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。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/tomevault-io/skills-registry --skill ingesting-rag-content命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
| Use when this capability is needed.
> Use when this capability is needed.
Review architecture and API design for the vfs-s3 project. Use when the user mentions @architect, asks to review an issue's design, discuss module boundaries, API shape, or architectural decisions for vfs-s3. Also trigger when the user wants to create an ADR (Architecture Decision Record) or evaluate a technical approach for the project. Intended for dispatch from Codex automation or Claude routines; GitHub trigger phrase: @vfs-s3-bot please prepare design doc Use when this capability is needed.
基于 SOC 职业分类
正在显示 SKILL.md
| name | ingesting-rag-content |
| description | Specialized skill for ingesting rag content Use when this capability is needed. |
| metadata | {"author":"gitwalter"} |
Automated process for indexing new documents into the factory's Qdrant vector store using standardized Parent-Child retrieval patterns.
cursor-factory env active.D:/ebooks or target document path.antigravity-rag MCP server active (configured in %USERPROFILE%\.gemini\antigravity\mcp_config.json).@tool mcp_antigravity-rag_ingest_document with the absolute path.list_library_sources to confirm registration.scripts/validate_ingestion.py: Runs a health check on the Qdrant ebook_library collection.scripts/ai/rag/rag_optimized.py: The core ingestion engine logic.references/rag-architecture.md: Explains the Parent-Child chunking strategy and Qdrant storage schema.$env:PYTHONIOENCODING="utf-8") are set.BAAI/bge-small-en-v1.5 (via FastEmbed) for performance.scripts/validate_ingestion.py after bulk ingestion.
---
> Converted and distributed by [TomeVault](https://tomevault.io/claim/gitwalter) — claim your Tome and manage your conversions.
<!-- tomevault:4.0:skill_md:2026-04-13 -->