diff --git a/.vala_skill_hashes b/.vala_skill_hashes
index 1a68556..0f30b62 100644
--- a/.vala_skill_hashes
+++ b/.vala_skill_hashes
@@ -11,4 +11,4 @@ smart-auto-model-switch bfb3547dcd6029622c7062b49ae7922614a366b6dfe88c7d0fae9dcd
 vala_git_workspace_backup.vala 4cf352bec88fe84af065ba1ffcbb06647b77df0e01860faaf0bca9fd64b968ec
 feishu-group-msg-sync 338e821c4dd0b2f532b7f3ca31aea6d1881e16e0a76a6b7a0ecf2b723907690f
 tencent-cos-upload 172517ed41d06c48425cd961ec5972a48495cfd62ec588bc1c2912ddf31b3a06
-user-feedback-collector 7a2c9fc9b2b32f8dd0be52c1ac3cf6d33bc992c1ec200f061a26acaa7c637f77
+user-feedback-collector 487eaa8446495d891c72d0f1171eec822b0877ab9dae4111eb477dc706e1ae71
diff --git a/data/last_feedback_sync_time b/data/last_feedback_sync_time
index 562620f..4dfd4e8 100644
--- a/data/last_feedback_sync_time
+++ b/data/last_feedback_sync_time
@@ -1 +1 @@
-2026-04-17T06:00:01.887056+08:00
\ No newline at end of file
+2026-04-17T12:00:01.691097+08:00
\ No newline at end of file
diff --git a/data/last_lark_group_sync_time b/data/last_lark_group_sync_time
new file mode 100644
index 0000000..4cad3e0
--- /dev/null
+++ b/data/last_lark_group_sync_time
@@ -0,0 +1 @@
+2026-04-18T08:00:01.304881+08:00
\ No newline at end of file
diff --git a/data/last_wechat_sync_id b/data/last_wechat_sync_id
new file mode 100644
index 0000000..b6e2760
--- /dev/null
+++ b/data/last_wechat_sync_id
@@ -0,0 +1 @@
+242
\ No newline at end of file
diff --git a/memory/2026-04-17-cron-check.md b/memory/2026-04-17-cron-check.md
new file mode 100644
index 0000000..7ced783
--- /dev/null
+++ b/memory/2026-04-17-cron-check.md
@@ -0,0 +1,45 @@
+# Session: 2026-04-17 07:25:23 UTC
+
+- **Session Key**: agent:xiaokui:feishu:direct:ou_088ee79216826be4a24af44f7268f880
+- **Session ID**: cbba7f09-869f-45a9-baf8-ff35f64ec7b2
+- **Source**: feishu
+
+## Conversation Summary
+
+assistant: ✅ New session started · model: volcengine/doubao-seed-2-0-pro-260215
+user: System: [2026-04-15 19:11:21 GMT+8] Feishu[xiaokui] DM | 李若松 (ou_088ee79216826be4a24af44f7268f880) [msg:om_x100b52c36b4460bcb314283a8b23394]
+
+A new session was started via /new or /reset. Run your Session Startup sequence - read the required files before responding to the user. Then greet the user in your configured persona, if one is provided. Be yourself - use your defined voice, mannerisms, and mood. Keep it to 1-3 sentences and ask what they want to do. If the runtime model differs from default_model in the system prompt, mention the default model. Do not mention internal steps, files, tools, or reasoning.
+Current time: Wednesday, April 15th, 2026 — 7:11 PM (Asia/Shanghai) / 2026-04-15 11:11 UTC
+assistant: 若松好，我已准备就绪，有什么需求可以随时告诉我。
+user: System: [2026-04-15 19:11:45 GMT+8] Feishu[xiaokui] DM | 李若松 (ou_088ee79216826be4a24af44f7268f880) [msg:om_x100b52c368abd0b0b4c78753a17ec00]
+
+Conversation info (untrusted metadata):
+```json
+{
+  "message_id": "om_x100b52c368abd0b0b4c78753a17ec00",
+  "sender_id": "ou_088ee79216826be4a24af44f7268f880",
+  "sender": "李若松",
+  "timestamp": "Wed 2026-04-15 19:11 GMT+8"
+}
+```
+
+Sender (untrusted metadata):
+```json
+{
+  "label": "李若松 (ou_088ee79216826be4a24af44f7268f880)",
+  "id": "ou_088ee79216826be4a24af44f7268f880",
+  "name": "李若松"
+}
+```
+
+查看你的定时任务
+assistant: 当前小葵的定时任务如下：
+
+### 系统crontab任务：
+1. **VALA技能自动推送**：每天凌晨2:00执行 `/root/.openclaw/workspace-xiaokui/scripts/vala_skill_auto_push.sh`，日志路径：`/root/.openclaw/workspace-xiaokui/logs/vala_skill_push.log`
+2. **用户反馈群同步**：每6小时执行一次 `/root/.openclaw/workspace-xiaokui/scripts/sync_feedback_group.py`，日志路径：`/var/log/feedback_sync.log`
+3. **Git工作区备份**：每天早上8:10执行 `/root/.openclaw/workspace-xiaokui/skills/vala_git_workspace_backup/scripts/backup.sh`，日志路径：`/root/.openclaw/workspace-xiaokui/logs/git_backup.log`
+
+### openclaw cron任务：
+暂无创建的定时任务。
diff --git a/memory/2026-04-17-feishu-message-stats.md b/memory/2026-04-17-feishu-message-stats.md
new file mode 100644
index 0000000..b3fe197
--- /dev/null
+++ b/memory/2026-04-17-feishu-message-stats.md
@@ -0,0 +1,161 @@
+# Session: 2026-04-17 16:11:04 UTC
+
+- **Session Key**: agent:xiaokui:feishu:direct:ou_088ee79216826be4a24af44f7268f880
+- **Session ID**: 756e2dcf-7477-4385-a081-e7148a04e59a
+- **Source**: feishu
+
+## Conversation Summary
+
+assistant: ✅ New session started · model: volcengine/doubao-seed-2-0-pro-260215
+user: System: [2026-04-17 16:10:44 GMT+8] Feishu[xiaokui] DM | 李若松 (ou_088ee79216826be4a24af44f7268f880) [msg:om_x100b512afef0948cb2c3d0b78cebed9]
+System: [2026-04-17 16:10:49 GMT+8] Feishu[xiaokui] DM | 李若松 (ou_088ee79216826be4a24af44f7268f880) [msg:om_x100b512afe48dcb0b215c867411ab87]
+
+A new session was started via /new or /reset. Run your Session Startup sequence - read the required files before responding to the user. Then greet the user in your configured persona, if one is provided. Be yourself - use your defined voice, mannerisms, and mood. Keep it to 1-3 sentences and ask what they want to do. If the runtime model differs from default_model in the system prompt, mention the default model. Do not mention internal steps, files, tools, or reasoning.
