) >= 5:
-        cmd_add(
-            sys.argv[2],
-            sys.argv[3],
-            sys.argv[4],
-            sys.argv[5] if len(sys.argv) >= 6 else "",
-            sys.argv[6] if len(sys.argv) >= 7 else "",
-        )
+    elif cmd == "add" and len(sys.argv) >= 3:
+        plat = sys.argv[2].lower()
+        phone_arg = sys.argv[3] if len(sys.argv) >= 4 else ""
+        cmd_add(plat, phone_arg)
     elif cmd == "list":
-        # 默认不传 platform 时打出 all
         cmd_list(sys.argv[2] if len(sys.argv) >= 3 else "all")
     elif cmd == "get" and len(sys.argv) >= 3:
         cmd_get(sys.argv[2])
@@ -303,4 +542,4 @@ if __name__ == "__main__":
         cmd_login(sys.argv[2])
     else:
         print("参数错误")
-        sys.exit(1)
\ No newline at end of file
+        sys.exit(1)