/SKILL.md
微信聊天记录分析助手,用于查询、分析和导出本地微信数据库中的聊天数据。适用场景:(1) 查看与特定联系人或群组的聊天消息,(2) 通过关键词搜索跨会话消息,(3) 分析聊天模式、活跃度趋势或关系动态,(4) 导出多种格式的聊天记录(HTML/PDF/DOCX/CSV/XLSX),(5) 获取社交互动和沟通习惯的洞察,(6) 管理客户关系和跟进提醒,(7) 生成年度报告或统计数据,(8) 生成精美的可视化 HTML 页面。触发词:wetrace、微信、聊天记录、wechat、分析聊天、导出聊天、生成报告、生成仪表板,或任何涉及微信聊天数据分析、消息搜索或关系洞察的请求。
npx skillsauth add afumu/wetrace-skill wetraceInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
查询、分析和导出微信聊天数据,提供 AI 驱动的智能洞察和精美的可视化页面。
⚠️ 重要提示
- 本 Skill 依赖 Wetrace 服务
- 仅支持 Windows 平台(微信数据库位于 Windows 系统)
- 需要先安装并运行 Wetrace 服务才能使用本 Skill
http://127.0.0.1:5200将用户请求分类为以下类别:
从用户请求中识别关键参数:
本 Skill 提供了 Python 脚本工具来调用 Wetrace API,比直接使用 WebFetch 更方便。
使用 wetrace_api.py 脚本,位于 scripts/wetrace_api.py:
# 查询会话
python scripts/wetrace_api.py sessions --keyword "张三" --limit 20
# 获取消息
python scripts/wetrace_api.py messages --talker wxid_abc123 --limit 50
# 搜索关键词
python scripts/wetrace_api.py search --keyword "项目" --limit 30
# 分析数据
python scripts/wetrace_api.py analysis hourly wxid_abc123
python scripts/wetrace_api.py analysis daily wxid_abc123
# 导出聊天记录
python scripts/wetrace_api.py export chat --talker wxid_abc123 --format html
完整脚本文档:查看 scripts/README.md
基础 URL:http://127.0.0.1:5200/api/v1
完整 API 文档:参考 references/api.md
GET /sessions?keyword={名称}&limit=50
GET /messages?talker_id={id}&time_range={范围}&limit=100
GET /search?keyword={关键词}&time_range={范围}&limit=50
GET /analysis/hourly/{session_id}
GET /analysis/daily/{session_id}
GET /export/chat?talker={id}&format={格式}&time_range={范围}
以清晰、结构化的格式呈现数据。
调用导出 API,告知用户下载信息。
Wetrace 提供 8 个核心可视化功能,每个功能都会:
~/wetrace-exports/ 并提供访问链接当用户请求生成可视化页面时,根据触发关键词选择对应的功能:
智能摘要生成 - 触发词:总结聊天记录、生成摘要、智能总结
待办事项提取 - 触发词:提取待办、找出任务、待办事项
聊天活跃度热力图 - 触发词:活跃度热力图、聊天时间分布
互动趋势分析 - 触发词:趋势分析、互动趋势
智能周报月报 - 触发词:生成周报、生成月报
数据仪表板 - 触发词:生成仪表板、数据总览
智能对话摘要 - 触发词:对话摘要、智能总结、分类摘要
客户关系健康度 - 触发词:客户健康度、CRM 仪表板
所有生成的 HTML 页面都遵循统一的设计系统,详见 references/design-system.md,包括:
所有生成的 HTML 页面:
当用户请求生成网页时:
~/wetrace-exports/ 目录支持多种格式:
转换为 API 格式:YYYY-MM-DD~YYYY-MM-DD
对于大数据集:
limit=50 开始~/wetrace-exports/ 目录file:// 协议的完整路径脚本位置:scripts/wetrace_api.py
cd scripts
pip install -r requirements.txt
# 查看帮助
python wetrace_api.py --help
# 查询会话
python wetrace_api.py sessions --keyword "张三" --limit 20
# 获取消息(需要会话ID)
python wetrace_api.py messages --talker wxid_abc123 --limit 50
# 按时间范围查询
python wetrace_api.py messages --talker wxid_abc123 --time-range "2024-01-01~2024-01-31"
# 全文搜索
python wetrace_api.py search --keyword "项目" --limit 30
# 数据分析
python wetrace_api.py analysis hourly wxid_abc123
python wetrace_api.py analysis daily wxid_abc123
python wetrace_api.py analysis type wxid_abc123
# 获取总览
python wetrace_api.py dashboard
# 导出聊天记录
python wetrace_api.py export chat --talker wxid_abc123 --format html
from scripts.wetrace_api import WetraceAPI
# 创建API客户端
api = WetraceAPI()
# 查询会话
sessions = api.get_sessions(keyword="张三", limit=10)
for session in sessions:
print(f"{session['NickName']}: {session['MessageCount']} 条消息")
# 获取消息
messages = api.get_messages(talker_id="wxid_abc123", limit=50)
for msg in messages:
print(f"[{msg['CreateTime']}] {msg['Content']}")
# 搜索
result = api.search(keyword="项目", limit=20)
print(f"找到 {result['Total']} 条相关消息")
完整文档:查看 scripts/README.md
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.
development
End-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests. Use when Codex needs to run, rerun, debug, or interpret VM-based install, onboarding, gateway smoke tests, latest-release-to-main upgrade checks, fresh snapshot retests, or optional Discord roundtrip verification under Parallels.