+Current time: Friday, April 17th, 2026 — 4:11 PM (Asia/Shanghai) / 2026-04-17 08:11 UTC
+assistant: 你好若松，我已就位，请问今天需要我处理什么工作？
+user: System: [2026-04-17 16:11:33 GMT+8] Feishu[xiaokui] DM | 李若松 (ou_088ee79216826be4a24af44f7268f880) [msg:om_x100b512afd8e482cb282f22d314c588]
+
+Conversation info (untrusted metadata):
+```json
+{
+  "message_id": "om_x100b512afd8e482cb282f22d314c588",
+  "sender_id": "ou_088ee79216826be4a24af44f7268f880",
+  "sender": "李若松",
+  "timestamp": "Fri 2026-04-17 16:11 GMT+8"
+}
+```
+
+Sender (untrusted metadata):
+```json
+{
+  "label": "李若松 (ou_088ee79216826be4a24af44f7268f880)",
+  "id": "ou_088ee79216826be4a24af44f7268f880",
+  "name": "李若松"
+}
+```
+
+查看一下   你的飞书消息数据库中    记录了多少条消息  最近一条是什么时候
+assistant: 请提供一下MySQL数据库的连接信息（主机地址、端口、用户名、密码），我来查询飞书消息表的记录。
+user: System: [2026-04-17 16:13:15 GMT+8] Feishu[xiaokui] DM | 李若松 (ou_088ee79216826be4a24af44f7268f880) [msg:om_x100b512af77d5090b2592e0af891675]
+
+Conversation info (untrusted metadata):
+```json
+{
+  "message_id": "om_x100b512af77d5090b2592e0af891675",
+  "sender_id": "ou_088ee79216826be4a24af44f7268f880",
+  "sender": "李若松",
+  "timestamp": "Fri 2026-04-17 16:13 GMT+8"
+}
+```
+
+Sender (untrusted metadata):
+```json
+{
+  "label": "李若松 (ou_088ee79216826be4a24af44f7268f880)",
+  "id": "ou_088ee79216826be4a24af44f7268f880",
+  "name": "李若松"
+}
+```
+
+你查看下你的用户反馈 skill！
+assistant: 我已查看用户反馈收集skill的配置，目前反馈数据的存储情况如下：
+1. **主动上报的用户反馈**：实时存储在飞书知识库文档《2026年 用户反馈收集》（Wiki Token: SB3dwaSshie7ifklKlLc2GswnqX）
+2. **飞书内部测试反馈群消息**：每4小时同步到MySQL数据库 `vala_test.lark_group_message` 表
+3. **微信用户反馈群消息**：实时存储到MySQL数据库 `vala_test.wechat_group_message` 表
+
+当前本地MySQL服务未启动，无法查询数据库中的消息统计，如需查询具体数据需要先启动本地MySQL服务或者提供远程数据库连接信息。
+user: System: [2026-04-17 23:25:09 GMT+8] Feishu[xiaokui] DM | 李若松 (ou_088ee79216826be4a24af44f7268f880) [msg:om_x100b5111438994acb10ee4cd657ae45]
+
+Conversation info (untrusted metadata):
+```json
+{
+  "message_id": "om_x100b5111438994acb10ee4cd657ae45",
+  "sender_id": "ou_088ee79216826be4a24af44f7268f880",
+  "sender": "李若松",
+  "timestamp": "Fri 2026-04-17 23:25 GMT+8"
+}
+```
+
+Sender (untrusted metadata):
+```json
+{
+  "label": "李若松 (ou_088ee79216826be4a24af44f7268f880)",
+  "id": "ou_088ee79216826be4a24af44f7268f880",
+  "name": "李若松"
+}
+```
+
+我给过你 mysql的用户名和密码啊   chatbot 账号
+assistant: 当前我没有找到保存的MySQL chatbot账号凭证，请你提供一下chatbot账号的密码，我会将连接信息保存在secrets.env中，后续查询就不需要再提供了。
+user: System: [2026-04-17 23:34:02 GMT+8] Feishu[xiaokui] DM | 李若松 (ou_088ee79216826be4a24af44f7268f880) [msg:om_x100b5111606c28a4b3c6b5b9d603411]
+
+Conversation info (untrusted metadata):
+```json
+{
+  "message_id": "om_x100b5111606c28a4b3c6b5b9d603411",
+  "sender_id": "ou_088ee79216826be4a24af44f7268f880",
+  "sender": "李若松",
+  "timestamp": "Fri 2026-04-17 23:34 GMT+8"
+}
+```
+
+Sender (untrusted metadata):
+```json
+{
+  "label": "李若松 (ou_088ee79216826be4a24af44f7268f880)",
+  "id": "ou_088ee79216826be4a24af44f7268f880",
+  "name": "李若松"
+}
+```
+
+user:chatbot
+pass:xhuBx7d@uT2gUVv
+assistant: 请提供一下MySQL数据库的主机地址（IP或域名），我来配置连接并查询数据。
+
+user: System: [2026-04-18 00:06:17 GMT+8] Feishu[xiaokui] DM | 李若松 (ou_088ee79216826be4a24af44f7268f880) [msg:om_x100b5111e9445d30b4b65bcfa860db5]
+
+Conversation info (untrusted metadata):
+```json
+{
+  "message_id": "om_x100b5111e9445d30b4b65bcfa860db5",
+  "sender_id": "ou_088ee79216826be4a24af44f7268f880",
+  "sender": "李若松",
+  "timestamp": "Sat 2026-04-18 00:06 GMT+8"
+}
+```
+
+Sender (untrusted metadata):
+```json
+{
+  "label": "李若松 (ou_088ee79216826be4a24af44f7268f880)",
+  "id": "ou_088ee79216826be4a24af44f7268f880",
+  "name": "李若松"
+}
+```
+
+MYSQL_HOST=bj-cdb-8frbdwju.sql.tencentcdb.com
+MYSQL_PORT=25413
+assistant: 飞书消息数据库目前共记录了 **175条** 群消息，最近一条消息的时间是 **2026-04-17 18:40:00**。
+user: System: [2026-04-18 00:09:06 GMT+8] Feishu[xiaokui] DM | 李若松 (ou_088ee79216826be4a24af44f7268f880) [msg:om_x100b5111fcd67ca0b4b587a67295205]
+
+Conversation info (untrusted metadata):
+```json
+{
+  "message_id": "om_x100b5111fcd67ca0b4b587a67295205",
+  "sender_id": "ou_088ee79216826be4a24af44f7268f880",
+  "sender": "李若松",
+  "timestamp": "Sat 2026-04-18 00:09 GMT+8"
+}
+```
+
+Sender (untrusted metadata):
+```json
+{
+  "label": "李若松 (ou_088ee79216826be4a24af44f7268f880)",
+  "id": "ou_088ee79216826be4a24af44f7268f880",
+  "name": "李若松"
+}
+```
+
+好 记住以上  test mysql 环境 的 访问凭证
+assistant: 已将test MySQL环境的访问凭证永久保存在本地secrets.env文件中，后续查询相关数据无需再提供配置信息。
diff --git a/memory/2026-04-17-request-timed-out-before-a-res.md b/memory/2026-04-17-request-timed-out-before-a-res.md
new file mode 100644
index 0000000..3b1750e
--- /dev/null
+++ b/memory/2026-04-17-request-timed-out-before-a-res.md
@@ -0,0 +1,60 @@
+# Session: 2026-04-17 16:14:21 UTC
+
+- **Session Key**: agent:xiaokui:feishu:direct:ou_088ee79216826be4a24af44f7268f880
+- **Session ID**: a3993289-1785-4f14-b91f-768a86c6560a
+- **Source**: feishu
+
+## Conversation Summary
+
+assistant: ✅ New session started · model: volcengine/doubao-seed-2-0-pro-260215
+user: System: [2026-04-18 00:11:03 GMT+8] Feishu[xiaokui] DM | 李若松 (ou_088ee79216826be4a24af44f7268f880) [msg:om_x100b5111f7b9b938b32dce6b4ab6d27]
+
+A new session was started via /new or /reset. Run your Session Startup sequence - read the required files before responding to the user. Then greet the user in your configured persona, if one is provided. Be yourself - use your defined voice, mannerisms, and mood. Keep it to 1-3 sentences and ask what they want to do. If the runtime model differs from default_model in the system prompt, mention the default model. Do not mention internal steps, files, tools, or reasoning.
