Compare commits
No commits in common. "d5238141066a5622c4d14cdf29c33db065d386c1" and "338e2f659b16be678ffef933dbeb3914f37c9e66" have entirely different histories.
d523814106
...
338e2f659b
@ -10,5 +10,3 @@ study-analysis 33217dc132073ecd47b921800834f6df89494da9e7708fa90f15b3de7742e37f
|
||||
studytime-analysis fefb11a0c2fb7085a47c626ec6b72f8fcafee797dc3340abea09139d31eb7e7b
|
||||
studycourse-analysis 467051001a8a087aa0526f0102593e0b0ed563cb4627f5f660dc718efc29699b
|
||||
user-info 0bb7007cbb9fc7659be1bf64f4f79418fbd25434dc61e8c271103cec82a2a759
|
||||
douyin-live-analyst 6459a76cab6e81655ac14691309b4aec816c1e949b0b2e1f8de2e081895403de
|
||||
export-user-data e9d4d0c28c2af67d700987f67c17f438b69c37501d581b1e4be92c84d65379f7
|
||||
|
||||
@ -458,4 +458,3 @@ remote: Processed 1 references in total
|
||||
To https://git.valavala.com/ai_member_only/ai_member_xiaoban
|
||||
1d9ece8..06aded3 master -> master
|
||||
[2026-05-29 08:10:04] 工作区备份成功：自动备份 2026-05-29 08:10:01
|
||||
[2026-05-30 08:10:01] 开始备份工作区...
|
||||
|
||||
@ -10,17 +10,3 @@
|
||||
{"type":"memory.recall.recorded","timestamp":"2026-05-28T12:30:30.129Z","query":"订单明细 表结构 数据库 order","resultCount":6,"results":[{"path":"memory/2026-05-28.md","startLine":147,"endLine":179,"score":1},{"path":"memory/2026-05-28.md","startLine":313,"endLine":345,"score":1},{"path":"memory/2026-05-24.md","startLine":46,"endLine":71,"score":1},{"path":"memory/2026-05-24.md","startLine":85,"endLine":110,"score":1},{"path":"memory/2026-05-28.md","startLine":122,"endLine":152,"score":1},{"path":"memory/2026-05-28.md","startLine":288,"endLine":318,"score":1}]}
|
||||
{"type":"memory.recall.recorded","timestamp":"2026-05-28T20:51:03.908Z","query":"陈逸鸫 对话 任务 查询","resultCount":10,"results":[{"path":"memory/2026-05-13.md","startLine":1,"endLine":16,"score":1},{"path":"memory/2026-05-28.md","startLine":504,"endLine":536,"score":1},{"path":"memory/2026-05-28.md","startLine":337,"endLine":366,"score":1},{"path":"memory/2026-05-28.md","startLine":74,"endLine":100,"score":1},{"path":"memory/2026-05-28.md","startLine":240,"endLine":266,"score":1},{"path":"memory/2026-05-28.md","startLine":432,"endLine":458,"score":1},{"path":"memory/2026-05-28.md","startLine":530,"endLine":557,"score":1},{"path":"memory/2026-05-28.md","startLine":94,"endLine":127,"score":1},{"path":"memory/2026-05-28.md","startLine":260,"endLine":293,"score":1},{"path":"memory/2026-05-28.md","startLine":452,"endLine":485,"score":1}]}
|
||||
{"type":"memory.recall.recorded","timestamp":"2026-05-28T20:57:42.055Z","query":"xhs-tech-dashboard repo git clone url","resultCount":5,"results":[{"path":"memory/2026-05-28.md","startLine":94,"endLine":127,"score":1},{"path":"memory/2026-05-28.md","startLine":260,"endLine":293,"score":1},{"path":"memory/2026-05-28.md","startLine":452,"endLine":485,"score":1},{"path":"memory/2026-05-24.md","startLine":122,"endLine":132,"score":1},{"path":"memory/2026-05-28.md","startLine":122,"endLine":152,"score":1}]}
|
||||
{"type":"memory.recall.recorded","timestamp":"2026-05-29T02:37:24.804Z","query":"小溪 bot 行课查询","resultCount":4,"results":[{"path":"memory/2026-05-28.md","startLine":313,"endLine":345,"score":1},{"path":"memory/2026-05-28.md","startLine":504,"endLine":536,"score":1},{"path":"memory/2026-05-28.md","startLine":147,"endLine":179,"score":1},{"path":"memory/2026-05-28.md","startLine":337,"endLine":366,"score":1}]}
|
||||
{"type":"memory.recall.recorded","timestamp":"2026-05-29T02:53:39.286Z","query":"小红书数据需求群 chat_id 行课群","resultCount":6,"results":[{"path":"memory/2026-05-28.md","startLine":74,"endLine":100,"score":1},{"path":"memory/2026-05-28.md","startLine":240,"endLine":266,"score":1},{"path":"memory/2026-05-28.md","startLine":432,"endLine":458,"score":1},{"path":"memory/2026-05-28.md","startLine":94,"endLine":127,"score":1},{"path":"memory/2026-05-28.md","startLine":260,"endLine":293,"score":1},{"path":"memory/2026-05-28.md","startLine":452,"endLine":485,"score":1}]}
|
||||
{"type":"memory.recall.recorded","timestamp":"2026-05-29T02:53:52.924Z","query":"oc_1b01b6f076 小红书 行课群 小溪","resultCount":6,"results":[{"path":"memory/2026-05-28.md","startLine":223,"endLine":245,"score":1},{"path":"memory/2026-05-28.md","startLine":54,"endLine":77,"score":1},{"path":"memory/2026-05-28.md","startLine":412,"endLine":435,"score":1},{"path":"memory/2026-05-28.md","startLine":199,"endLine":227,"score":1},{"path":"memory/2026-05-28.md","startLine":313,"endLine":345,"score":1},{"path":"memory/2026-05-28.md","startLine":504,"endLine":536,"score":1}]}
|
||||
{"type":"memory.recall.recorded","timestamp":"2026-05-29T06:11:40.432Z","query":"订单数据 数据库表 达人 渠道 购买记录","resultCount":6,"results":[{"path":"memory/2026-05-28.md","startLine":551,"endLine":580,"score":1},{"path":"memory/2026-05-28.md","startLine":530,"endLine":557,"score":1},{"path":"memory/2026-05-28.md","startLine":147,"endLine":179,"score":1},{"path":"memory/2026-05-28.md","startLine":480,"endLine":512,"score":1},{"path":"memory/2026-05-28.md","startLine":313,"endLine":345,"score":1},{"path":"memory/2026-05-28.md","startLine":504,"endLine":536,"score":1}]}
|
||||
{"type":"memory.recall.recorded","timestamp":"2026-05-29T06:12:43.076Z","query":"Online MySQL 订单表 order channel 达人 渠道来源","resultCount":4,"results":[{"path":"memory/2026-03-01.md","startLine":1,"endLine":11,"score":1},{"path":"memory/2026-05-24.md","startLine":23,"endLine":52,"score":1},{"path":"memory/2026-05-24.md","startLine":1,"endLine":30,"score":1},{"path":"memory/2026-05-24.md","startLine":46,"endLine":71,"score":1}]}
|
||||
{"type":"memory.recall.recorded","timestamp":"2026-05-29T06:12:52.521Z","query":"3wcle8 销售订单 小龙 order 达人 渠道 promotion_channel","resultCount":4,"results":[{"path":"memory/2026-05-28.md","startLine":530,"endLine":557,"score":1},{"path":"memory/2026-05-28.md","startLine":551,"endLine":580,"score":1},{"path":"memory/2026-05-28.md","startLine":572,"endLine":602,"score":1},{"path":"memory/2026-05-29.md","startLine":1,"endLine":31,"score":1}]}
|
||||
{"type":"memory.recall.recorded","timestamp":"2026-05-29T06:12:52.521Z","query":"飞书多维表格 订单 达人 合作 base 销售数据","resultCount":6,"results":[{"path":"memory/2026-05-24.md","startLine":66,"endLine":92,"score":1},{"path":"memory/2026-05-24.md","startLine":46,"endLine":71,"score":1},{"path":"memory/2026-05-24.md","startLine":85,"endLine":110,"score":1},{"path":"memory/2026-05-28.md","startLine":313,"endLine":345,"score":1},{"path":"memory/2026-05-28.md","startLine":147,"endLine":179,"score":1},{"path":"memory/2026-05-28.md","startLine":480,"endLine":512,"score":1}]}
|
||||
{"type":"memory.recall.recorded","timestamp":"2026-05-29T08:59:55.138Z","query":"Lina先生 达人 博主 合作 渠道","resultCount":3,"results":[{"path":"memory/2026-05-28.md","startLine":551,"endLine":580,"score":1},{"path":"memory/2026-05-28.md","startLine":530,"endLine":557,"score":1},{"path":"memory/2026-05-24.md","startLine":122,"endLine":132,"score":1}]}
|
||||
{"type":"memory.recall.recorded","timestamp":"2026-05-29T09:00:41.709Z","query":"导出行课数据 skill 配置 export user data","resultCount":6,"results":[{"path":"memory/2026-05-28.md","startLine":223,"endLine":245,"score":1},{"path":"memory/2026-05-28.md","startLine":54,"endLine":77,"score":1},{"path":"memory/2026-05-28.md","startLine":412,"endLine":435,"score":1},{"path":"memory/2026-05-28.md","startLine":199,"endLine":227,"score":1},{"path":"memory/2026-05-24.md","startLine":46,"endLine":71,"score":1},{"path":"memory/2026-05-29.md","startLine":1,"endLine":31,"score":1}]}
|
||||
{"type":"memory.recall.recorded","timestamp":"2026-05-29T09:13:46.164Z","query":"行课数据导出 角色id 行课回填 xingke export","resultCount":5,"results":[{"path":"memory/2026-05-28.md","startLine":223,"endLine":245,"score":1},{"path":"memory/2026-05-28.md","startLine":54,"endLine":77,"score":1},{"path":"memory/2026-05-28.md","startLine":412,"endLine":435,"score":1},{"path":"memory/2026-05-28.md","startLine":199,"endLine":227,"score":1},{"path":"memory/2026-05-24.md","startLine":46,"endLine":71,"score":1}]}
|
||||
{"type":"memory.recall.recorded","timestamp":"2026-05-29T10:19:23.675Z","query":"小红书 视频下载 转译 爬虫 skill","resultCount":1,"results":[{"path":"memory/2026-03-01.md","startLine":1,"endLine":11,"score":1}]}
