菜单
Generate semantic embeddings for a repository's code symbols
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Use when the user wants their Kimi CLI agent to self-improve from past usage, asks about a nightly/offline "sleep" or "dream" cycle, memory/skill consolidation, or says things like "make my agent better the more I use it", "review my past sessions", "learn my preferences", "consolidate what you learned", "run the sleep cycle", or wants to schedule offline self-optimization.
Generate a structured knowledge report for a repository
Search across all registered repositories using hybrid (vector + keyword) search
基于 SOC 职业分类
| name | embed-repo |
| version | 1.0.0 |
| description | Generate semantic embeddings for a repository's code symbols |
| author | devbase-team |
| tags | ["embedding","semantic-search","indexing"] |
| skill_type | builtin |
| inputs | [{"name":"repo_id","type":"string","description":"Target repository ID in devbase","required":true},{"name":"device","type":"string","description":"Device for embedding model (cpu, cuda, auto)","default":"auto"}] |
| outputs | [{"name":"status","type":"string","description":"Completion status"}] |
This skill invokes the local embedding provider (examples/embedding-provider/local.py)
to generate 384-dimensional vectors for all code symbols in the specified repository.
devbase skill run embed-repo --arg repo_id=devbase --arg device=cuda
The entry script locates local.py relative to the devbase workspace and runs it
with the provided --repo-id and --device arguments.