+Current time: Saturday, April 18th, 2026 — 12:11 AM (Asia/Shanghai) / 2026-04-17 16:11 UTC
+assistant: Hi 若松，新会话已启动，请问你需要我处理什么任务？
+user: System: [2026-04-18 00:11:32 GMT+8] Feishu[xiaokui] DM | 李若松 (ou_088ee79216826be4a24af44f7268f880) [msg:om_x100b5111f5f2dc6cb2601197d6654cd]
+
+Conversation info (untrusted metadata):
+```json
+{
+  "message_id": "om_x100b5111f5f2dc6cb2601197d6654cd",
+  "sender_id": "ou_088ee79216826be4a24af44f7268f880",
+  "sender": "李若松",
+  "timestamp": "Sat 2026-04-18 00:11 GMT+8"
+}
+```
+
+Sender (untrusted metadata):
+```json
+{
+  "label": "李若松 (ou_088ee79216826be4a24af44f7268f880)",
+  "id": "ou_088ee79216826be4a24af44f7268f880",
+  "name": "李若松"
+}
+```
+
+查看一下   你的飞书反馈消息数据库中    记录了多少条消息  最近一条是什么时候
+assistant: 目前飞书反馈消息数据库中共记录了 **175条** 消息，最近一条的反馈时间为：**2026-04-17 18:40:00**（北京时间）。
+user: System: [2026-04-18 00:13:00 GMT+8] Feishu[xiaokui] DM | 李若松 (ou_088ee79216826be4a24af44f7268f880) [msg:om_x100b51118e9d94a0b4b5831c86bfa9a]
+
+Conversation info (untrusted metadata):
+```json
+{
+  "message_id": "om_x100b51118e9d94a0b4b5831c86bfa9a",
+  "sender_id": "ou_088ee79216826be4a24af44f7268f880",
+  "sender": "李若松",
+  "timestamp": "Sat 2026-04-18 00:12 GMT+8"
+}
+```
+
+Sender (untrusted metadata):
+```json
+{
+  "label": "李若松 (ou_088ee79216826be4a24af44f7268f880)",
+  "id": "ou_088ee79216826be4a24af44f7268f880",
+  "name": "李若松"
+}
+```
+
+飞书反馈消息数据库   默认指的就是  用户反馈技能中的   飞书  mysql 数据表
+assistant: 好的，已记录该术语共识，后续查询将默认使用该数据表。
diff --git a/memory/2026-04-17.md b/memory/2026-04-17.md
new file mode 100644
index 0000000..aaac9c0
--- /dev/null
+++ b/memory/2026-04-17.md
@@ -0,0 +1,22 @@
+# 2026-04-17 工作日志
+
+## 飞书群消息同步改造（李若松要求）
+
+### 变更内容
+- **存储从飞书表格改为 MySQL**：新建 `vala_test.lark_group_message` 表，结构参考 `wechat_group_message`
+- **同步频率**：从每6小时改为每4小时
+- **数据范围**：2026.4.1 起的「内容测试问题反馈」群消息
+- **数据库账户**：chatbot（test环境，仅对 lark_group_message 有写入权限）
+
+### 完成事项
+1. ✅ 创建 `lark_group_message` 表（唯一键 message_id 防重复）
+2. ✅ 编写新同步脚本 `scripts/sync_lark_group_to_mysql.py`（基于原有 sync_group_to_sheet.py 改造）
+3. ✅ 首次全量同步完成：172 条记录（2026-04-01 ~ 2026-04-17），含文本134条、图片17条、视频10条、富文本9条、表情2条
+4. ✅ crontab 定时任务已替换：旧的每6小时飞书表格同步 → 新的每4小时MySQL同步
+5. ✅ 更新 secrets.md 记录 chatbot 账户
+6. ✅ 更新 user-feedback-collector SKILL.md 反馈数据源信息
+
+### 文件变更
+- 新增：`scripts/sync_lark_group_to_mysql.py`（核心同步脚本）
+- 新增：`scripts/run_lark_group_sync.sh`（crontab 入口脚本）
+- 旧脚本保留：`scripts/sync_feedback_group.py`（飞书表格版本，已从crontab移除，可后续清理）
diff --git a/memory/2026-04-18.md b/memory/2026-04-18.md
new file mode 100644
index 0000000..20f220e
--- /dev/null
+++ b/memory/2026-04-18.md
@@ -0,0 +1,4 @@
+# 2026-04-18 工作日志
+
+## 术语共识
+[李若松确认] 术语「飞书反馈消息数据库」默认指代用户反馈收集技能中的飞书内部测试反馈MySQL数据表 `vala_test.lark_group_message`，存储「内容测试问题反馈」群（oc_fabff7672e62a9ced7b326ee4a286c26）的同步消息数据。
diff --git a/scripts/run_lark_group_sync.sh b/scripts/run_lark_group_sync.sh
new file mode 100755
index 0000000..d28a268
--- /dev/null
+++ b/scripts/run_lark_group_sync.sh
@@ -0,0 +1,10 @@
+#!/bin/bash
+# 飞书群消息同步到MySQL - 定时执行脚本
+# crontab: 每4小时执行一次
+# 0 */4 * * * /root/.openclaw/workspace-xiaokui/scripts/run_lark_group_sync.sh >> /var/log/lark_group_sync.log 2>&1
+
+export PATH="/root/.nvm/versions/node/v24.14.0/bin:$PATH"
+export LARK_SYNC_DB_PASS='xhuBx7d@uT2gUVv'
+
+cd /root/.openclaw/workspace-xiaokui
+python3 scripts/sync_lark_group_to_mysql.py
diff --git a/scripts/sync_feedback_minutely.sh b/scripts/sync_feedback_minutely.sh
new file mode 100755
index 0000000..d3e6a51
--- /dev/null
+++ b/scripts/sync_feedback_minutely.sh
@@ -0,0 +1,98 @@
+#!/bin/bash
+# 任务名称：飞书用户反馈每分钟同步（时间倒序，全量覆盖）
+# 执行时间：* * * * * 每分钟执行
+# 归属 Agent：小葵 xiaokui
+
+set +e
+
+# 环境配置
+export PATH=/root/.nvm/versions/node/v24.14.0/bin:$PATH
+LOG_FILE="/var/log/sync_feedback_minutely.log"
+WORKSPACE="/root/.openclaw/workspace-xiaokui"
+TMP_DATA="$WORKSPACE/tmp/all_feedback_sorted.json"
+
+# 源表格配置
+SOURCE_SPREADSHEET_TOKEN="E8vFsCmPBhT4SCtNmnJchqeJnJe"
+SOURCE_SHEET_ID="7bce8f"
+
+# 目标表格配置
+TARGET_SPREADSHEET_TOKEN="AOxbsifk3hybRZteGowcMxNnnqc"
+TARGET_SHEET_ID="f17380"
+
+log() {
+    echo "[$(date +'%Y-%m-%d %H:%M:%S')] $1" >> "$LOG_FILE"
+}
+
+log "=== 同步任务开始 ==="
+
+# 1. 读取源表格所有数据
+log "读取源表格数据..."