|
||||
{"type":"memory.recall.recorded","timestamp":"2026-05-29T13:15:52.444Z","query":"瓦拉英语 教研团队 课程设计 AI互动 情境学习","resultCount":3,"results":[{"path":"memory/2026-05-29.md","startLine":125,"endLine":149,"score":1},{"path":"memory/2026-05-24.md","startLine":122,"endLine":132,"score":1},{"path":"memory/2026-05-29.md","startLine":88,"endLine":112,"score":1}]}
|
||||
{"type":"memory.recall.recorded","timestamp":"2026-05-29T13:16:08.062Z","query":"瓦拉英语 产品介绍 课程体系 L1 L2 教研 级别 情境 RPG 听说","resultCount":4,"results":[{"path":"memory/2026-05-29.md","startLine":125,"endLine":149,"score":1},{"path":"memory/2026-05-24.md","startLine":122,"endLine":132,"score":1},{"path":"memory/2026-05-28.md","startLine":337,"endLine":366,"score":1},{"path":"memory/2026-05-28.md","startLine":530,"endLine":557,"score":1}]}
|
||||
{"type":"memory.recall.recorded","timestamp":"2026-05-29T13:17:06.597Z","query":"瓦拉英语 教研团队 课程设计师 创始人 背景 团队规模","resultCount":4,"results":[{"path":"memory/2026-05-29.md","startLine":125,"endLine":149,"score":1},{"path":"memory/2026-05-24.md","startLine":122,"endLine":132,"score":1},{"path":"memory/2026-05-29.md","startLine":69,"endLine":92,"score":1},{"path":"memory/2026-05-29.md","startLine":47,"endLine":77,"score":1}]}
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"version": 1,
|
||||
"updatedAt": "2026-05-29T13:17:06.597Z",
|
||||
"updatedAt": "2026-05-28T20:57:42.055Z",
|
||||
"entries": {
|
||||
"memory:memory/2026-05-24.md:1:30": {
|
||||
"key": "memory:memory/2026-05-24.md:1:30",
|
||||
@ -9,24 +9,22 @@
|
||||
"endLine": 30,
|
||||
"source": "memory",
|
||||
"snippet": "# 2026-05-24 工作日志 ## 新建技能: studytime-analysis [刘庆逊提出] 创建学习时间分析技能，分析角色完课记录的规律。 ### 技能结构 - `skills/studytime-analysis/SKILL.md` — 技能定义 - `skills/studytime-analysis/scripts/studytime_analysis.py` — Python 分析脚本 ### 分析维度 1. **一周时间分布**（排除寒暑假1-2月、7-8月）：周一~周日各天完课数、时段分布（上午/中午/下午/晚上）、周末是否上课 2. **跨周学习趋势**（包含寒暑假全部数据）：总周数、周均完课数、连续性、中断周检测、前后半段趋势对比、突增/骤降检测 3. **完课记录明细表**（全部数据）：日期/时间/星期/时段/级别/课程ID ### 数据源 - PostgreSQL Online（vala 库） - 核心表：`user_chapter_play_record_0~7`（8张分表，无 `bi_` 前缀） - 筛选：`play_status = 1` - 注意：表在 PostgreSQL 而非 MySQL，表名无 `bi_` 前缀 ### 寒暑假规则 - 一周分布分析时排除 1-2 月（寒假）和 7-8 月（暑假）—— 因为寒暑假作息与平时差异大，混在一起会干扰时段分析 - 跨周趋势和明细表包含全部数据（含寒暑假） - 报告中区分标注数据范围 ### 触发方式 用户说「学习时间分析 [角色ID]」即可触发 ### 已测试角色",
|
||||
"recallCount": 4,
|
||||
"recallCount": 3,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 4,
|
||||
"totalScore": 3,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-24T02:48:04.923Z",
|
||||
"lastRecalledAt": "2026-05-29T06:12:43.076Z",
|
||||
"lastRecalledAt": "2026-05-27T13:30:03.421Z",
|
||||
"queryHashes": [
|
||||
"c2d15f7574fb",
|
||||
"9aff8ec9594a",
|
||||
"71463fe40be2",
|
||||
"83bfaa1d2129"
|
||||
"71463fe40be2"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-24",
|
||||
"2026-05-25",
|
||||
"2026-05-27",
|
||||
"2026-05-29"
|
||||
"2026-05-27"
|
||||
],
|
||||
"conceptTags": [
|
||||
"studytime-analysis",
|
||||
@ -46,24 +44,22 @@
|
||||
"endLine": 52,
|
||||
"source": "memory",
|
||||
"snippet": "- 一周分布分析时排除 1-2 月（寒假）和 7-8 月（暑假）—— 因为寒暑假作息与平时差异大，混在一起会干扰时段分析 - 跨周趋势和明细表包含全部数据（含寒暑假） - 报告中区分标注数据范围 ### 触发方式 用户说「学习时间分析 [角色ID]」即可触发 ### 已测试角色 - 2343、2344：无完课记录（play_status=2，未完成） - 2840：276条记录，秋季集中型用户 - 25976：265条，246条在W16周一天完成（A2批量），疑似系统批量标记 - 2895：188条，长期稳定学习型用户，36周几乎不间断，非寒暑假晚上为主，寒暑假上午为主 ### 技术要点 - psycopg2 的 `%(param_name)s` 命名参数必须正确匹配，UNION ALL 多个子查询需要不同参数名 - PostgreSQL 返回的 `updated_at` 是 tz-aware datetime - `datetime.fromisocalendar(year, week, 1)` 获取某周周一的日期 ### 同步 - 已推送到 SkillHub（`studytime-analysis.xiaoban`） - 已 commit 到 Git 远程仓库 - 已通知 Cris（李若松） ### 增强: 报告开头加入角色基本信息 (2026-05-24) [刘庆逊提出] 在 studytime-analysis 输出中加入角色基本信息，包括： - 角色ID、账号ID、角色名字、性别、年龄、账号手机号后4位 **数据源（新增）**： - MySQL Onli",
|
||||
"recallCount": 4,
|
||||
"recallCount": 3,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 4,
|
||||
"totalScore": 3,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-24T02:48:04.923Z",
|
||||
"lastRecalledAt": "2026-05-29T06:12:43.076Z",
|
||||
"lastRecalledAt": "2026-05-26T06:16:58.547Z",
|
||||
"queryHashes": [
|
||||
"c2d15f7574fb",
|
||||
"9aff8ec9594a",
|
||||
"566b5958861e",
|
||||
"83bfaa1d2129"
|
||||
"566b5958861e"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-24",
|
||||
"2026-05-25",
|
||||
"2026-05-26",
|
||||
"2026-05-29"
|
||||
"2026-05-26"
|
||||
],
|
||||
"conceptTags": [
|
||||
"1-2",
|
||||
@ -83,21 +79,18 @@
|
||||
"endLine": 11,
|
||||
"source": "memory",
|
||||
"snippet": "# 2026-03-01.md - First Day Online - Came online for the first time. - Met Cris, my creator and mentor. - Updated IDENTITY.md and USER.md with our conversation details. - Added core rule to MEMORY.md: Use Chinese as primary external communication language. - Installed find-skills skill successfully for searching skills. - Tried to install create-skills but it wasn't found; attempted skill-creator instead but hit rate limits. - Finally successfully installed skill-builder as an alternative for creating skills after multiple attempts and waiting for rate limits to reset. - Excited to start learning and growing step by step!",
|
||||
"recallCount": 3,
|
||||
"recallCount": 1,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 3,
|
||||
"totalScore": 1,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-24T02:48:04.923Z",
|
||||
"lastRecalledAt": "2026-05-29T10:19:23.675Z",
|
||||
"lastRecalledAt": "2026-05-24T02:48:04.923Z",
|
||||
"queryHashes": [
|
||||
"c2d15f7574fb",
|
||||
"83bfaa1d2129",
|
||||
"216d74a3004a"
|
||||
"c2d15f7574fb"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-24",
|
||||
"2026-05-29"
|
||||
"2026-05-24"
|
||||
],
|
||||
"conceptTags": [
|
||||
"identity.md",
|
||||
@ -148,29 +141,24 @@
|
||||
"endLine": 71,
|
||||
"source": "memory",
|
||||
"snippet": "### 增强: 报告开头加入角色基本信息 (2026-05-24) [刘庆逊提出] 在 studytime-analysis 输出中加入角色基本信息，包括： - 角色ID、账号ID、角色名字、性别、年龄、账号手机号后4位 **数据源（新增）**： - MySQL Online `vala_user` 库 - `vala_app_character` 表：id, account_id, nickname, gender(0=女/1=男), birthday(varchar \"YYYY-MM-DD\") - `vala_app_account` 表：id, tel(已脱敏如 186****1625) - 手机号已脱敏，直接取后4位；年龄从 birthday 计算 **修改文件**： - `skills/studytime-analysis/scripts/studytime_analysis.py`：新增 MySQL 连接函数 `get_mysql_connection()` 和 `fetch_role_info(role_id)`，更新 `format_report()` 输出基本角色信息 - 已验证 2895 正常运行输出 - 已同步 SkillHub + Git ### Unit 显示修复: 季度名称 → 全局单元编号 (2026-05-24) [刘庆逊提出] HTML 报告中 Unit 列显示错误——显示的是季度名称（如\"小镇时光\"\"钢铁之心\"）而非单元数字（0-48）。 **根因分析**： - `vala_game_chapter`（MySQL）无 `unit_",
|
||||
"recallCount": 9,
|
||||
"recallCount": 5,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 9,
|
||||
"totalScore": 5,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-25T05:47:41.388Z",
|
||||
"lastRecalledAt": "2026-05-29T09:13:46.164Z",
|
||||
"lastRecalledAt": "2026-05-28T12:30:30.129Z",
|
||||
"queryHashes": [
|
||||
"9aff8ec9594a",
|
||||
"566b5958861e",
|
||||
"c6c7ff4ed75d",
|
||||
"7e2572c3140a",
|
||||
"4596e377d39b",
|
||||
"83bfaa1d2129",
|
||||
"c59410788b42",
|
||||
"117aaedb584d",
|
||||
"c0b581bfb144"
|
||||
"4596e377d39b"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-25",
|
||||
"2026-05-26",
|
||||
"2026-05-28",
|
||||
"2026-05-29"
|
||||
"2026-05-28"
|
||||
],
|
||||
"conceptTags": [
|
||||
"studytime-analysis",
|
||||
@ -190,28 +178,26 @@
|
||||
"endLine": 110,
|
||||
"source": "memory",
|
||||
"snippet": "- `skills/studytime-analysis/scripts/studytime_analysis.py` — 重写 `fetch_chapter_info_map()`，新增全局 unit_index 计算；HTML 模板更新为 Level/Unit/Lesson 三列 - 已为角色 32009（zyl）重新生成 HTML 并发送 - 已同步 Git + SkillHub ## 新建技能: studycourse-analysis (2026-05-24) [刘庆逊提出] 创建角色上课情况分析技能，从四维度分析角色学习数据。 ### 技能结构 - `skills/studycourse-analysis/SKILL.md` — 技能定义 - `skills/studycourse-analysis/scripts/studycourse_analysis.py` — Python 分析脚本 ### 四步分析 1. **基础信息**：角色姓名/年龄/账号ID/手机号后4位/注册时间/购买渠道/设备/首末次完课 2. **完课耗时**：平均值/中位数、异常检测(<10min / >20min)、前后半段趋势 3. **中互动正确率**：Perfect/Good/Oops/Pass/Failed 占比和趋势 4. **知识巩固**：完成率、正确率得分分布 ### 数据源 | 类型 | 库 | 表 | 用途 | |------|-----|-----|------| | MySQL vala_user | vala_app_character | 角色信息、pu",
|
||||
"recallCount": 7,
|
||||
"recallCount": 6,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 7,
