
Ima Knowledge Base
This connects Claude to the IMA knowledge base API for search, upload, and content management. You'd use it when someone asks to search their knowledge base, upload files, or import web pages. The tool defaults to keyword search and returns content snippets directly rather than dumping metadata. It handles Chinese language queries well and includes smart rules like using broader searches for recommendation questions, then narrowing down with inspect commands for OCR or image heavy results. Setup requires copying client_id and api_key from the IMA mobile app's Claw configuration screen. The documentation is thorough about execution patterns, which matters since search behavior and result filtering have specific conventions you'll want to follow.
- skills.sh installs
- 234
- GitHub stars
- 784
- last updated
- Jun 1, 2026
Install
$ npx -y skills add countbot-ai/countbot --skill ima-knowledge-base --agent claude-codeInstalls into .claude/skills of the current project.
Files
IMA Knowledge Base
入口:
python skills/ima-knowledge-base/scripts/ima_kb_tool.py <command> ...
执行规则
- 用户说“搜、查、找、看看有没有”时,先
search-kb - 默认直接返回命中片段,不堆字段
search-kb搜的是内容,不是知识库列表- 用户给了
kb-id或kb-name时,加定向参数 - 默认优先
--keyword,只有明确要把多个词合成一次搜索串时才用--query - 宽搜建议加
--show 5 --limit 10;知识库很大再加--search-pages 2或更高
查看单条结果
- 默认先
show-kb-hit - 只有命中像图片、截图、OCR 文档、菜单图,或
show-kb-hit太短时,才用inspect-kb-hit - 一条
--keyword "推荐 菜单 餐厅 美食"会拆成多次搜索,同一标题可能重复出现 - 宽搜后稳定定位优先级:更窄关键词 >
--title>--media-id>--pick
常用命令
Sponsors
Details
- Repository
- github.com/countbot-ai/countbot
- License
- MIT
- First seen
- Jun 11, 2026