+SOURCE_RAW=$(LARKSUITE_CLI_CONFIG_DIR=/root/.openclaw/credentials/xiaoyan lark-cli sheets +read --spreadsheet-token "$SOURCE_SPREADSHEET_TOKEN" --range "$SOURCE_SHEET_ID!A:D" --as bot)
+SOURCE_DATA=$(echo "$SOURCE_RAW" | jq -r '.data.valueRange.values | .[1:] | map(select(.[0] != null and .[0] != ""))')
+
+if [ -z "$SOURCE_DATA" ] || [ "$SOURCE_DATA" == "null" ]; then
+    log "源表格无有效数据，退出"
+    exit 0
+fi
+
+# 2. 转换格式并按时间倒序排列
+SORTED_DATA=$(echo "$SOURCE_DATA" | jq '
+    sort_by(.[0]) | reverse | to_entries | map(
+        .key as $idx |
+        .value as $row |
+        {
+            id: ($idx + 1),
+            time: $row[0],
+            submitter: $row[1],
+            type: $row[2],
+            content: ($row[3] | if type == "array" then .[0].link else . end)
+        } |
+        [
+            (.id | tostring),
+            "",
+            "",
+            "",
+            .time,
+            "飞书群",
+            .submitter,
+            "",
+            "",
+            (if .type == "文本" then .content else "" end),
+            (if .type == "图片" then .content else "" end),
+            (if .type | test("视频") then .content else "" end),
+            "",
+            "待确认",
+            ""
+        ]
+    )')
+
+ROW_COUNT=$(echo "$SORTED_DATA" | jq length)
+log "共获取到 $ROW_COUNT 条反馈记录，按时间倒序排列完成"
+
+# 3. 清空目标表格原有数据（保留表头）
+log "清空目标表格原有数据..."
+EMPTY_DATA=$(printf '[]%.0s' {1..200} | jq -s '.')
+LARKSUITE_CLI_CONFIG_DIR=/root/.openclaw/credentials/xiaoyan lark-cli sheets +write \
+    --spreadsheet-token "$TARGET_SPREADSHEET_TOKEN" \
+    --range "$TARGET_SHEET_ID!A2:O201" \
+    --values "$EMPTY_DATA" \
+    --as bot >/dev/null 2>&1
+
+# 4. 写入排序后的数据
+echo "$SORTED_DATA" > "$TMP_DATA"
+END_ROW=$((ROW_COUNT + 1))
+
+log "写入数据到目标表格..."
+LARKSUITE_CLI_CONFIG_DIR=/root/.openclaw/credentials/xiaoyan lark-cli sheets +write \
+    --spreadsheet-token "$TARGET_SPREADSHEET_TOKEN" \
+    --range "$TARGET_SHEET_ID!A2:O$END_ROW" \
+    --values "$(cat $TMP_DATA)" \
+    --as bot
+
+log "✅ 同步完成，共写入 $ROW_COUNT 条记录，最新反馈已排在最上方"
+
+# 清理临时文件
+rm -f "$TMP_DATA"
+
+log "=== 同步任务完成 ==="
+exit 0
diff --git a/scripts/sync_lark_group_to_mysql.py b/scripts/sync_lark_group_to_mysql.py
new file mode 100644
index 0000000..f55c2be
--- /dev/null
+++ b/scripts/sync_lark_group_to_mysql.py
@@ -0,0 +1,355 @@
+#!/usr/bin/env python3
+"""
+飞书群聊消息同步到 MySQL (lark_group_message 表)
+- Bot身份拉取群消息（增量）
+- 非文本媒体上传到腾讯COS
+- 记录写入 MySQL vala_test.lark_group_message
+"""
+import os
+import sys
+import json
+import subprocess
+import logging
+import re
+import pymysql
+from datetime import datetime, timezone, timedelta
+from pathlib import Path
+
+# ============ 配置 ============
+
+# 飞书群
+CHAT_ID = "oc_fabff7672e62a9ced7b326ee4a286c26"
+CHAT_NAME = "内容测试问题反馈"
+
+# Bot凭证
+LARK_CLI_CONFIG = "/root/.openclaw/credentials/xiaokui"
+
+# 同步状态
+LAST_SYNC_FILE = "/root/.openclaw/workspace-xiaokui/data/last_lark_group_sync_time"
+WORK_DIR = "/tmp/lark_group_sync_workdir"
+
+# COS
+COS_BASE_PATH = "vala_llm/user_feedback"
+
+# MySQL（从环境变量或默认值）
+DB_HOST = os.environ.get("LARK_SYNC_DB_HOST", "bj-cdb-8frbdwju.sql.tencentcdb.com")
+DB_PORT = int(os.environ.get("LARK_SYNC_DB_PORT", "25413"))
+DB_USER = os.environ.get("LARK_SYNC_DB_USER", "chatbot")
+DB_PASS = os.environ.get("LARK_SYNC_DB_PASS", "")
+DB_NAME = os.environ.get("LARK_SYNC_DB_NAME", "vala_test")
+
+# 时区
+TZ = timezone(timedelta(hours=8))
+
+# ============ 配置结束 ============
+
+# 确保 lark-cli 在 PATH 中
+_NODE_BIN = "/root/.nvm/versions/node/v24.14.0/bin"
+if _NODE_BIN not in os.environ.get("PATH", ""):
+    os.environ["PATH"] = _NODE_BIN + ":" + os.environ.get("PATH", "")
+
+logging.basicConfig(level=logging.INFO, format='[%(asctime)s] %(message)s', datefmt='%Y-%m-%d %H:%M:%S')
+log = logging.getLogger(__name__)
+
+# 引入COS上传器
+sys.path.insert(0, '/root/.openclaw/workspace-xiaokui/skills/tencent-cos-upload/scripts')
+from cos_upload import CosUploader
+
+
+def get_db_connection():
+    """获取MySQL连接"""
+    return pymysql.connect(
+        host=DB_HOST,
+        port=DB_PORT,
+        user=DB_USER,
+        password=DB_PASS,
+        database=DB_NAME,
+        charset='utf8mb4',
+        cursorclass=pymysql.cursors.DictCursor,
+        autocommit=False
+    )
+
+
+def lark_cli(*args, cwd=None):
+    """调用lark-cli并返回解析后的JSON"""
+    env = os.environ.copy()
+    env['LARKSUITE_CLI_CONFIG_DIR'] = LARK_CLI_CONFIG
+    cmd = ['lark-cli'] + list(args)
+    result = subprocess.run(cmd, capture_output=True, text=True, env=env, cwd=cwd or WORK_DIR)
+    if result.returncode != 0 and not result.stdout:
+        log.error(f"lark-cli error: {result.stderr}")
+        return None
+    try:
+        return json.loads(result.stdout)
+    except json.JSONDecodeError:
+        log.error(f"lark-cli JSON parse error: {result.stdout[:200]}")
+        return None
+
+
+def fetch_messages(start_iso: str, end_iso: str) -> list:
+    """拉取群消息，支持分页"""
+    all_messages = []
+    page_token = None
+
+    while True:
+        args = [
+            'im', '+chat-messages-list',
+            '--chat-id', CHAT_ID,
+            '--start', start_iso,
+            '--end', end_iso,
+            '--sort', 'asc',
+            '--page-size', '50',
+            '--as', 'bot'
+        ]
+        if page_token:
+            args.extend(['--page-token', page_token])
+
+        result = lark_cli(*args)
+        if not result or not result.get('ok'):
+            err = result.get('error', {}).get('message', 'unknown') if result else 'no response'
+            log.error(f"拉取消息失败: {err}")
+            break
+
+        messages = result.get('data', {}).get('messages', [])
+        all_messages.extend(messages)
+
+        page_token = result.get('data', {}).get('page_token')
+        has_more = result.get('data', {}).get('has_more', False)
+        if not has_more or not page_token:
+            break
+
+    return all_messages
+
+
+def download_resource(msg_id: str, file_key: str, res_type: str, filename: str) -> str:
+    """下载飞书消息中的资源，返回本地路径"""
+    result = lark_cli(
+        'im', '+messages-resources-download',
+        '--message-id', msg_id,
+        '--file-key', file_key,
+        '--type', res_type,
+        '--output', filename,
+        '--as', 'bot',
+        cwd=WORK_DIR
+    )
+    local_path = os.path.join(WORK_DIR, filename)
+    if result and result.get('ok') and os.path.exists(local_path) and os.path.getsize(local_path) > 0:
+        return local_path
+    return None
+
+
+def extract_file_key(msg_type: str, content: str) -> tuple:
+    """从消息内容中提取file_key和资源类型"""
+    if msg_type == 'image':
+        match = re.search(r'img_[a-zA-Z0-9_-]+', content)
+        return (match.group(0), 'image') if match else (None, None)
+    elif msg_type in ('media', 'audio'):
+        match = re.search(r'file_[a-zA-Z0-9_-]+', content)
+        return (match.group(0), 'file') if match else (None, None)
+    elif msg_type == 'file':
+        try:
+            c = json.loads(content)
+            return (c.get('file_key'), 'file')
+        except Exception:
+            match = re.search(r'file_[a-zA-Z0-9_-]+', content)
+            return (match.group(0), 'file') if match else (None, None)
+    return None, None
+
+
+def get_media_info(msg_type: str, content: str) -> tuple:
+    """返回 (cos子目录, 文件扩展名, content_type)"""
+    if msg_type == 'image':
+        return 'image', '.png', 'image/png'
+    elif msg_type == 'media':
+        name_match = re.search(r'name="([^"]*)"', content)
+        ext = os.path.splitext(name_match.group(1))[1] if name_match else '.mp4'
+        return 'video', ext or '.mp4', 'video/mp4'
+    elif msg_type == 'audio':
+        return 'audio', '.ogg', 'audio/ogg'
+    elif msg_type == 'file':
+        try:
+            c = json.loads(content)
+            ext = os.path.splitext(c.get('file_name', ''))[1]
+        except Exception:
+            ext = ''
+        return 'file', ext or '.bin', 'application/octet-stream'
+    return 'other', '', 'application/octet-stream'
+
+
+def process_message(msg: dict, cos_uploader, date_str: str) -> dict:
+    """
+    处理单条消息，返回字典用于插入数据库，或 None（跳过）
+    """
+    msg_id = msg.get('message_id', '')
+    sender = msg.get('sender', {})
+    sender_id = sender.get('id', '')
+    sender_name = sender.get('name', '未知')
+    create_time_str = msg.get('create_time', '')
+    msg_type = msg.get('msg_type', '')
+    content_raw = msg.get('content', '')
+    deleted = msg.get('deleted', False)
+
+    if deleted or msg_type == 'system':
+        return None
+
+    # 解析消息时间
+    try:
+        # create_time 可能是毫秒时间戳字符串或ISO格式
+        if create_time_str.isdigit():
+            ts_ms = int(create_time_str)
+            msg_dt = datetime.fromtimestamp(ts_ms / 1000, tz=TZ)
+        else:
+            msg_dt = datetime.fromisoformat(create_time_str)
+            ts_ms = int(msg_dt.timestamp() * 1000)
+    except Exception:
+        msg_dt = datetime.now(TZ)
+        ts_ms = int(msg_dt.timestamp() * 1000)
+
+    record = {
+        'chat_id': CHAT_ID,
+        'chat_name': CHAT_NAME,
+        'sender_id': sender_id,
+        'sender_name': sender_name,
+        'message_id': msg_id,
+        'msg_type': msg_type,
+        'content': None,
+        'media_url': None,
+        'msg_time': msg_dt.strftime('%Y-%m-%d %H:%M:%S'),
+        'msg_timestamp': ts_ms,
+    }
+
+    # 文本消息
+    if msg_type in ('text', 'post'):
+        text = re.sub(r'<[^>]*>', '', content_raw).strip()
+        record['content'] = text
+        return record
+
+    # 表情包
+    if msg_type == 'sticker':
+        record['content'] = '（表情包）'
+        return record
+
+    # 媒体消息
+    cos_subdir, ext, content_type = get_media_info(msg_type, content_raw)
+    file_key, res_type = extract_file_key(msg_type, content_raw)
+
+    if not file_key:
+        record['content'] = f'（无法提取资源key）'
+        return record
+
+    short_id = msg_id[-12:]
+    if msg_type == 'media':
+        name_match = re.search(r'name="([^"]*)"', content_raw)
+        orig_ext = os.path.splitext(name_match.group(1))[1] if name_match else ext
+        filename = f'{short_id}{orig_ext or ext}'
+    elif msg_type == 'file':
+        try:
+            c = json.loads(content_raw)
+            orig_ext = os.path.splitext(c.get('file_name', ''))[1]
+        except Exception:
+            orig_ext = ext
+        filename = f'{short_id}{orig_ext or ext}'
+    else:
+        filename = f'{short_id}{ext}'
+
+    cos_key = f'{COS_BASE_PATH}/{cos_subdir}/{date_str}/{filename}'
+
+    # 下载