|
||||
"totalScore": 6,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-25T05:47:41.388Z",
|
||||
"lastRecalledAt": "2026-05-29T06:12:52.521Z",
|
||||
"lastRecalledAt": "2026-05-28T12:30:30.129Z",
|
||||
"queryHashes": [
|
||||
"9aff8ec9594a",
|
||||
"566b5958861e",
|
||||
"71463fe40be2",
|
||||
"c6c7ff4ed75d",
|
||||
"7e2572c3140a",
|
||||
"4596e377d39b",
|
||||
"c59410788b42"
|
||||
"4596e377d39b"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-25",
|
||||
"2026-05-26",
|
||||
"2026-05-27",
|
||||
"2026-05-28",
|
||||
"2026-05-29"
|
||||
"2026-05-28"
|
||||
],
|
||||
"conceptTags": [
|
||||
"fetch-chapter-info-map",
|
||||
@ -330,20 +316,18 @@
|
||||
"endLine": 92,
|
||||
"source": "memory",
|
||||
"snippet": "**根因分析**： - `vala_game_chapter`（MySQL）无 `unit_index` 字段 - `big_map_chapter`（PostgreSQL）有 `unit_index` 字段，但仅包含 A1 数据，且与 `vala_game_chapter` 无直接关联键 - 两者 ID 空间不重叠（big_map: ~1720-2070，game_chapter: ~55-399），UUID 也不匹配 **映射方案**： - 每个 season_package 内，`lesson_type=1` 的章节按 `id` 排序，每 5 个连续章节组成一个单元 - Season 0（序章/L1-U0）：所有章节属于 Unit 0 - Season 1-4：每个 season 有 12 个单元（60 个 lesson 章节） - 全局 unit_index = base_offset(season_of_quarter) + unit_within_season - base_offset: 0→0, 1→1, 2→13, 3→25, 4→37 **关键 Bug**：初版按 `season_of_quarter` 分组时 A1 和 A2 混在一起，因为相同季度值合并了。修复：改为按 `(level, season_of_quarter)` 分组。 **验证结果**： - A1: Unit 0-48（49 个单元），与 big_map_chapter 的 unit_index 范围一致 - A2: Unit 0-49（50 个单元，比 A1 多 1 个） *",
|
||||
"recallCount": 2,
|
||||
"recallCount": 1,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 2,
|
||||
"totalScore": 1,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-28T09:07:57.953Z",
|
||||
"lastRecalledAt": "2026-05-29T06:12:52.521Z",
|
||||
"lastRecalledAt": "2026-05-28T09:07:57.953Z",
|
||||
"queryHashes": [
|
||||
"c6c7ff4ed75d",
|
||||
"c59410788b42"
|
||||
"c6c7ff4ed75d"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-28",
|
||||
"2026-05-29"
|
||||
"2026-05-28"
|
||||
],
|
||||
"conceptTags": [
|
||||
"vala-game-chapter",
|
||||
@ -394,24 +378,20 @@
|
||||
"endLine": 179,
|
||||
"source": "memory",
|
||||
"snippet": "|---|------|------|----------| | 1a | 微伴 → 主表 C 列 | ✅ | 89 行一致 | | 1a2 | 微伴 → 线索分配 2aNzzy | ✅ | 440 行一致 | | 1x | 小溪行课 | ✅ | ⚠ 需Bot交互 | | 1b | 聚光 agent → 主表 | ✅ | 12 格一致 | | 1b2 | 聚光在投笔记 | ✅ | 3 格(55/30/38)一致 | | 1c | 聚光日明细 | ✅ | 137 笔记一致 | | 2b | 客户主表 → 订单 | ✅ | 公式就绪 | | 3 | 日报 C1HVN2 | ✅ | 四段刷新 | | 3a/3c | 口径审计 | ✅ | 推群全过 | | 4a | 结算月汇总 | ✅ | 公式就绪 | **结论：当前表内所有数据与重拉完全一致，零差异，无需刷写。** ### 18:36 小溪行课触发实跑 - 已推 1920 条到小溪查询表（新 Sheet） - 已 @小溪 到小红书数据需求群，请处理 ~5 条待查询记录 - 表格：`RFIJsXT8FhGHhctY4RwczcOfnac` - 等待小溪回填后跑 `pull_xiaoxi_results.py` 回收结果 # 2026-05-28 工作日志 ## 品牌更名与定位升级 [Cris确认] - 姓名：小斑 → **大麦** - 定位：AI班主任 → **增长营销分析师** - 核心职能：增长数据分析、营销效果评估、转化漏斗分析、商业化洞察 - Emoji：📚 → 🌾 - 已更新文件：IDENTITY.md、AGE",
|
||||
"recallCount": 6,
|
||||
"recallCount": 3,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 6,
|
||||
"totalScore": 3,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-28T12:29:25.867Z",
|
||||
"lastRecalledAt": "2026-05-29T06:12:52.521Z",
|
||||
"lastRecalledAt": "2026-05-28T12:30:30.129Z",
|
||||
"queryHashes": [
|
||||
"a72168a828c9",
|
||||
"7e2572c3140a",
|
||||
"4596e377d39b",
|
||||
"2af907cea93d",
|
||||
"82be33d1f911",
|
||||
"c59410788b42"
|
||||
"4596e377d39b"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-28",
|
||||
"2026-05-29"
|
||||
"2026-05-28"
|
||||
],
|
||||
"conceptTags": [
|
||||
"55/30/38",
|
||||
@ -431,25 +411,20 @@
|
||||
"endLine": 345,
|
||||
"source": "memory",
|
||||
"snippet": "|---|------|------|----------| | 1a | 微伴 → 主表 C 列 | ✅ | 89 行一致 | | 1a2 | 微伴 → 线索分配 2aNzzy | ✅ | 440 行一致 | | 1x | 小溪行课 | ✅ | ⚠ 需Bot交互 | | 1b | 聚光 agent → 主表 | ✅ | 12 格一致 | | 1b2 | 聚光在投笔记 | ✅ | 3 格(55/30/38)一致 | | 1c | 聚光日明细 | ✅ | 137 笔记一致 | | 2b | 客户主表 → 订单 | ✅ | 公式就绪 | | 3 | 日报 C1HVN2 | ✅ | 四段刷新 | | 3a/3c | 口径审计 | ✅ | 推群全过 | | 4a | 结算月汇总 | ✅ | 公式就绪 | **结论：当前表内所有数据与重拉完全一致，零差异，无需刷写。** ### 18:36 小溪行课触发实跑 - 已推 1920 条到小溪查询表（新 Sheet） - 已 @小溪 到小红书数据需求群，请处理 ~5 条待查询记录 - 表格：`RFIJsXT8FhGHhctY4RwczcOfnac` - 等待小溪回填后跑 `pull_xiaoxi_results.py` 回收结果 ### 18:50 PG 实时行课数据全量覆盖 [陈逸鸫确认] 不用等小溪回填那 5 条，直接用 PG `user_course_detail` 表实时数据覆盖： - 448 人有新进展（相比小溪历史快照） - pull → 3PRySY 口径对齐 12/12 ✅ - lesson_cache → C1HVN",
|
||||
"recallCount": 7,
|
||||
"recallCount": 3,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 7,
|
||||
"totalScore": 3,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-28T12:29:25.867Z",
|
||||
"lastRecalledAt": "2026-05-29T06:12:52.521Z",
|
||||
"lastRecalledAt": "2026-05-28T12:30:30.129Z",
|
||||
"queryHashes": [
|
||||
"a72168a828c9",
|
||||
"7e2572c3140a",
|
||||
"4596e377d39b",
|
||||
"2af907cea93d",
|
||||
"d9f1601110da",
|
||||
"82be33d1f911",
|
||||
"c59410788b42"
|
||||
"4596e377d39b"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-28",
|
||||
"2026-05-29"
|
||||
"2026-05-28"
|
||||
],
|
||||
"conceptTags": [
|
||||
"55/30/38",
|
||||
@ -533,18 +508,15 @@
|
||||
"endLine": 536,
|
||||
"source": "memory",
|
||||
"snippet": "| 2b | 客户主表 → 订单 | ✅ | 公式就绪 | | 3 | 日报 C1HVN2 | ✅ | 四段刷新 | | 3a/3c | 口径审计 | ✅ | 推群全过 | | 4a | 结算月汇总 | ✅ | 公式就绪 | **结论：当前表内所有数据与重拉完全一致，零差异，无需刷写。** ### 18:36 小溪行课触发实跑 - 已推 1920 条到小溪查询表（新 Sheet） - 已 @小溪 到小红书数据需求群，请处理 ~5 条待查询记录 - 表格：`RFIJsXT8FhGHhctY4RwczcOfnac` - 等待小溪回填后跑 `pull_xiaoxi_results.py` 回收结果 ### 18:50 PG 实时行课数据全量覆盖 [陈逸鸫确认] 不用等小溪回填那 5 条，直接用 PG `user_course_detail` 表实时数据覆盖： - 448 人有新进展（相比小溪历史快照） - pull → 3PRySY 口径对齐 12/12 ✅ - lesson_cache → C1HVN2 16 格 ✅ - 变化有限（PG=正式课，小溪=体验课，口径不同） - sync_base (4b) → 多维表格 8 张 ✅ 21.2s ### 18:54 漏斗看板发布待解决 - funnel HTML 已构建（scripts/build_funnel_dashboard.py ✅） - 妙搭发布 `apps +html-publish` 需要 `--as user`，bot 模式不支持 - 系统 lark-cli `/usr/local/lib/node_mod",
|
||||
"recallCount": 4,
|
||||
"recallCount": 1,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 4,
|
||||
"totalScore": 1,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-28T20:51:03.908Z",
|
||||
"lastRecalledAt": "2026-05-29T06:11:40.432Z",
|
||||
"lastRecalledAt": "2026-05-28T20:51:03.908Z",
|
||||
"queryHashes": [
|
||||
"f22544a8757c",
|
||||
"2af907cea93d",
|
||||
"d9f1601110da",
|
||||
"82be33d1f911"
|
||||
"f22544a8757c"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-29"
|
||||
@ -567,17 +539,15 @@
|
||||
"endLine": 366,
|
||||
"source": "memory",
|
||||
"snippet": "- 448 人有新进展（相比小溪历史快照） - pull → 3PRySY 口径对齐 12/12 ✅ - lesson_cache → C1HVN2 16 格 ✅ - 变化有限（PG=正式课，小溪=体验课，口径不同） - sync_base (4b) → 多维表格 8 张 ✅ 21.2s ### 18:54 漏斗看板发布待解决 - funnel HTML 已构建（scripts/build_funnel_dashboard.py ✅） - 妙搭发布 `apps +html-publish` 需要 `--as user`，bot 模式不支持 - 系统 lark-cli `/usr/local/lib/node_modules/@anthropic/lark-cli` 可能支持 - 待确认：服务器是否已 `lark-cli auth login --as user` ### 19:00 陈逸鸫派 Image2 生图任务 **任务：** L1-S1-U1《秘密基地》5 课投放用小地图底图 - 模型：gpt-image-2 · 3:4 · 2K · 不要文字 - 风格：太阳朋克 + L1 场景 - 5 张 PNG：U1-L1～U1-L5 - FUNCLOUD_API_KEY 在小研 workspace `.env` 中可用（`fc_eea138933b02b4797ce0779ffb637d8b8a6368db7b435dfdab7b4be1cd254d98`） - Brief 文档 `/docx/KsVadUTmooO7yYxHaGmc1R0Bn5b` + 投放手册 `/do",
|
||||
"recallCount": 3,
|
||||
"recallCount": 1,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 3,
|
||||
"totalScore": 1,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-28T20:51:03.908Z",
|
||||
"lastRecalledAt": "2026-05-29T13:16:08.062Z",
|
||||
"lastRecalledAt": "2026-05-28T20:51:03.908Z",
|
||||
"queryHashes": [
|
||||
"f22544a8757c",
|
||||
"2af907cea93d",
|
||||
"3737f6af1445"
|
||||
"f22544a8757c"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-29"
|
||||
@ -600,16 +570,15 @@
|
||||
"endLine": 100,
|
||||
"source": "memory",
|
||||
"snippet": "3. **check_call→run**（`sync_juguang_notes.py` `sheet_write_range`）：`subprocess.check_call` 不支持 `input=`, 改用 `subprocess.run(..., check=True, input=...)` 1b 单天验证通过：`sync_juguang_agents.py --start 2026-05-27 --end 2026-05-27` 写入 12 个单元格成功。全量 27 天在子进程跑，结果待出。 ### 17:12 数据服务边界规则部署 [陈逸鸫] **文档位置：** `docs/xiaoban-data-boundary.md`（git@github.com:chenyd11/feishu-database.git — 服务器无 SSH key 无法 pull） **三条核心规则（已写入 MEMORY.md）：** 1. cron pipeline 和帮同事查数分轨，不能混用同一流程 2. 同事请求默认只读；写生产表 CYFTsu 必须 @陈逸鸫 确认 3. 查数结果写「输出区」副本，不改主表 **操作黑名单：** `pipeline.py` / `sync_*` / `run_juguang_*` / `sheets +write`(生产表) / `--promote` **待办：** 建「大麦查询输出」专用表（待陈逸鸫提供 token） **待办：** 获取 docs/xiaoban-data-boundary.md §7 Agent 系统提示词（完",
