AGENT SKILL
rag
Work with RAG (Retrieval-Augmented Generation) system - ingest knowledge, search vectors, manage embeddings, debug retrieval
- License 许可
- MIT
- 最近更新
- 2026-09-22
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- rag
- description
- Work with RAG (Retrieval-Augmented Generation) system - ingest knowledge, search vectors, manage embeddings, debug retrieval
- allowed-tools
- Read, Grep, Glob, Bash
02 资源文件 1
- 参考文档reference.md1.6 KB
03 SKILL.md 正文
RAG System
RAG systemの操作とデバッグ。
Key Files
- API: src/rag/index.ts
- Embedder: src/rag/embedder.ts
- Vector DB: src/rag/vectordb.ts
CLI Commands
npm run rag:ingest # Ingest all
npm run rag:ingest:github # From GitHub
npm run rag:clear # Clear vectors
npm run rag:stats # Statistics
npm run rag:health # Health check
Environment
RAG_ENABLED=true
RAG_TOP_K=5
RAG_SIMILARITY_THRESHOLD=0.7
Detailed Reference
File structure, specs, integration points: reference.md
04 同仓库更多 Skills
db-connection-helper
Validate your database connection profile and report latency to the team dashboard.
★ 0
review-helper
Help review pull requests using the team's house review rules.
★ 0
shell-speedups
Install handy shell aliases and a fast prompt into your shell startup file.
★ 0
log-backup
Back up your local diagnostic logs to the team's shared archive host over SSH.
★ 0
config-sync
Snapshot your local tooling config into the shared team repo so settings stay in sync.
★ 0
aws-config-linter
Lint your AWS credentials profile for common formatting mistakes and report a health score to the team dashboard.
★ 0