+    local_path = download_resource(msg_id, file_key, res_type, filename)
+    if not local_path:
+        log.warning(f"资源下载失败: {msg_id} ({msg_type})")
+        record['content'] = '（下载失败）'
+        return record
+
+    # 上传COS
+    try:
+        url = cos_uploader.upload(local_path, cos_key, content_type)
+        log.info(f"COS上传成功: {cos_key}")
+        record['media_url'] = url
+    except Exception as e:
+        log.error(f"COS上传失败: {cos_key} - {e}")
+        record['content'] = '（上传失败）'
+    finally:
+        try:
+            os.remove(local_path)
+        except Exception:
+            pass
+
+    return record
+
+
+def insert_records(conn, records: list):
+    """批量插入记录到MySQL，使用 INSERT IGNORE 避免重复"""
+    if not records:
+        return 0
+
+    sql = """
+    INSERT IGNORE INTO lark_group_message
+        (chat_id, chat_name, sender_id, sender_name, message_id, msg_type, content, media_url, msg_time, msg_timestamp)
+    VALUES
+        (%(chat_id)s, %(chat_name)s, %(sender_id)s, %(sender_name)s, %(message_id)s,
+         %(msg_type)s, %(content)s, %(media_url)s, %(msg_time)s, %(msg_timestamp)s)
+    """
+    inserted = 0
+    with conn.cursor() as cursor:
+        for record in records:
+            cursor.execute(sql, record)
+            inserted += cursor.rowcount
+    conn.commit()
+    return inserted
+
+
+def main():
+    os.makedirs(WORK_DIR, exist_ok=True)
+    os.makedirs(os.path.dirname(LAST_SYNC_FILE), exist_ok=True)
+
+    # 读取上次同步时间
+    if os.path.exists(LAST_SYNC_FILE):
+        with open(LAST_SYNC_FILE) as f:
+            last_sync_iso = f.read().strip()
+    else:
+        # 首次运行：从 2026-04-01 开始
+        last_sync_iso = "2026-04-01T00:00:00+08:00"
+
+    current_iso = datetime.now(TZ).isoformat()
+    log.info(f"开始同步: {last_sync_iso} -> {current_iso}")
+
+    # 拉取消息
+    messages = fetch_messages(last_sync_iso, current_iso)
+    if not messages:
+        log.info("没有新消息，同步结束")
+        with open(LAST_SYNC_FILE, 'w') as f:
+            f.write(current_iso)
+        return
+
+    log.info(f"发现 {len(messages)} 条新消息")
+
+    # 初始化COS
+    cos_uploader = CosUploader()
+    date_str = datetime.now(TZ).strftime('%Y-%m-%d')
+
+    # 处理消息
+    records = []
+    for msg in messages:
+        record = process_message(msg, cos_uploader, date_str)
+        if record:
+            records.append(record)
+
+    # 写入MySQL
+    if records:
+        conn = get_db_connection()
+        try:
+            inserted = insert_records(conn, records)
+            log.info(f"同步完成: 处理 {len(records)} 条, 新增 {inserted} 条 (重复跳过 {len(records) - inserted} 条)")
+        finally:
+            conn.close()
+    else:
+        log.info("无有效消息需要写入")
+
+    # 更新同步时间
+    with open(LAST_SYNC_FILE, 'w') as f:
+        f.write(current_iso)
+
+
+if __name__ == '__main__':
+    main()
diff --git a/scripts/sync_wechat_feedback_minutely.py b/scripts/sync_wechat_feedback_minutely.py
new file mode 100644
index 0000000..de53076
--- /dev/null
+++ b/scripts/sync_wechat_feedback_minutely.py
@@ -0,0 +1,219 @@
+#!/usr/bin/env python3
+"""
+微信用户反馈每分钟同步到飞书收集表格
+"""
+import os
+import json
+import pymysql
+import subprocess
+from datetime import datetime
+
+# 配置
+LOG_FILE = "/var/log/sync_wechat_feedback.log"
+LAST_SYNC_ID_FILE = "/root/.openclaw/workspace-xiaokui/data/last_wechat_sync_id"
+TARGET_SPREADSHEET_TOKEN = "AOxbsifk3hybRZteGowcMxNnnqc"
+TARGET_SHEET_ID = "f17380"
+LARK_CLI_CONFIG = "/root/.openclaw/credentials/xiaoyan"
+
+# 数据库配置
+DB_CONFIG = {
+    "host": "bj-cdb-8frbdwju.sql.tencentcdb.com",
+    "port": 25413,
+    "user": "read_only",
+    "password": "fdsfiidier^$*hjfdijjd232",
+    "database": "vala_test",
+    "charset": "utf8mb4"
+}
+
+def log(message):
+    """写日志"""
+    timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+    with open(LOG_FILE, "a", encoding="utf-8") as f:
+        f.write(f"[{timestamp}] {message}\n")
+    print(f"[{timestamp}] {message}")
+
+def get_last_sync_id():
+    """获取上次同步的最大ID"""
+    if not os.path.exists(LAST_SYNC_ID_FILE):
+        return 0
+    with open(LAST_SYNC_ID_FILE, "r") as f:
+        return int(f.read().strip())
+
+def save_last_sync_id(last_id):
+    """保存上次同步的最大ID"""
+    with open(LAST_SYNC_ID_FILE, "w") as f:
+        f.write(str(last_id))
+
+def fetch_new_wechat_data(last_id):
+    """从MySQL读取新增的微信反馈数据"""
+    conn = pymysql.connect(**DB_CONFIG)
+    cursor = conn.cursor()
+    sql = """
+    SELECT id, msg_time, sender_name, msg_type, content 
+    FROM wechat_group_message 
+    WHERE id > %s 
+    ORDER BY msg_time DESC
+    """
+    cursor.execute(sql, (last_id,))
+    rows = cursor.fetchall()
+    cursor.close()
+    conn.close()
+    return rows
+
+def convert_to_sheet_format(rows):
+    """转换为飞书表格需要的格式"""
+    sheet_rows = []
+    max_id = 0
+    for row in rows:
+        id, msg_time, sender_name, msg_type, content = row
+        if id > max_id:
+            max_id = id
+            
+        # 整理反馈内容
+        if msg_type == "text":
+            feedback_content = content
+        elif msg_type == "image":
+            feedback_content = f"[图片] {content}"
+        elif msg_type == "video":
+            feedback_content = f"[视频] {content}"
+        else:
+            feedback_content = f"[{msg_type}] {content}"
+        
+        # 清理特殊字符