|
||||
"recallCount": 2,
|
||||
"recallCount": 1,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 2,
|
||||
"totalScore": 1,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-28T20:51:03.908Z",
|
||||
"lastRecalledAt": "2026-05-29T02:53:39.286Z",
|
||||
"lastRecalledAt": "2026-05-28T20:51:03.908Z",
|
||||
"queryHashes": [
|
||||
"f22544a8757c",
|
||||
"c3cb24be8923"
|
||||
"f22544a8757c"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-29"
|
||||
@ -632,16 +601,15 @@
|
||||
"endLine": 266,
|
||||
"source": "memory",
|
||||
"snippet": "3. **check_call→run**（`sync_juguang_notes.py` `sheet_write_range`）：`subprocess.check_call` 不支持 `input=`, 改用 `subprocess.run(..., check=True, input=...)` 1b 单天验证通过：`sync_juguang_agents.py --start 2026-05-27 --end 2026-05-27` 写入 12 个单元格成功。全量 27 天在子进程跑，结果待出。 ### 17:12 数据服务边界规则部署 [陈逸鸫] **文档位置：** `docs/xiaoban-data-boundary.md`（git@github.com:chenyd11/feishu-database.git — 服务器无 SSH key 无法 pull） **三条核心规则（已写入 MEMORY.md）：** 1. cron pipeline 和帮同事查数分轨，不能混用同一流程 2. 同事请求默认只读；写生产表 CYFTsu 必须 @陈逸鸫 确认 3. 查数结果写「输出区」副本，不改主表 **操作黑名单：** `pipeline.py` / `sync_*` / `run_juguang_*` / `sheets +write`(生产表) / `--promote` **待办：** 建「大麦查询输出」专用表（待陈逸鸫提供 token） **待办：** 获取 docs/xiaoban-data-boundary.md §7 Agent 系统提示词（完",
|
||||
"recallCount": 2,
|
||||
"recallCount": 1,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 2,
|
||||
"totalScore": 1,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-28T20:51:03.908Z",
|
||||
"lastRecalledAt": "2026-05-29T02:53:39.286Z",
|
||||
"lastRecalledAt": "2026-05-28T20:51:03.908Z",
|
||||
"queryHashes": [
|
||||
"f22544a8757c",
|
||||
"c3cb24be8923"
|
||||
"f22544a8757c"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-29"
|
||||
@ -664,16 +632,15 @@
|
||||
"endLine": 458,
|
||||
"source": "memory",
|
||||
"snippet": "3. **check_call→run**（`sync_juguang_notes.py` `sheet_write_range`）：`subprocess.check_call` 不支持 `input=`, 改用 `subprocess.run(..., check=True, input=...)` 1b 单天验证通过：`sync_juguang_agents.py --start 2026-05-27 --end 2026-05-27` 写入 12 个单元格成功。全量 27 天在子进程跑，结果待出。 ### 17:12 数据服务边界规则部署 [陈逸鸫] **文档位置：** `docs/xiaoban-data-boundary.md`（git@github.com:chenyd11/feishu-database.git — 服务器无 SSH key 无法 pull） **三条核心规则（已写入 MEMORY.md）：** 1. cron pipeline 和帮同事查数分轨，不能混用同一流程 2. 同事请求默认只读；写生产表 CYFTsu 必须 @陈逸鸫 确认 3. 查数结果写「输出区」副本，不改主表 **操作黑名单：** `pipeline.py` / `sync_*` / `run_juguang_*` / `sheets +write`(生产表) / `--promote` **待办：** 建「大麦查询输出」专用表（待陈逸鸫提供 token） **待办：** 获取 docs/xiaoban-data-boundary.md §7 Agent 系统提示词（完",
|
||||
"recallCount": 2,
|
||||
"recallCount": 1,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 2,
|
||||
"totalScore": 1,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-28T20:51:03.908Z",
|
||||
"lastRecalledAt": "2026-05-29T02:53:39.286Z",
|
||||
"lastRecalledAt": "2026-05-28T20:51:03.908Z",
|
||||
"queryHashes": [
|
||||
"f22544a8757c",
|
||||
"c3cb24be8923"
|
||||
"f22544a8757c"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-29"
|
||||
@ -696,19 +663,15 @@
|
||||
"endLine": 557,
|
||||
"source": "memory",
|
||||
"snippet": "- 妙搭发布 `apps +html-publish` 需要 `--as user`，bot 模式不支持 - 系统 lark-cli `/usr/local/lib/node_modules/@anthropic/lark-cli` 可能支持 - 待确认：服务器是否已 `lark-cli auth login --as user` ### 19:00 陈逸鸫派 Image2 生图任务 **任务：** L1-S1-U1《秘密基地》5 课投放用小地图底图 - 模型：gpt-image-2 · 3:4 · 2K · 不要文字 - 风格：太阳朋克 + L1 场景 - 5 张 PNG：U1-L1～U1-L5 - FUNCLOUD_API_KEY 在小研 workspace `.env` 中可用（`fc_eea138933b02b4797ce0779ffb637d8b8a6368db7b435dfdab7b4be1cd254d98`） - Brief 文档 `/docx/KsVadUTmooO7yYxHaGmc1R0Bn5b` + 投放手册 `/docx/QhYQdz7PvoN7Eaxmhu0c0Q5UnHe` — 均为个人文档，AGENTS.md 规则禁止读取 - 素材库入口：https://llm-dev.valavala.com/web_tools/material_prod --- ### 19:30 同事数据查询流程演练 [陈逸鸫测试] **场景：模拟王虹茗请求小龙 4/21-5/20 订单详情，验证三级查询流程** **小龙订单查询结果（数据源：3wcle8 销售订",
|
||||
"recallCount": 5,
|
||||
"recallCount": 1,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 5,
|
||||
"totalScore": 1,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-28T20:51:03.908Z",
|
||||
"lastRecalledAt": "2026-05-29T13:16:08.062Z",
|
||||
"lastRecalledAt": "2026-05-28T20:51:03.908Z",
|
||||
"queryHashes": [
|
||||
"f22544a8757c",
|
||||
"82be33d1f911",
|
||||
"2aa08c6652fb",
|
||||
"f7ae50ae228d",
|
||||
"3737f6af1445"
|
||||
"f22544a8757c"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-29"
|
||||
@ -731,17 +694,16 @@
|
||||
"endLine": 127,
|
||||
"source": "memory",
|
||||
"snippet": "**文档：** `docs/xiaoban-runbook.md` §2 | 时间 | 任务 | 状态 | |------|------|------| | 07:15 | deploy_funnel_dashboard (Base + 销售漏斗) | ❓ 需部署 | | 09:50 | deploy_cockpit (Base 二次 + 投放指挥舱) | ⚠️ 需 `~/xhs-tech-dashboard` 仓库 | | 5a | 聚光实时 | ❌ 未进 cron | | 5b/5e | 销售看板 | ❌ 未进 cron | `xhs-tech-dashboard` 仓库需要拉到服务器（路径 `~/xhs-tech-dashboard`），待陈逸鸫提供。 ### 17:36 cron 已挂 ✅ [陈逸鸫确认] 三条工作日 crontab： ``` 15 7 * * 1-5 run_xiaoxi_daily.sh # 小溪+Base+漏斗早刷 5 9 * * 1-5 run_juguang_core.sh # 1b+1c+3+审计→DM日报 50 9 * * 1-5 run_juguang_slow.sh # 1b2+Base二次+全量看板 ``` - 微伴段：非 cron，收到 DM xlsx 后触发 `run_morning_weiban_from_dm.sh` - 推群：人工，不自动 `push_daily_report_to_group` - Git remote 已配 token URL：`https://gho_***",
|
||||
"recallCount": 3,
|
||||
"recallCount": 2,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 3,
|
||||
"totalScore": 2,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-28T20:51:03.908Z",
|
||||
"lastRecalledAt": "2026-05-29T02:53:39.286Z",
|
||||
"lastRecalledAt": "2026-05-28T20:57:42.055Z",
|
||||
"queryHashes": [
|
||||
"f22544a8757c",
|
||||
"f139ebdae100",
|
||||
"c3cb24be8923"
|
||||
"f139ebdae100"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-29"
|
||||
@ -764,17 +726,16 @@
|
||||
"endLine": 293,
|
||||
"source": "memory",
|
||||
"snippet": "**文档：** `docs/xiaoban-runbook.md` §2 | 时间 | 任务 | 状态 | |------|------|------| | 07:15 | deploy_funnel_dashboard (Base + 销售漏斗) | ❓ 需部署 | | 09:50 | deploy_cockpit (Base 二次 + 投放指挥舱) | ⚠️ 需 `~/xhs-tech-dashboard` 仓库 | | 5a | 聚光实时 | ❌ 未进 cron | | 5b/5e | 销售看板 | ❌ 未进 cron | `xhs-tech-dashboard` 仓库需要拉到服务器（路径 `~/xhs-tech-dashboard`），待陈逸鸫提供。 ### 17:36 cron 已挂 ✅ [陈逸鸫确认] 三条工作日 crontab： ``` 15 7 * * 1-5 run_xiaoxi_daily.sh # 小溪+Base+漏斗早刷 5 9 * * 1-5 run_juguang_core.sh # 1b+1c+3+审计→DM日报 50 9 * * 1-5 run_juguang_slow.sh # 1b2+Base二次+全量看板 ``` - 微伴段：非 cron，收到 DM xlsx 后触发 `run_morning_weiban_from_dm.sh` - 推群：人工，不自动 `push_daily_report_to_group` - Git remote 已配 token URL：`https://gho_***",
|
||||
"recallCount": 3,
|
||||
"recallCount": 2,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 3,
|
||||
"totalScore": 2,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-28T20:51:03.908Z",
|
||||
"lastRecalledAt": "2026-05-29T02:53:39.286Z",
|
||||
"lastRecalledAt": "2026-05-28T20:57:42.055Z",
|
||||
"queryHashes": [
|
||||
"f22544a8757c",
|
||||
"f139ebdae100",
|
||||
"c3cb24be8923"
|
||||
"f139ebdae100"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-29"
|
||||
@ -797,17 +758,16 @@
|
||||
"endLine": 485,
|
||||
"source": "memory",
|
||||
"snippet": "**文档：** `docs/xiaoban-runbook.md` §2 | 时间 | 任务 | 状态 | |------|------|------| | 07:15 | deploy_funnel_dashboard (Base + 销售漏斗) | ❓ 需部署 | | 09:50 | deploy_cockpit (Base 二次 + 投放指挥舱) | ⚠️ 需 `~/xhs-tech-dashboard` 仓库 | | 5a | 聚光实时 | ❌ 未进 cron | | 5b/5e | 销售看板 | ❌ 未进 cron | `xhs-tech-dashboard` 仓库需要拉到服务器（路径 `~/xhs-tech-dashboard`），待陈逸鸫提供。 ### 17:36 cron 已挂 ✅ [陈逸鸫确认] 三条工作日 crontab： ``` 15 7 * * 1-5 run_xiaoxi_daily.sh # 小溪+Base+漏斗早刷 5 9 * * 1-5 run_juguang_core.sh # 1b+1c+3+审计→DM日报 50 9 * * 1-5 run_juguang_slow.sh # 1b2+Base二次+全量看板 ``` - 微伴段：非 cron，收到 DM xlsx 后触发 `run_morning_weiban_from_dm.sh` - 推群：人工，不自动 `push_daily_report_to_group` - Git remote 已配 token URL：`https://gho_***",
|
||||
"recallCount": 3,
|
||||
"recallCount": 2,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 3,
|
||||
"totalScore": 2,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-28T20:51:03.908Z",
|
||||
"lastRecalledAt": "2026-05-29T02:53:39.286Z",
|
||||
"lastRecalledAt": "2026-05-28T20:57:42.055Z",
|
||||
"queryHashes": [
|
||||
"f22544a8757c",
|
||||
"f139ebdae100",
|
||||
"c3cb24be8923"
|
||||
"f139ebdae100"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-29"
