friends-db
by alexuser
Query and maintain Alex's local friends database stored in a private SQLite file under the OpenClaw workspace. Use when looking up a friend, finding phone/email/contact details, reading relationship notes, or updating those records. Prefer this over reading friends.md directly.
安装
claude skill add --url github.com/openclaw/skills/tree/main/skills/alexuser/friends-db文档
Friends DB
Use the helper script in scripts/friends_db.py. Do not run arbitrary SQL.
When to use
- A request depends on friend/contact details that used to live in
friends.md - You need a phone number, email, preferred name, or relationship note
- You need to track friendship cadence, last-seen dates, or activity ideas
- You need to add or update a friend fact after a conversation or event
- You need to sync past in-person interactions from calendar into the friend CRM
Commands
Initialize or migrate:
python3 ./skills/friends-db/scripts/friends_db.py migrate --source "$HOME/.openclaw/workspace/friends.md" --replace-with-stub
Search:
python3 ./skills/friends-db/scripts/friends_db.py search "lily"
python3 ./skills/friends-db/scripts/friends_db.py list
Show one contact:
python3 ./skills/friends-db/scripts/friends_db.py show "Lily Li"
python3 ./skills/friends-db/scripts/friends_db.py show "jerrypaulgreen@gmail.com"
Friend CRM overview:
python3 ./skills/friends-db/scripts/friends_db.py due-list
python3 ./skills/friends-db/scripts/friends_db.py due-list --status all --within-days 14
python3 ./skills/friends-db/scripts/friends_db.py profile "David Su"
python3 ./skills/friends-db/scripts/friends_db.py suggest "David Su"
CRM setup and updates:
python3 ./skills/friends-db/scripts/friends_db.py set-importance "David Su" high
python3 ./skills/friends-db/scripts/friends_db.py set-cadence "David Su" 21
python3 ./skills/friends-db/scripts/friends_db.py set-context "David Su" --home-area "South Bay" --best-times "weekday evenings"
python3 ./skills/friends-db/scripts/friends_db.py add-tag "David Su" interest pickleball
python3 ./skills/friends-db/scripts/friends_db.py add-tag "David Su" neighborhood "South Park"
Interaction logging:
python3 ./skills/friends-db/scripts/friends_db.py log-interaction "David Su" --type in_person --at 2026-03-15T18:30:00-07:00 --location "South Park"
python3 ./skills/friends-db/scripts/friends_db.py sync-calendar --days-back 180
General contact updates:
python3 ./skills/friends-db/scripts/friends_db.py add-fact "Lily Li" "Invited to dinner on 2026-03-20"
python3 ./skills/friends-db/scripts/friends_db.py set-method "David Su" phone "+14086246128" --primary
python3 ./skills/friends-db/scripts/friends_db.py set-preferred-name "Lily Li" "Lily"
Rules
- Keep the database in the hidden OpenClaw workspace state directory created by the helper.
- The helper enforces private filesystem permissions and parameterized SQL. Keep using it instead of shelling out to
sqlite3with raw user text. - Treat
friends.mdas a stub only after migration. The database is the source of truth. sync-calendaruses attendee email first, then title/description alias matches.- Count only
in_personinteractions toward the cadence target. Calls/texts/emails are supporting context. - Cadence defaults:
high=20,medium=30,low=90days. - Suggestions are local and deterministic; they come from tags plus the bundled activity template asset.
- Return only the fields needed for the task. Do not dump the whole contact database into chat unless Alex explicitly asks.
相关 Skills
数据库建模
by alirezarezvani
把需求梳理成关系型数据库表结构,自动生成迁移脚本、TypeScript/Python 类型、种子数据、RLS 策略和索引方案,适合多租户、审计追踪、软删除等后端建模与 Schema 评审场景。
✎ 把数据库结构设计、ER图梳理和SQL建模放到一处,复杂业务也能快速统一数据模式,少走不少返工弯路。
资深数据科学家
by alirezarezvani
覆盖实验设计、特征工程、预测建模、因果推断与模型评估,适合用 Python/R/SQL 做 A/B 测试、时序分析和生产级 ML 落地,支撑数据驱动决策。
✎ 从 A/B 测试、因果分析到预测建模一条龙搞定,既有硬核统计方法也懂业务沟通,特别适合把数据结论真正落地。
数据库设计
by alirezarezvani
聚焦数据库 Schema 设计与演进,自动检查规范化、数据类型、约束和索引问题,生成 ERD,并为零停机迁移、数据变更和回滚提供可执行方案。
✎ 专注数据库设计与数据建模,帮你快速理清表结构和关系,减少后期返工,SQL 落地也更顺手。
相关 MCP 服务
PostgreSQL 数据库
编辑精选by Anthropic
PostgreSQL 是让 Claude 直接查询和管理你的数据库的 MCP 服务器。
✎ 这个服务器解决了开发者需要手动编写 SQL 查询的痛点,特别适合数据分析师或后端开发者快速探索数据库结构。不过,由于是参考实现,生产环境使用前务必评估安全风险,别指望它能处理复杂事务。
SQLite 数据库
编辑精选by Anthropic
SQLite 是让 AI 直接查询本地数据库进行数据分析的 MCP 服务器。
✎ 这个服务器解决了 AI 无法直接访问 SQLite 数据库的问题,适合需要快速分析本地数据集的开发者。不过,作为参考实现,它可能缺乏生产级的安全特性,建议在受控环境中使用。
Firecrawl 智能爬虫
编辑精选by Firecrawl
Firecrawl 是让 AI 直接抓取网页并提取结构化数据的 MCP 服务器。
✎ 它解决了手动写爬虫的麻烦,让 Claude 能直接访问动态网页内容。最适合需要实时数据的研究者或开发者,比如监控竞品价格或抓取新闻。但要注意,它依赖第三方 API,可能涉及隐私和成本问题。