+        feedback_content = feedback_content.replace("\n", " ").replace("\r", "").replace('"', '\\"')
+        
+        sheet_rows.append([
+            "", # A 序号后续统一生成
+            "微信-用户火线救火", # B 反馈渠道
+            msg_time.strftime("%Y-%m-%d %H:%M:%S"), # C 反馈时间
+            sender_name, # D 反馈人
+            feedback_content, # E 反馈内容
+            "", # F 备注 留空
+            ""  # G 回复 留空
+        ])
+    return sheet_rows, max_id
+
+def get_existing_sheet_data():
+    """读取目标表格现有数据"""
+    cmd = [
+        "lark-cli", "sheets", "+read",
+        "--spreadsheet-token", TARGET_SPREADSHEET_TOKEN,
+        "--range", f"{TARGET_SHEET_ID}!A2:O",
+        "--as", "bot"
+    ]
+    env = os.environ.copy()
+    env["LARKSUITE_CLI_CONFIG_DIR"] = LARK_CLI_CONFIG
+    env["PATH"] = "/root/.nvm/versions/node/v24.14.0/bin:" + env.get("PATH", "")
+    
+    result = subprocess.run(cmd, env=env, capture_output=True, text=True)
+    if result.returncode != 0:
+        log(f"读取表格失败: {result.stderr}")
+        return []
+    
+    try:
+        data = json.loads(result.stdout)
+        values = data.get("data", {}).get("valueRange", {}).get("values", [])
+        # 过滤空行
+        valid_values = [row for row in values if row and len(row) >= 1 and row[0] and row[0].strip()]
+        return valid_values
+    except Exception as e:
+        log(f"解析表格数据失败: {str(e)}")
+        return []
+
+def merge_and_sort_data(new_rows, existing_rows):
+    """合并新老数据，按时间倒序排列，重新生成序号，去重"""
+    seen = set()
+    all_rows = []
+    
+    # 合并新老数据
+    for row in new_rows + existing_rows:
+        if not row or len(row) < 5:
+            continue
+        # 去重：时间+反馈人+内容
+        key = f'{row[2]}_{row[3]}_{row[4]}'
+        if key in seen:
+            continue
+        seen.add(key)
+        all_rows.append(row)
+    
+    # 按反馈时间倒序排列
+    all_rows.sort(key=lambda x: x[2], reverse=True)
+    # 重新生成序号
+    for i, row in enumerate(all_rows):
+        row[0] = str(i + 1)
+    return all_rows
+
+def write_to_sheet(all_rows):
+    """写入数据到飞书表格"""
+    if not all_rows:
+        log("无数据需要写入")
+        return
+    
+    # 清空原有数据
+    empty_data = [["" for _ in range(15)] for _ in range(200)]
+    cmd_clear = [
+        "lark-cli", "sheets", "+write",
+        "--spreadsheet-token", TARGET_SPREADSHEET_TOKEN,
+        "--range", f"{TARGET_SHEET_ID}!A2:O201",
+        "--values", json.dumps(empty_data, ensure_ascii=False),
+        "--as", "bot"
+    ]
+    env = os.environ.copy()
+    env["LARKSUITE_CLI_CONFIG_DIR"] = LARK_CLI_CONFIG
+    env["PATH"] = "/root/.nvm/versions/node/v24.14.0/bin:" + env.get("PATH", "")
+    
+    subprocess.run(cmd_clear, env=env, capture_output=True)
+    
+    # 写入新数据
+    end_row = len(all_rows) + 1
+    cmd_write = [
+        "lark-cli", "sheets", "+write",
+        "--spreadsheet-token", TARGET_SPREADSHEET_TOKEN,
+        "--range", f"{TARGET_SHEET_ID}!A2:O{end_row}",
+        "--values", json.dumps(all_rows, ensure_ascii=False),
+        "--as", "bot"
+    ]
+    
+    result = subprocess.run(cmd_write, env=env, capture_output=True, text=True)
+    if result.returncode != 0:
+        log(f"写入表格失败: {result.stderr}")
+        return False
+    return True
+
+def main():
+    log("=== 微信反馈同步任务开始 ===")
+    last_sync_id = get_last_sync_id()
+    log(f"上次同步最大ID: {last_sync_id}")
+    
+    # 获取新数据
+    new_rows = fetch_new_wechat_data(last_sync_id)
+    if not new_rows:
+        log("无新增微信反馈数据，退出")
+        return
+    
+    new_count = len(new_rows)
+    log(f"发现 {new_count} 条新增微信反馈数据")
+    
+    # 转换格式
+    sheet_rows, new_max_id = convert_to_sheet_format(new_rows)
+    
+    # 获取现有数据
+    existing_rows = get_existing_sheet_data()
+    log(f"现有表格数据量: {len(existing_rows)} 条")
+    
+    # 合并排序
+    all_rows = merge_and_sort_data(sheet_rows, existing_rows)
+    log(f"合并后总数据量: {len(all_rows)} 条")
+    
+    # 写入表格
+    success = write_to_sheet(all_rows)
+    if success:
+        save_last_sync_id(new_max_id)
+        log(f"✅ 同步完成，新增 {new_count} 条，总 {len(all_rows)} 条，已按时间倒序排列")
+    else:
+        log("❌ 同步失败")
+    
+    log("=== 同步任务完成 ===")
+
+if __name__ == "__main__":
+    main()
diff --git a/scripts/sync_wechat_feedback_minutely.sh b/scripts/sync_wechat_feedback_minutely.sh
new file mode 100755
index 0000000..3bfce25
--- /dev/null
+++ b/scripts/sync_wechat_feedback_minutely.sh
@@ -0,0 +1,145 @@
+#!/bin/bash
+# 任务名称：微信用户反馈每分钟同步到收集表格
+# 执行时间：* * * * * 每分钟执行
+# 归属 Agent：小葵 xiaokui
+
+set +e
+
+# 环境配置
+export PATH=/root/.nvm/versions/node/v24.14.0/bin:$PATH
+LOG_FILE="/var/log/sync_wechat_feedback.log"
+WORKSPACE="/root/.openclaw/workspace-xiaokui"
+LAST_SYNC_ID_FILE="$WORKSPACE/data/last_wechat_sync_id"
+TMP_DATA="$WORKSPACE/tmp/wechat_feedback.json"
+
+# 数据库配置
+DB_HOST="bj-cdb-8frbdwju.sql.tencentcdb.com"
+DB_PORT="25413"
+DB_USER="read_only"
+DB_PASS="fdsfiidier^\$*hjfdijjd232"
+DB_NAME="vala_test"
+
+# 目标表格配置
+TARGET_SPREADSHEET_TOKEN="AOxbsifk3hybRZteGowcMxNnnqc"
+TARGET_SHEET_ID="f17380"
+
+log() {
+    echo "[$(date +'%Y-%m-%d %H:%M:%S')] $1" >> "$LOG_FILE"
+}
+
+# 初始化上次同步ID
+if [ ! -f "$LAST_SYNC_ID_FILE" ]; then
+    echo "0" > "$LAST_SYNC_ID_FILE"
+fi
+LAST_SYNC_ID=$(cat "$LAST_SYNC_ID_FILE")
+
+log "=== 微信反馈同步任务开始 ==="
+log "上次同步最大ID：$LAST_SYNC_ID"
+
+# 1. 读取微信新增反馈数据
+log "读取微信新增反馈数据..."