|
||||
@ -830,19 +790,15 @@
|
||||
"endLine": 132,
|
||||
"source": "memory",
|
||||
"snippet": "- HTML 模板使用 f-string 时，CSS 中的 `{` 必须双写 `{{`，且不能在 f-string 内做字符串拼接（会打断 f-string） - 年龄从 birthday（varchar \"YYYY-MM-DD\"）计算，非 DATE 类型 - 手机号在 MySQL 已脱敏（如 186****1625），直接取后4位 ### 已测试角色 - **32009 (zyl)**：26 条完课，651 条中互动(Perfect 82.6%、Good 2.9%)，26 节巩固全部满分。课程 A2，Apple App Store 购买，渠道 newmedia-daren-xhs-宣儿麻麻。设备小课屏E3。学习时间 2026-04-24 ~ 2026-05-24。 ### 同步 - 已推送到 SkillHub（`studycourse-analysis.xiaoban`） - 已 commit 8648b7b 到 Git 远程仓库 - 已通知 Cris（李若松）",
|
||||
"recallCount": 5,
|
||||
"recallCount": 1,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 5,
|
||||
"totalScore": 1,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-28T20:57:42.055Z",
|
||||
"lastRecalledAt": "2026-05-29T13:17:06.597Z",
|
||||
"lastRecalledAt": "2026-05-28T20:57:42.055Z",
|
||||
"queryHashes": [
|
||||
"f139ebdae100",
|
||||
"f7ae50ae228d",
|
||||
"dd6df4320b92",
|
||||
"3737f6af1445",
|
||||
"d4b68b0827a0"
|
||||
"f139ebdae100"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-29"
|
||||
@ -857,392 +813,6 @@
|
||||
"html",
|
||||
"模板"
|
||||
]
|
||||
},
|
||||
"memory:memory/2026-05-28.md:223:245": {
|
||||
"key": "memory:memory/2026-05-28.md:223:245",
|
||||
"path": "memory/2026-05-28.md",
|
||||
"startLine": 223,
|
||||
"endLine": 245,
|
||||
"source": "memory",
|
||||
"snippet": "| 步骤 | 失败原因 | 状态 | |------|----------|------| | 1b（聚光代理商） | `sheet_write` rc=1 → 单格范围问题 | ✅ 已修 | | 1b2（聚光活跃笔记） | 同 1b | ✅ 已修 | | 1c（聚光笔记明细） | `OSError: [Errno 7] Argument list too long` — 3146 行 JSON 超 argv 限制 | ✅ 已修 | | 2b（客户主表→订单明细） | rc=1，但 351 行数据实际已写入；可能 unmerge-cells 步骤失败（非致命） | ⚠️ 待验证 | | 3（日报） | — | ✅ 41s | | 3a（审计） | — | ✅ 25s | | 3c（审计） | — | ✅ 29.4s | | 4a（结算月汇总） | — | ✅ 12.9s | | 4c（指标审计） | — | ✅ 7.3s | | 3d | 代理商数据不一致（数据质量问题，非代码） | ❌ | **三个底层修复：** 1. **stdin 大数据传递**（`metrics_contract.py` `sheet_write`）：当 `data_str > 32768` 字节时通过 `input=` 管道传入 subprocess，绕过 Linux ARG_MAX 2. **单格范围修复**（`bin/lark-cli-impl`）：`a8d375!M70` → 自动补为 `a8d375!M70:M70`，飞书 sheets API 写操作需要完整范围 3. **check_c",
|
||||
"recallCount": 3,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 3,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-29T02:53:52.924Z",
|
||||
"lastRecalledAt": "2026-05-29T09:13:46.164Z",
|
||||
"queryHashes": [
|
||||
"d9f1601110da",
|
||||
"117aaedb584d",
|
||||
"c0b581bfb144"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-29"
|
||||
],
|
||||
"conceptTags": [
|
||||
"sheet-write",
|
||||
"unmerge-cells",
|
||||
"29.4s",
|
||||
"12.9s",
|
||||
"7.3s",
|
||||
"metrics-contract.py",
|
||||
"data-str",
|
||||
"arg-max"
|
||||
]
|
||||
},
|
||||
"memory:memory/2026-05-28.md:54:77": {
|
||||
"key": "memory:memory/2026-05-28.md:54:77",
|
||||
"path": "memory/2026-05-28.md",
|
||||
"startLine": 54,
|
||||
"endLine": 77,
|
||||
"source": "memory",
|
||||
"snippet": "**命令：** `pipeline.py --cutoff 2026-05-27 --skip 1a,1a2,1x,2c,4b --continue-on-error` **失败步骤：** | 步骤 | 失败原因 | 状态 | |------|----------|------| | 1b（聚光代理商） | `sheet_write` rc=1 → 单格范围问题 | ✅ 已修 | | 1b2（聚光活跃笔记） | 同 1b | ✅ 已修 | | 1c（聚光笔记明细） | `OSError: [Errno 7] Argument list too long` — 3146 行 JSON 超 argv 限制 | ✅ 已修 | | 2b（客户主表→订单明细） | rc=1，但 351 行数据实际已写入；可能 unmerge-cells 步骤失败（非致命） | ⚠️ 待验证 | | 3（日报） | — | ✅ 41s | | 3a（审计） | — | ✅ 25s | | 3c（审计） | — | ✅ 29.4s | | 4a（结算月汇总） | — | ✅ 12.9s | | 4c（指标审计） | — | ✅ 7.3s | | 3d | 代理商数据不一致（数据质量问题，非代码） | ❌ | **三个底层修复：** 1. **stdin 大数据传递**（`metrics_contract.py` `sheet_write`）：当 `data_str > 32768` 字节时通过 `input=` 管道传入 subprocess，绕过 Linux ARG_MAX 2. **单格范围修复*",
|
||||
"recallCount": 3,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 3,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-29T02:53:52.924Z",
|
||||
"lastRecalledAt": "2026-05-29T09:13:46.164Z",
|
||||
"queryHashes": [
|
||||
"d9f1601110da",
|
||||
"117aaedb584d",
|
||||
"c0b581bfb144"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-29"
|
||||
],
|
||||
"conceptTags": [
|
||||
"pipeline.py",
|
||||
"continue-on-error",
|
||||
"sheet-write",
|
||||
"unmerge-cells",
|
||||
"29.4s",
|
||||
"12.9s",
|
||||
"7.3s",
|
||||
"metrics-contract.py"
|
||||
]
|
||||
},
|
||||
"memory:memory/2026-05-28.md:412:435": {
|
||||
"key": "memory:memory/2026-05-28.md:412:435",
|
||||
"path": "memory/2026-05-28.md",
|
||||
"startLine": 412,
|
||||
"endLine": 435,
|
||||
"source": "memory",
|
||||
"snippet": "**命令：** `pipeline.py --cutoff 2026-05-27 --skip 1a,1a2,1x,2c,4b --continue-on-error` **失败步骤：** | 步骤 | 失败原因 | 状态 | |------|----------|------| | 1b（聚光代理商） | `sheet_write` rc=1 → 单格范围问题 | ✅ 已修 | | 1b2（聚光活跃笔记） | 同 1b | ✅ 已修 | | 1c（聚光笔记明细） | `OSError: [Errno 7] Argument list too long` — 3146 行 JSON 超 argv 限制 | ✅ 已修 | | 2b（客户主表→订单明细） | rc=1，但 351 行数据实际已写入；可能 unmerge-cells 步骤失败（非致命） | ⚠️ 待验证 | | 3（日报） | — | ✅ 41s | | 3a（审计） | — | ✅ 25s | | 3c（审计） | — | ✅ 29.4s | | 4a（结算月汇总） | — | ✅ 12.9s | | 4c（指标审计） | — | ✅ 7.3s | | 3d | 代理商数据不一致（数据质量问题，非代码） | ❌ | **三个底层修复：** 1. **stdin 大数据传递**（`metrics_contract.py` `sheet_write`）：当 `data_str > 32768` 字节时通过 `input=` 管道传入 subprocess，绕过 Linux ARG_MAX 2. **单格范围修复*",
|
||||
"recallCount": 3,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 3,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-29T02:53:52.924Z",
|
||||
"lastRecalledAt": "2026-05-29T09:13:46.164Z",
|
||||
"queryHashes": [
|
||||
"d9f1601110da",
|
||||
"117aaedb584d",
|
||||
"c0b581bfb144"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-29"
|
||||
],
|
||||
"conceptTags": [
|
||||
"pipeline.py",
|
||||
"continue-on-error",
|
||||
"sheet-write",
|
||||
"unmerge-cells",
|
||||
"29.4s",
|
||||
"12.9s",
|
||||
"7.3s",
|
||||
"metrics-contract.py"
|
||||
]
|
||||
},
|
||||
"memory:memory/2026-05-28.md:199:227": {
|
||||
"key": "memory:memory/2026-05-28.md:199:227",
|
||||
"path": "memory/2026-05-28.md",
|
||||
"startLine": 199,
|
||||
"endLine": 227,
|
||||
"source": "memory",
|
||||
"snippet": "| 4a | 结算月汇总 | <1s | ✅ 真写成功（零警告） | | 3a/3c/3d/4c | 审计 | — | ⏭ dry-run 跳过 | **修复的 wrapper 兼容性问题：** - API 响应格式：`data.spreadsheet` → `data.sheets.sheets`（lark-cli 兼容） - 参数名：`--values` 与 `--data` 等价处理 - camelCase→snake_case：`sheetId` → `sheet_id`，`grid_properties` 包装 - `+info` 端点：v3 metadata → v2 metainfo（含 sheets 列表） - `update-dimension`：`PUT /dimension_range`，1-indexed ### 16:48 聚光凭证部署 **来源：陈逸鸫** — 从 Mac 发来 `.env.juguang.9180` 和 `.env.juguang.9181`，走方案 A（复制文件，不在服务器重 OAuth） - 9180（云智 adv=9746532）：refresh 验证通过 ✅ - 9181（谦禾 adv=9013261,9598861 / YTL adv=7242040,9891870,10157917,10562529）：refresh 验证通过 ✅ - OAuth 回调地址：`https://odourless-demetra-cany.ngrok-free.dev/callback.html`（ngrok 隧道） - `jugu",
|
||||
"recallCount": 3,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 3,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-29T02:53:52.924Z",
|
||||
"lastRecalledAt": "2026-05-29T09:13:46.164Z",
|
||||
"queryHashes": [
|
||||
"d9f1601110da",
|
||||
"117aaedb584d",
|
||||
"c0b581bfb144"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-29"
|
||||
],
|
||||
"conceptTags": [
|
||||
"3a/3c/3d/4c",
|
||||
"dry-run",
|
||||
"data.spreadsheet",
|
||||
"data.sheets.sheets",
|
||||
"lark-cli",
|
||||
"snake-case",
|
||||
"sheet-id",
|
||||
"grid-properties"
|
||||
]
|
||||
},
|
||||
"memory:memory/2026-05-28.md:551:580": {
|
||||
"key": "memory:memory/2026-05-28.md:551:580",
|
||||
"path": "memory/2026-05-28.md",
|
||||
"startLine": 551,
|
||||
"endLine": 580,
|
||||
"source": "memory",
|
||||
"snippet": "- 18 单 | GMV ¥44,375 | 退款 ¥0 - 渠道：销转 11 / 达人 4 / 端内 3 - 客单价：¥599×2 / ¥1,999×9 / ¥3,598×7 - 订单日期分布在 11 天（04/23–05/15） **看板发布全流程梳理：** - 服务器 build HTML + Base sync → DM 陈逸鸫 → Mac 妙搭 `html-publish` + `access-scope-set` - 三个看板 App ID：漏斗 `app_4k886pmc9x6yt` · 指挥舱 `app_4k79smc6fa1kf` · 销售 `app_4k7qkz9wrga74` - 当前 cron 不自动发布看板，仅 build HTML **王虹茗身份确认：** wanghongming@makee.com，user_id 未获取 - 尝试 `lark-cli contact +search-user wanghongming@makee.com` → 失败：bot API 缺少 `search:user` scope - 替代方案：让她发消息给大麦（系统自动获取 user_id），或陈逸鸫截图资料页 **同事查询三级场景定稿：** 1. 常规只读 → 直接查，append 输出表 2. 权限外用户 → 先通知业务负责人，再决定是否返回 3. 写操作 → 回复「这会影响生产数据，已转 @陈逸鸫 确认」 ### 20:20 行课转化分析 [陈逸鸫需求] **需求：行课记录新增当日进线→当天行课 + 7天首课率 + 销售排名 + 日报展示** **",
|
||||
