Install
openclaw skills install knowledge-base-collectorCollect and organize a personal knowledge base from URLs (web/X/WeChat) and screenshots. Use when the user says they want to save an URL, ingest a link, archive content to KB, tag/classify notes, store screenshots, or search their saved knowledge in Telegram. Supports WeChat via a connected macOS node when cloud fetch is blocked.
openclaw skills install knowledge-base-collectorcontent.md + meta.json and a global index.jsonl#agent, #coding-agent, #claude-code, #mcp, #rag, #prompt-injection, #security, #pricing, #database)把用户发来的链接/截图沉淀到共享知识库(KB),并做标签化整理。
/home/ubuntu/.openclaw/kbkb/20_Inbox/urls/index.jsonlkb/20_Inbox/urls/<YYYY-MM>/<item>/content.md + meta.json目标:先入库不丢,再迭代“摘要/标签/检索”。
运行脚本:
python3 /home/ubuntu/.openclaw/skills/knowledge-base-collector/scripts/ingest_url.py "<URL>" --tags "#optional" --note "context"
行为:
r.jina.ai 抽取正文(无需登录)status=blocked_verification + tag #needs-manual当云端抓取命中“环境异常/验证”时:
Reed-Mac)且该节点能访问该文章,可用 nodes.run 在节点上执行抓取(requests+bs4),然后写入 KB。脚本:
python3 /home/ubuntu/.openclaw/skills/knowledge-base-collector/scripts/ingest_image.py /path/to/image.jpg \
--text-file /path/to/ocr.txt \
--title "..." --tags "#ai #product" --note "..."
说明:
ingest_image.py 负责“落盘+索引”。OCR 可用:
tesseract-ocr + chi_sim)--text-file推荐先用脚本(本机/服务器):
python3 /home/ubuntu/.openclaw/skills/knowledge-base-collector/scripts/search_kb.py --q "claude code" --limit 10
python3 /home/ubuntu/.openclaw/skills/knowledge-base-collector/scripts/search_kb.py --tags "#claude-code #coding-agent" --limit 20
python3 /home/ubuntu/.openclaw/skills/knowledge-base-collector/scripts/search_kb.py --source wechat --since 7d --q "Elys"
python3 /home/ubuntu/.openclaw/skills/knowledge-base-collector/scripts/wechat_backlog.py --limit 30
python3 /home/ubuntu/.openclaw/skills/knowledge-base-collector/scripts/weekly_digest.py --days 7 --limit 30
REDACTED)。