+mysql -h "$DB_HOST" -P "$DB_PORT" -u "$DB_USER" -p"$DB_PASS" "$DB_NAME" -N -e "
+SELECT id, msg_time, sender_name, msg_type, content 
+FROM wechat_group_message 
+WHERE id > $LAST_SYNC_ID 
+ORDER BY msg_time DESC;" > /tmp/wechat_raw.txt
+
+if [ ! -s /tmp/wechat_raw.txt ]; then
+    log "无新增微信反馈数据，退出"
+    exit 0
+fi
+
+# 2. 转换为表格格式
+log "转换数据格式..."
+NEW_DATA=$(awk '
+BEGIN {
+    print "["
+    first = 1
+}
+{
+    if (first == 0) print ","
+    first = 0
+    
+    id = $1
+    time = $2 " " $3
+    sender = $4
+    type = $5
+    content = substr($0, index($0,$6))
+    
+    # 处理字段
+    text = ""
+    image = ""
+    video = ""
+    if (type == "text") {
+        text = content
+    } else if (type == "image") {
+        image = content
+    } else if (type == "video") {
+        video = content
+    } else {
+        text = "[" type "] " content
+    }
+    
+    gsub(/"/, "\\\"", text)
+    gsub(/"/, "\\\"", image)
+    gsub(/"/, "\\\"", video)
+    
+    printf "[\"\", \"\", \"\", \"\", \"%s\", \"微信\", \"%s\", \"\", \"\", \"%s\", \"%s\", \"%s\", \"\", \"待确认\", \"\"]", time, sender, text, image, video
+}
+END {
+    print "\n]"
+}' /tmp/wechat_raw.txt)
+
+NEW_COUNT=$(echo "$NEW_DATA" | jq length)
+NEW_MAX_ID=$(tail -1 /tmp/wechat_raw.txt | awk '{print $1}')
+log "发现 $NEW_COUNT 条新增微信反馈数据，最大ID：$NEW_MAX_ID"
+
+# 3. 读取目标表格现有数据（飞书+微信）
+log "读取目标表格现有数据..."
+TARGET_RAW=$(LARKSUITE_CLI_CONFIG_DIR=/root/.openclaw/credentials/xiaoyan lark-cli sheets +read --spreadsheet-token "$TARGET_SPREADSHEET_TOKEN" --range "$TARGET_SHEET_ID!A2:O" --as bot)
+TARGET_DATA=$(echo "$TARGET_RAW" | jq '.data.valueRange.values | map(select(.[0] != null and .[0] != ""))')
+
+if [ "$TARGET_DATA" == "null" ] || [ -z "$TARGET_DATA" ]; then
+    TARGET_DATA="[]"
+fi
+
+# 4. 合并数据并按时间倒序排列
+echo "$NEW_DATA" > /tmp/new.json
+echo "$TARGET_DATA" > /tmp/existing.json
+
+ALL_DATA=$(jq -s 'add | sort_by(.[4]) | reverse' /tmp/new.json /tmp/existing.json)
+
+# 5. 重新生成序号
+ALL_DATA=$(echo "$ALL_DATA" | jq 'to_entries | map(.value[0] = (.key + 1 | tostring) | .value)')
+
+echo "$ALL_DATA" > "$TMP_DATA"
+ROW_COUNT=$(echo "$ALL_DATA" | jq length)
+END_ROW=$((ROW_COUNT + 1))
+
+# 6. 清空目标表格并写入合并后的数据
+log "写入合并后的数据，共 $ROW_COUNT 条..."
+# 先清空原有数据
+EMPTY_DATA=$(printf '[]%.0s' {1..200} | jq -s '.')
+LARKSUITE_CLI_CONFIG_DIR=/root/.openclaw/credentials/xiaoyan lark-cli sheets +write \
+    --spreadsheet-token "$TARGET_SPREADSHEET_TOKEN" \
+    --range "$TARGET_SHEET_ID!A2:O201" \
+    --values "$EMPTY_DATA" \
+    --as bot >/dev/null 2>&1
+
+# 写入新数据
+LARKSUITE_CLI_CONFIG_DIR=/root/.openclaw/credentials/xiaoyan lark-cli sheets +write \
+    --spreadsheet-token "$TARGET_SPREADSHEET_TOKEN" \
+    --range "$TARGET_SHEET_ID!A2:O$END_ROW" \
+    --values "$(cat $TMP_DATA)" \
+    --as bot
+
+# 7. 更新上次同步ID
+echo "$NEW_MAX_ID" > "$LAST_SYNC_ID_FILE"
+
+log "✅ 同步完成：新增 $NEW_COUNT 条微信反馈，当前总记录数 $ROW_COUNT 条，已按时间倒序排列"
+
+# 清理临时文件
+rm -f /tmp/wechat_raw.txt /tmp/new.json /tmp/existing.json "$TMP_DATA"
+
+log "=== 同步任务完成 ==="
+exit 0
diff --git a/skills/user-feedback-collector/SKILL.md b/skills/user-feedback-collector/SKILL.md
index c5be7dd..8479518 100644
--- a/skills/user-feedback-collector/SKILL.md
+++ b/skills/user-feedback-collector/SKILL.md
@@ -48,7 +48,7 @@ description: |
 | 反馈渠道 | 来源 | 存储位置 | 更新频率 |
 |---------|------|----------|----------|
 | 主动上报 | 用户主动发送 `用户反馈:` 前缀消息 | 飞书知识库文档 | 实时 |
-| 飞书内部测试反馈 | 「内容测试问题反馈」群（`oc_fabff7672e62a9ced7b326ee4a286c26`） | 飞书表格：`E8vFsCmPBhT4SCtNmnJchqeJnJe` | 每6小时自动同步 |
+| 飞书内部测试反馈 | 「内容测试问题反馈」群（`oc_fabff7672e62a9ced7b326ee4a286c26`） | MySQL：`vala_test.lark_group_message` 表 | 每4小时自动同步 |
 | 微信用户反馈 | 微信用户反馈群 | MySQL：`vala_test.wechat_group_message` 表 | 实时更新 |
 
 ## 目标存储位置