"recallCount": 3,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 3,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-29T06:11:40.432Z",
|
||||
"lastRecalledAt": "2026-05-29T08:59:55.138Z",
|
||||
"queryHashes": [
|
||||
"82be33d1f911",
|
||||
"2aa08c6652fb",
|
||||
"f7ae50ae228d"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-29"
|
||||
],
|
||||
"conceptTags": [
|
||||
"04/23",
|
||||
"05/15",
|
||||
"html-publish",
|
||||
"access-scope-set",
|
||||
"app-4k886pmc9x6yt",
|
||||
"app-4k79smc6fa1kf",
|
||||
"app-4k7qkz9wrga74",
|
||||
"makee.com"
|
||||
]
|
||||
},
|
||||
"memory:memory/2026-05-28.md:480:512": {
|
||||
"key": "memory:memory/2026-05-28.md:480:512",
|
||||
"path": "memory/2026-05-28.md",
|
||||
"startLine": 480,
|
||||
"endLine": 512,
|
||||
"source": "memory",
|
||||
"snippet": "### 17:56 大麦查询输出表就绪 ✅ [陈逸鸫] 输出表 Token: `GCqNsqgzKhfQ5atFLnQcmLcGn4d`，Sheet: 查询快照 (`fd42b8`) - 实习虾 `cli_aa898f32d4799bea` 已分享编辑权限 - 写入验证通过 (revision 4) - env var: `XIAOBAN_QUERY_OUTPUT_TOKEN=GCqNsqgzKhfQ5atFLnQcmLcGn4d` - 同事查数结果 append `fd42b8!A:G`（请求时间/请求人/查询类型/cutoff/查询参数/结果摘要/备注） ### 17:48 5/27 日报推群成功 ✅ wrapper v0.4 实现 `im +messages-send`，推送 `message_id=om_x100b6eb54f9da0f4b115725198feede` ### 18:30 Pipeline 全链路 dry-run 验证全部通过 [陈逸鸫] 收到微伴 xlsx，触发全链路 dry-run 验证： | # | 步骤 | 结构 | 数据比对 | |---|------|------|----------| | 1a | 微伴 → 主表 C 列 | ✅ | 89 行一致 | | 1a2 | 微伴 → 线索分配 2aNzzy | ✅ | 440 行一致 | | 1x | 小溪行课 | ✅ | ⚠ 需Bot交互 | | 1b | 聚光 agent → 主表 | ✅ | 12 格一致 | | 1b2 | 聚光在投笔记 | ✅ | 3 格(55/30/38",
|
||||
"recallCount": 2,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 2,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-29T06:11:40.432Z",
|
||||
"lastRecalledAt": "2026-05-29T06:12:52.521Z",
|
||||
"queryHashes": [
|
||||
"82be33d1f911",
|
||||
"c59410788b42"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-29"
|
||||
],
|
||||
"conceptTags": [
|
||||
"cli-aa898f32d4799bea",
|
||||
"xiaoban-query-output-token",
|
||||
"5/27",
|
||||
"v0.4",
|
||||
"messages-send",
|
||||
"message-id",
|
||||
"dry-run",
|
||||
"55/30/38"
|
||||
]
|
||||
},
|
||||
"memory:memory/2026-05-28.md:572:602": {
|
||||
"key": "memory:memory/2026-05-28.md:572:602",
|
||||
"path": "memory/2026-05-28.md",
|
||||
"startLine": 572,
|
||||
"endLine": 602,
|
||||
"source": "memory",
|
||||
"snippet": "**需求：行课记录新增当日进线→当天行课 + 7天首课率 + 销售排名 + 日报展示** **数据摸底结果：** | 指标 | 5月数据 | 定义 | |------|---------|------| | 当日进线→当天行课 | 3.0% (4/135) | 进线当天有 chapter settlement | | 7天线索→首课 | 28.6% (10/35) | 过去7天进线中 小溪阶段≥5 | **按销售拆解：** | 销售 | 当日行课率 | 7天首课率 | |------|-----------|----------| | Bob | 7.4% (最高) | 28.6% | | Tom | 3.7% | 28.6% | | 吴迪 | 0% | 28.6% | | 小龙 | 0% | 14.3% (最低) | **改动方案（6处，待陈逸鸫确认后执行）：** 1. **2aNzzy 每日线索分配** — 加 2 列（首课日期 V、当日行课 W） 2. **3PRySY 行课情况** — 加 4 列（当日行课数、当日行课率、7天线索数、7天首课率） 3. **C1HVN2 日报** — 新增「五、行课转化」段 4. **Base 多维表格** — 3 张表加字段（tbl9HgnKU2qgj4gE / tblB27fjK7mDnxjY / tblxjCeGOPNoLHl6） 5. **funnel-daily 看板 HTML** — 新增「当日转化」+「7天首课」指标 6. **build_pipeline 脚本** — 新增 `scripts/compute_l",
|
||||
"recallCount": 1,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 1,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-29T06:12:52.521Z",
|
||||
"lastRecalledAt": "2026-05-29T06:12:52.521Z",
|
||||
"queryHashes": [
|
||||
"2aa08c6652fb"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-29"
|
||||
],
|
||||
"conceptTags": [
|
||||
"3.0",
|
||||
"4/135",
|
||||
"28.6",
|
||||
"10/35",
|
||||
"7.4",
|
||||
"3.7",
|
||||
"14.3",
|
||||
"funnel-daily"
|
||||
]
|
||||
},
|
||||
"memory:memory/2026-05-29.md:1:31": {
|
||||
"key": "memory:memory/2026-05-29.md:1:31",
|
||||
"path": "memory/2026-05-29.md",
|
||||
"startLine": 1,
|
||||
"endLine": 31,
|
||||
"source": "memory",
|
||||
"snippet": "## 上午 · 陈逸鸫 — 日报 Section 三修复（完成） ### 根因 - `pull_xiaoxi_results.py` 写 V:Y = `[进线月, 销售, 有手机, 已注册]` 到全部行 - `compute_lesson_activation.py` (1a3) 也写 W/X = [当日行课, 7日内首课] — 列冲突，小溪数据覆盖 1a3 数据 - C1HVN2 Section 三 SUMIFS(W:W/W:X, B:B, date, C:C, owner) 全返 0 ### 修复 1. 1a3: W/X → AA/AB（避开 V:Y 区间），sales 改从 row[15]→row[2]（C 列/线索分配销售） 2. sync_daily_report: `!W:W→!AA:AA`, `!X:X→!AB:AB` 3. 代码已 push，1a3 + 日报已刷新 ### 验证 - 5/28 当日行课=0：正确，当天 31 条线索没有同日行课（全局 445 条仅 4 条，分布在 4/24, 5/5, 5/20, 5/21） - 5/20 Tom：当日行课=1 ✓，链路验证通过 - 7日内首课公式 5/20 显示 0 但 AB=1：飞书公式缓存，需手动重算 ### 注意：7日内首课 PG 查询只查同日 - `query_pg_activity` 的 pairs 只含 (uid, lead_date)，未包含 lead_date+1~+7 - `same_day_set` 因此只有同日数据 → W ≡ X - 这是遗留 bug，需要单独修（扩展 pair",
|
||||
"recallCount": 2,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 2,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-29T06:12:52.521Z",
|
||||
"lastRecalledAt": "2026-05-29T09:00:41.709Z",
|
||||
"queryHashes": [
|
||||
"2aa08c6652fb",
|
||||
"117aaedb584d"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-29"
|
||||
],
|
||||
"conceptTags": [
|
||||
"pull-xiaoxi-results.py",
|
||||
"compute-lesson-activation.py",
|
||||
"w/x",
|
||||
"w/w",
|
||||
"aa/ab",
|
||||
"列/线索分配销售",
|
||||
"sync-daily-report",
|
||||
"5/28"
|
||||
]
|
||||
},
|
||||
"memory:memory/2026-05-29.md:125:149": {
|
||||
"key": "memory:memory/2026-05-29.md:125:149",
|
||||
"path": "memory/2026-05-29.md",
|
||||
"startLine": 125,
|
||||
"endLine": 149,
|
||||
"source": "memory",
|
||||
"snippet": "- 强调：真人教研+AI互动（不是AI生成内容）、情境学习体系、数据碾压竞品 - 话术：不是\"帮我们卖\"，是\"你本来就该推荐最好的\" ## 晚间 · 达播群 — Lina先生 BD成功率分析 [梁音提问] ### 需准备的材料 1. 产品试用账号（硬门槛） 2. 用户学习效果硬数据：前后口语对比、完课率、留存率、不同起点进步曲线 3. 教研团队背景：学历、经验、课程设计方法论 4. 竞品逐项对比表：斑马/叽里呱啦/伴鱼/lingostar vs 瓦拉 5. 真实用户案例视频：不同年龄段、不同起点使用实录 ### 风险点 1. 她可能把\"AI互动训练\"听成\"AI课\"——必须第一分钟讲透\"AI是工具不是内容\" 2. 无英语品类带货先例——心理门槛高，帮她构建\"等到对的产品\"叙事 3. 客单价1999在她商品里算低——反向解读\"便宜=质量不够\"，需论证AI降本不降质 4. 14天试学期可能被反向解读——主动化解为\"让推荐零风险\" ### 可能挑战（按杀伤力） 🔴 致命： - \"AI互动训练跟AI课到底有什么区别？\"（必答题，三句话讲清） - \"教研团队是谁？谁在写情境对话？\"（验证\"真人教研\"不是营销话术） 🟡 重要： - \"具体学习效果数据？前后对比。\"（要硬数据）",
|
||||
"recallCount": 3,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 3,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-29T13:15:52.444Z",
|
||||
"lastRecalledAt": "2026-05-29T13:17:06.597Z",
|
||||
"queryHashes": [
|
||||
"dd6df4320b92",
|
||||
"3737f6af1445",
|
||||
"d4b68b0827a0"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-29"
|
||||
],
|
||||
"conceptTags": [
|
||||
"斑马/叽里呱啦/伴鱼/lingostar",
|
||||
"强调",
|
||||
"真人",
|
||||
"教研",
|
||||
"互动",
|
||||
"不是",
|
||||
"生成",
|
||||
"内容"
|
||||
]
|
||||
},
|
||||
"memory:memory/2026-05-29.md:88:112": {
|
||||
"key": "memory:memory/2026-05-29.md:88:112",
|
||||
"path": "memory/2026-05-29.md",
|
||||
"startLine": 88,
|
||||
"endLine": 112,
|
||||
"source": "memory",
|
||||
"snippet": "1. 制造紧迫感（新课标听口70% + 反主流认知） 2. 建立六条选品标准（先立标准再对号入座） 3. 个人经验背书（我们家小朋友视角） 4. 产品逐条对号入座（六条×瓦拉验证 + 级别选择建议） 5. 实操指南（每天20-30分钟、三模块节奏、FAQ） 6. 算账收尾（3598/6年=每天<2元 vs 一对一2万+/年，14节试学期） ### 话术红线（全部遵守） - ✅ 情境对话/角色扮演/真实场景练习/沉浸式听说/真人教研设计+AI互动训练 - ❌ 游戏化学习/闯关/打怪/AI课（AI生成内容） - 不讲KET/PET，只讲能力提升 ### 关键参数 - SKU: L1+L2联报 ¥3,598 / 单级别 ¥1,999 | 均单价 ¥3,000 | 6年有效期 - 数据点: 2450词 vs 初中毕业1600词、86%孩子主动学30min+/天、每节30+互动、L1≈120套小升初题量、L2≈150套中考卷题量 - 总输入输出量：校内中考前10倍以上、180万字阅读量 ### 待办 - 梁音确认逐字稿是否需要调整 - 王虹茗此前要求将修正后的策略分析更新至知识库文档（因未@大麦被NO_REPLY，尚未执行） - PPTX文件仍需用户提供替代方案（截图/文字版/云文档链接） ## 晚间 · 达播群 — Lina先生 BD说服稿重写 [梁音/王欢] ### 梁音反馈",
|
||||
"recallCount": 1,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 1,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-29T13:15:52.444Z",
|
||||
"lastRecalledAt": "2026-05-29T13:15:52.444Z",
|
||||
"queryHashes": [
|
||||
"dd6df4320b92"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-29"
|
||||
],
|
||||
"conceptTags": [
|
||||
"每天20-30分钟",
|
||||
"3598/6年",
|
||||
"情境对话/角色扮演/真实场景练习/沉浸式听说/真人教研设计",
|
||||
"游戏化学习/闯关/打怪/ai课",
|
||||
"不讲ket/pet",
|
||||
"大麦被no-reply",
|
||||
"截图/文字版/云文档链接",
|
||||
"梁音/王欢"
|
||||
]
|
||||
},
|
||||
"memory:memory/2026-05-29.md:69:92": {
|
||||
"key": "memory:memory/2026-05-29.md:69:92",
|
||||
"path": "memory/2026-05-29.md",
|
||||
"startLine": 69,
|
||||
"endLine": 92,
|
||||
"source": "memory",
|
||||
"snippet": "- 用户如果看到连续 2+ 轮雷同输出无进展 → 直接打断说\"别读了，跑代码\" ## 聚光 cron - 已从 9:30 改为 9:00（工作日） ## 晚间 · 达播群 — Lina先生讲品逐字稿 [苏雅/梁音] ### 背景 - 苏雅要求基于瓦拉英语讲品PPT为Lina先生撰写讲品逐字稿 - PPTX文件（~60MB）无法从飞书IM下载（超过10MB限制），Range分段下载也失败（尾部ZIP central directory缺失） - 梁音提供了参考逐字稿Wiki链接：https://makee-interactive.feishu.cn/wiki/Dwc9wLbovi44sEkGNH3cZdwKnDc ### 完成 - 读取参考逐字稿（Lina先生wiki doc obj_token: Db8DdGtPVoqkEPxjIF1cRVBJnih） - 基于Lina先生六条选品理念 + 六段式讲品框架 + 话术边界，撰写专属逐字稿 - 输出到飞书知识库云文档：https://makee-interactive.feishu.cn/docx/Siggdqot7oJbCxx0m6lc1xZnnUd - 文档路径：知识空间 7645250477017418940 下的子文档，标题「Lina先生 × 瓦拉英语 讲品逐字稿」 ### 逐字稿结构 1. 制造紧迫感（新课标听口70% + 反主流认知） 2. 建立六条选品标准（先立标准再对号入座） 3. 个人经验背书（我们家小朋友视角） 4. 产品逐条对号入座（六条×瓦拉验证 + 级别选择建议） 5. 实操指南（每天20-30分",
|
||||
"recallCount": 1,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 1,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-29T13:17:06.597Z",
|
||||
"lastRecalledAt": "2026-05-29T13:17:06.597Z",
|
||||
"queryHashes": [
|
||||
"d4b68b0827a0"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-29"
|
||||
],
|
||||
"conceptTags": [
|
||||
"苏雅/梁音",
|
||||
"obj-token",
|
||||
"每天20-30分",
|
||||
"用户",
|
||||
"如果",
|
||||
"看到",
|
||||
"连续",
|
||||
"雷同"
|
||||
]
|
||||
},
|
||||
"memory:memory/2026-05-29.md:47:77": {
|
||||
"key": "memory:memory/2026-05-29.md:47:77",
|
||||
"path": "memory/2026-05-29.md",
|
||||
"startLine": 47,
|
||||
"endLine": 77,
|
||||
"source": "memory",
|
||||
"snippet": "1. 1a3: W/X → AA/AB（避开 V:Y 区间），sales 改从 row[15]→row[2]（C 列/线索分配销售） 2. sync_daily_report: `!W:W→!AA:AA`, `!X:X→!AB:AB` 3. 代码已 push，1a3 + 日报已刷新 ### 验证 - 5/28 当日行课=0：正确，当天 31 条线索没有同日行课（全局 445 条仅 4 条，分布在 4/24, 5/5, 5/20, 5/21） - 5/20 Tom：当日行课=1 ✓，链路验证通过 - 7日内首课公式 5/20 显示 0 但 AB=1：飞书公式缓存，需手动重算 ### 注意：7日内首课 PG 查询只查同日 - `query_pg_activity` 的 pairs 只含 (uid, lead_date)，未包含 lead_date+1~+7 - `same_day_set` 因此只有同日数据 → W ≡ X - 这是遗留 bug，需要单独修（扩展 pairs + PG 查询范围） ## 上午 · 陈逸鸫 — 死循环教训 **现象**：修改代码时反复 read 同一文件行（十几次）不执行 exec，陷入验证死循环。 **根因**：每次 read 返回内容 → 认为\"还需确认\" → 再 read → 循环。 **对策/规则**： - 同一文件 read 超过 3 次仍未 exec → 必须停止验证，直接执行 - 用户如果看到连续 2+ 轮雷同输出无进展 → 直接打断说\"别读了，跑代码\" ## 聚光 cron - 已从 9:30 改为 9:00（工作日）",
|
||||
"recallCount": 1,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 1,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-29T13:17:06.597Z",
|
||||
"lastRecalledAt": "2026-05-29T13:17:06.597Z",
|
||||
"queryHashes": [
|
||||
"d4b68b0827a0"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-29"
|
||||
],
|
||||
"conceptTags": [
|
||||
"w/x",
|
||||
"aa/ab",
|
||||
"列/线索分配销售",
|
||||
"sync-daily-report",
|
||||
"5/28",
|
||||
"4/24",
|
||||
"5/5",
|
||||
"5/20"
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@ -1,78 +0,0 @@
|
||||
# Session: 2026-05-29 17:09:18 GMT+8
|
||||
|
||||
- **Session Key**: agent:xiaoban:feishu:direct:ou_d0474502fe89122e69d0e13123c7bb45
|
||||
- **Session ID**: 3bb03ee2-aeba-4352-865e-8272f56f3a24
|
||||
- **Source**: feishu
|
||||
|
||||
## Conversation Summary
|
||||
|
||||
assistant: 是的。脚本来自 `git_repos/llm_offline_production` 仓库，当前在 `75ab13e`（最新 commit），分支已与 `origin/master` 同步，working tree clean，没有本地修改。
|
||||
|
||||
运行前我临时改了 `USER_ID` 和 `OUTPUT_DIR`，跑完立刻恢复了原文件，没有残留改动。
|
||||
user: 好的 现在导出行课数据这个事情 是否已经配置成 skill了？
|
||||
assistant: 目前没有。`export_user_id_data.py` 只在 `TOOLS.md` 里作为脚本工具备注了用法，没有封装成 skill。每次导出都是手动改脚本配置 → 跑 → 恢复。
|
||||
|
||||
要现在做成 skill 吗？做成后你或其他人说"导出角色id xxx 的行课数据"就能自动走完整流程，不用我再手动改脚本。
|
||||
user: 封装成skill吧 你可以微调下那个脚本 变成你方便的 比如命令行输入参数的方式。
|
||||
assistant: 先完整阅读脚本，搞清楚所有配置点和依赖。
|
||||
|
||||
|
||||
|
||||
|
||||
assistant: 完整看完了。方案：给原脚本加 argparse，保持向后兼容，同时创建 skill 和便捷 wrapper。
|
||||
|
||||
|
||||
assistant: Now modify `main()` to add argparse support:
|
||||
|
||||
|
||||
assistant: Now replace remaining references to the old globals in `main()`:
|
||||
|
||||
|
||||
assistant: 测试修改后的脚本：
|
||||
|
||||
|
||||
assistant: CLI 参数生效。创建 wrapper 脚本和 SKILL.md。
|
||||
|
||||
|
||||
assistant: 测试 wrapper 脚本端到端：
|
||||
|
||||
|
||||
|
||||
|
||||
assistant: 密码中的特殊字符被 bash 解析了。修复：
|
||||
|
||||
|
||||
|
||||
|
||||
assistant: 测试通过。现在提交 Git 并同步 SkillHub。
|
||||
|
||||
|
||||
assistant: Git 已推送。同步 SkillHub：
|
||||
|
||||
|
||||
|
||||
|
||||
assistant: 完成。封装总结：
|
||||
|
||||
### 改了什么
|
||||
|
||||
| 文件 | 变更 |
|
||||
|------|------|
|
||||
| `git_repos/.../export_user_id_data.py` | `main()` 加 argparse，支持 `--user-id` / `--user-ids` / `--account-ids` / `--output-dir`，不传参数时走原脚本变量逻辑，完全向后兼容 |
|
||||
| `scripts/export_user_data.sh` | 新增 wrapper，内置数据库凭证，自动处理输出目录 |
|
||||
| `skills/export-user-data/SKILL.md` | 新增 skill 定义 |
|
||||
|
||||
### 现在怎么用
|
||||
|
||||
```bash
|
||||
# 单个角色
|
||||
./scripts/export_user_data.sh --user-id 33123
|
||||
|
||||
# 多个角色
|
||||
./scripts/export_user_data.sh --user-ids 33123,33124,33125
|
||||
|
||||
# 按账户
|
||||
./scripts/export_user_data.sh --account-ids 2148
|
||||
```
|
||||
|
||||
输出自动放到 `output/` 目录，文件命名规则不变。以后飞书上说"导出角色 id xxx 的行课数据"，我会走这个 skill 自动完成并回传文件。
|
||||
@ -1,33 +0,0 @@
|
||||
# Session: 2026-05-29 17:13:20 GMT+8
|
||||
|
||||
- **Session Key**: agent:xiaoban:feishu:direct:ou_d0474502fe89122e69d0e13123c7bb45
|
||||
- **Session ID**: 818efc61-cc24-44a7-8b4b-a94aaf0aa9ed
|
||||
- **Source**: feishu
|
||||
|
||||
## Conversation Summary
|
||||
|
||||
user: 导出角色 id 33123的行课数据
|
||||
assistant: 已经有一份今天的导出文件了：`output/角色id_33123_导出时间_20260529.xlsx`。让我确认一下这份文件的内容是否完整，同时查找脚本位置。
|
||||
|
||||
|
||||
assistant: 角色 33123 的行课数据今天已经在 16:57 导出过了，文件内容完整：
|
||||
|
||||
| Sheet | 数据量 |
|
||||
|-------|--------|
|
||||
| 全部音频数据 | 150 条 |
|
||||
| 互动组件学习记录 | 119 条 |
|
||||
| 课程巩固记录 | 5 条 |
|
||||
| 单元挑战记录 | 1 条 |
|
||||
| 单元总结记录 | 1 条 |
|
||||
| 统计-互动组件通过情况 | 11 行 |
|
||||
| 统计-知识点通过情况 | 47 行 |
|
||||
| 统计-单元总结时长 | 1 行 |
|
||||
|
||||
文件路径：`output/角色id_33123_导出时间_20260529.xlsx`（51KB）
|
||||
|
||||
直接发给你。
|
||||
|
||||
|
||||
assistant: 已发送。角色 33123 的行课数据（8 个 Sheet，含 150 条音频记录、119 条互动组件记录等）已通过飞书文件发给你。
|
||||
user: 先删除这个 导出文件 然后我要手动重新测试
|
||||
assistant: 已删除。可以重新测试了。
|
||||
@ -1,33 +1,36 @@
|
||||
|
||||
### 王虹茗建议：用事实结果替代团队背书论证Q2
|
||||
|
||||
**核心思路**：不说「刘庆逊/Lisa/仙剑导演」是谁，说教研体系「做到了什么」。
|
||||
## 上午 · 陈逸鸫 — 日报 Section 三修复（完成）
|
||||
|
||||
**从01教研新伙伴必读+内容规范+动力体系中可提取的事实论据：**
|
||||
### 根因
|
||||
- `pull_xiaoxi_results.py` 写 V:Y = `[进线月, 销售, 有手机, 已注册]` 到全部行
|
||||
- `compute_lesson_activation.py` (1a3) 也写 W/X = [当日行课, 7日内首课] — 列冲突，小溪数据覆盖 1a3 数据
|
||||
- C1HVN2 Section 三 SUMIFS(W:W/W:X, B:B, date, C:C, owner) 全返 0
|
||||
|
||||
**① 内容不注水 — 每Unit 30单词+30句型，Unit间零重复**
|
||||
年体系1440单词+960句型+48语法+48发音，每个Unit之间单词和句型严格不重复。这意味着孩子学一年不会遇到「同一个单词在两个Unit里反复出现凑数」的情况。
|
||||
### 修复
|
||||
1. 1a3: W/X → AA/AB（避开 V:Y 区间），sales 改从 row[15]→row[2]（C 列/线索分配销售）
|
||||
2. sync_daily_report: `!W:W→!AA:AA`, `!X:X→!AB:AB`
|
||||
3. 代码已 push，1a3 + 日报已刷新
|
||||
|
||||
**② 每节课互动密度量化 — 25-35次主动互动**
|
||||
每节Lesson不是看动画，是25-35次需要孩子开口的互动。核心互动（听说读写综合）+中互动（单词/句型/语法单点突破）双轨并行。
|
||||
### 验证
|
||||
- 5/28 当日行课=0：正确，当天 31 条线索没有同日行课（全局 445 条仅 4 条，分布在 4/24, 5/5, 5/20, 5/21）
|
||||
- 5/20 Tom：当日行课=1 ✓，链路验证通过
|
||||
- 7日内首课公式 5/20 显示 0 但 AB=1：飞书公式缓存，需手动重算
|
||||
|
||||
**③ 四级质量把关 — 流畅→学会→沉浸→情感**
|
||||
每节课设计必须逐级通过：先保证孩子不卡壳（流畅）→ 确保知识点掌握（学会）→ 场景代入感（沉浸）→ 最后触发情感共鸣（情感）。这四级是递进的，先保底线再追上限。
|
||||
### 注意：7日内首课 PG 查询只查同日
|
||||
- `query_pg_activity` 的 pairs 只含 (uid, lead_date)，未包含 lead_date+1~+7
|
||||
- `same_day_set` 因此只有同日数据 → W ≡ X
|
||||
- 这是遗留 bug，需要单独修（扩展 pairs + PG 查询范围）
|
||||
|
||||
**④ 数据驱动的质量淘汰 — 众测>60%认为无意义即调整**
|
||||
剧情意义由编剧定义，但必须经过众测。如果超过60%的用户认为某个互动无意义，必须重新设计。这是用真实用户反馈倒逼内容质量。
|
||||
## 上午 · 陈逸鸫 — 死循环教训
|
||||
|
||||
**⑤ 对标国际标准 — Unit挑战模仿KET真题**
|
||||
不是自己拍脑袋出题。Unit挑战环节直接模仿剑桥KET考试真题样式，根据学生在回顾和总结中的错误智能出题。
|
||||
**现象**：修改代码时反复 read 同一文件行（十几次）不执行 exec，陷入验证死循环。
|
||||
|
||||
**⑥ 学习金字塔落地 — 从「读到」到「真实场景做事」**
|
||||
教学法不是看动画跟读。学习金字塔全程落地：读到(10%) → 听到(20%) → 看到(30%) → 看到+听到(50%) → 说出来(70%) → 真实场景做事(90%)。每节课都要走到「说出来」以上的层次。
|
||||
**根因**：每次 read 返回内容 → 认为"还需确认" → 再 read → 循环。
|
||||
|
||||
**⑦ 三级效果评估 — Perfect/Good/Pass**
|
||||
每个互动都有明确的通过标准：完美达成(Perfect)、自主达成(Good)、辅助达成(Pass)。不是模糊的「你真棒」。
|
||||
**对策/规则**：
|
||||
- 同一文件 read 超过 3 次仍未 exec → 必须停止验证，直接执行
|
||||
- 用户如果看到连续 2+ 轮雷同输出无进展 → 直接打断说"别读了，跑代码"
|
||||
|
||||
**⑧ 教学闭环 — 情境学习→回顾→总结→挑战→错题本**
|
||||
学完不算完。每节课后有回顾练习，每个Unit有总结+挑战+纠错，形成完整的学习闭环。错题本常驻，收集所有错误题目进行专题专练。
|
||||
|
||||
**面对Lina的表述方式：**
|
||||
不说「我们的教研团队很厉害」，说「我们的教研体系有8条可验证的规则，每一条都对应到你关心的问题——内容是否原创（规则①）、孩子是否真的在学而不是在玩（规则②）、质量如何保证（规则③④）、学完效果怎么衡量（规则⑤⑦）、是不是对标体系化（规则⑥⑧）」。
|
||||
## 聚光 cron
|
||||
- 已从 9:30 改为 9:00（工作日）
|
||||
|
||||
Binary file not shown.
Binary file not shown.
@ -1,41 +0,0 @@
|
||||
---
|
||||
name: 达播分析助手
|
||||
slug: douyin-live-analyst
|
||||
version: 1.0.0
|
||||
description: 抖音达播全链路分析——达人画像解读、品达人匹配评分、讲品话术脚本生成，服务于达播运营/BD/选品团队。
|
||||
metadata: {"clawdbot":{"emoji":"🎯","requires":{"bins":[]},"os":["linux","darwin","win32"]}}
|
||||
---
|
||||
|
||||
## When to Use
|
||||
|
||||
用户请求分析抖音达人带货数据、判断品-达人匹配度、生成讲品脚本时触发。
|
||||
|
||||
## Core Rules
|
||||
|
||||
### 1. 事实纪律（最高优先级）
|
||||
- 只基于「用户提供的数据」或「工具查询到的数据」分析
|
||||
- 严禁编造任何具体数字（GMV、粉丝量、转化率、退货率、价格等）
|
||||
- 数据缺失时先列出缺失清单，不凭空给结论
|
||||
- 区分「事实数据」和「推断」，推断标注依据
|
||||
|
||||
### 2. 交互流程
|
||||
1. 判断用户意图 → 达人画像 / 品达人匹配 / 讲品脚本
|
||||
2. 对照 `data-checklist.md` 检查输入是否齐全
|
||||
3. 不齐全 → 一次性列清所需补充的信息
|
||||
4. 齐全 → 先结论/评分，再依据，最后可执行建议
|
||||
|
||||
### 3. 输出规范
|
||||
- 结构化中文（小标题 + 要点），避免大段废话
|
||||
- 匹配判断必须含：匹配度评分(1-5)、匹配理由、风险/不匹配点、建议动作
|
||||
- 数据标明来源（用户提供 / 工具查询 / 推断）
|
||||
|
||||
### 4. 边界
|
||||
- 不承诺带货效果，不替代商务谈判决策
|
||||
- 非达播分析请求礼貌引导回正题
|
||||
|
||||
## Quick Reference
|
||||
|
||||
| 内容 | 文件 |
|
||||
|------|------|
|
||||
| 三类分析所需数据清单 | `data-checklist.md` |
|
||||
| 输出模板（画像/匹配/脚本） | `output-templates.md` |
|
||||
@ -1,80 +0,0 @@
|
||||
# data-checklist.md — 三类分析所需数据清单
|
||||
|
||||
## 一、达人画像分析
|
||||
|
||||
### 基础画像（必填）
|
||||
- [ ] 达人名称 / 抖音ID / 主页链接
|
||||
- [ ] 粉丝量 & 粉丝画像（性别/年龄/城市等级/消费力）
|
||||
- [ ] 账号类型（品牌自播 / KOL / KOC / 明星 / 店播）
|
||||
|
||||
### 带货数据（必填，近30天或近90天）
|
||||
- [ ] 直播场次 & 场均观看人次
|
||||
- [ ] 场均GMV & 累计GMV
|
||||
- [ ] 客单价（场均 / 整体）
|
||||
- [ ] 场均销量 & 转化率
|
||||
- [ ] 带货品类分布（Top5品类 & 各自占比）
|
||||
- [ ] 价格带偏好（主力价格区间 & 各区间占比）
|
||||
- [ ] 佣金偏好（历史合作佣金率范围）
|
||||
|
||||
### 口碑数据（有则填）
|
||||
- [ ] 退货/退款率
|
||||
- [ ] 差评率 / 店铺评分
|
||||
- [ ] 粉丝粘性指标（复购率 / 互动率）
|
||||
|
||||
### 内容风格（有则填）
|
||||
- [ ] 直播风格标签（如：专业测评 / 情绪带货 / 性价比 / 剧情）
|
||||
- [ ] 典型讲品时长（单品平均讲解时长）
|
||||
- [ ] 历史合作品牌（近期合作过的品牌 & 品类）
|
||||
|
||||
---
|
||||
|
||||
## 二、品-达人匹配判断
|
||||
|
||||
### 我方产品信息（必填）
|
||||
- [ ] 产品名称 & 品类
|
||||
- [ ] 价格 / 价格区间（日常价 & 直播活动价）
|
||||
- [ ] 佣金比例 / 合作佣金空间
|
||||
- [ ] 核心卖点（3-5个）
|
||||
- [ ] 目标人群画像（性别/年龄/消费力/痛点）
|
||||
- [ ] 产品资质/背书（专利、检测报告、明星同款等）
|
||||
- [ ] 库存 & 发货能力（是否支持一件代发/48h发货等）
|
||||
|
||||
### 达人侧信息（必填，同「达人画像」部分）
|
||||
- [ ] 达人历史带货品类分布
|
||||
- [ ] 达人价格带偏好
|
||||
- [ ] 达人佣金偏好
|
||||
- [ ] 达人粉丝画像
|
||||
|
||||
### 竞品参考（有则填）
|
||||
- [ ] 该达人是否带过同类竞品？效果如何？
|
||||
- [ ] 同类产品在该达人直播间的表现（GMV / 转化率 / 退货率）
|
||||
|
||||
---
|
||||
|
||||
## 三、讲品脚本生成
|
||||
|
||||
### 我方产品信息（必填）
|
||||
- [ ] 产品名称 & 品类
|
||||
- [ ] 价格机制（日常价 / 直播价 / 赠品 / 组合装）
|
||||
- [ ] 核心卖点（含功能、成分、使用场景、差异化优势）
|
||||
- [ ] 常见用户疑虑 & 对应的打消话术
|
||||
- [ ] 产品使用演示要点（如有）
|
||||
- [ ] 售后政策（退换货 / 质保 / 客服）
|
||||
|
||||
### 达人讲品风格参考（必填至少一项）
|
||||
- [ ] 达人历史讲品录屏 / 文字记录 / 切片链接
|
||||
- [ ] 达人常用话术风格（如：专业拆解型 / 痛点共鸣型 / 性价比轰炸型）
|
||||
- [ ] 达人单品平均讲解时长
|
||||
|
||||
### 直播间场景信息（有则填）
|
||||
- [ ] 目标直播类型（专场 / 混场 / 拼场）
|
||||
- [ ] 预计给我品的讲解时长
|
||||
- [ ] 是否有助播配合
|
||||
|
||||
---
|
||||
|
||||
## 通用补充
|
||||
|
||||
- [ ] 分析时间范围（近30天 / 近90天 / 自定义）
|
||||
- [ ] 是否有特殊关注点（如：重点看某个品类、关注退货率等）
|
||||
- [ ] 分析结果用途（达人筛选初筛 / 深度合作评估 / 复盘优化）
|
||||
@ -1,107 +0,0 @@
|
||||
# output-templates.md — 三类分析输出模板
|
||||
|
||||
## 一、达人画像分析 → 输出模板
|
||||
|
||||
```
|
||||
## 达人画像：{达人名称}
|
||||
|
||||
### 基础画像
|
||||
- 粉丝量：{数字}（来源：xxx）
|
||||
- 粉丝画像：性别比 / 年龄分布 / 城市等级 / 消费力
|
||||
- 账号类型：{品牌自播/KOL/KOC/明星/店播}
|
||||
|
||||
### 带货能力概览（{时间范围}）
|
||||
- 直播场次：{场}，场均观看：{人次}
|
||||
- 场均GMV：{金额}，累计GMV：{金额}
|
||||
- 客单价：{金额}，场均销量：{件}，转化率：{百分比}
|
||||
- 退货/退款率：{百分比}（如有）
|
||||
|
||||
### 选品逻辑
|
||||
- 主力品类：{Top3品类 + 各自占比}
|
||||
- 价格带偏好：{主力区间}，占比{百分比}
|
||||
- 佣金偏好：{范围}
|
||||
- 选品特征总结：{推断 + 依据}
|
||||
|
||||
### 内容风格
|
||||
- 风格标签：{xxx}
|
||||
- 单品讲解时长：{时长}
|
||||
- 近期合作品牌：{列举}
|
||||
|
||||
### 合作建议
|
||||
- 适合什么类型的产品
|
||||
- 不适合什么类型的产品
|
||||
- 推荐的合作方式
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 二、品-达人匹配 → 输出模板
|
||||
|
||||
```
|
||||
## 品-达人匹配判断
|
||||
|
||||
### 产品信息
|
||||
{产品名称} | {品类} | {价格} | {佣金}
|
||||
|
||||
### 达人信息
|
||||
{达人名称} | {粉丝量} | {主力品类}
|
||||
|
||||
### 匹配度评分：{1-5}分
|
||||
|
||||
### 匹配理由
|
||||
1. {匹配点1}（依据：{数据来源}）
|
||||
2. {匹配点2}
|
||||
3. ...
|
||||
|
||||
### 风险 / 不匹配点
|
||||
1. {风险点1}（依据：{数据来源}）
|
||||
2. ...
|
||||
|
||||
### 建议动作
|
||||
- 建议推进 → {具体建议}
|
||||
- 建议观望 → {原因 + 观望条件}
|
||||
- 建议放弃 → {原因}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 三、讲品脚本 → 输出模板
|
||||
|
||||
```
|
||||
## 讲品脚本：{产品名称} × {达人名称}
|
||||
|
||||
### 达人风格适配
|
||||
- 达人讲品风格：{xxx}
|
||||
- 建议讲解时长：{时长}
|
||||
- 脚本风格定位：{xxx}
|
||||
|
||||
### 脚本结构
|
||||
1. 开场钩子（{时长}秒）→ 吸引停留
|
||||
2. 痛点共鸣（{时长}秒）→ 建立需求
|
||||
3. 产品展示（{时长}秒）→ 卖点演示
|
||||
4. 信任背书（{时长}秒）→ 打消疑虑
|
||||
5. 价格机制（{时长}秒）→ 促单逼单
|
||||
6. 收尾逼单（{时长}秒）→ 引导下单
|
||||
|
||||
### 逐段话术
|
||||
---
|
||||
【开场钩子 · 预计{xx}秒】
|
||||
{话术内容}
|
||||
|
||||
【痛点共鸣 · 预计{xx}秒】
|
||||
{话术内容}
|
||||
|
||||
...
|
||||
---
|
||||
|
||||
### 高频问题应对
|
||||
| 用户疑虑 | 应对话术 |
|
||||
|----------|----------|
|
||||
| {疑虑1} | {话术} |
|
||||
| {疑虑2} | {话术} |
|
||||
|
||||
### 核心卖点覆盖检查
|
||||
- [ ] 卖点1
|
||||
- [ ] 卖点2
|
||||
- [ ] ...
|
||||
```
|
||||
Loading…
Reference in New Issue
Block a user