skills.rest
carson-sweet
carson-sweetCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

Reindex RAG

Rebuild RAG vector collections by parsing source files and updating the embedding index.

6|3|Updated Apr 12, 2026
Search Tags:#indexing#embeddings#rag#maintenance#corpus#data-recovery
One-click install
npx skills add https://github.com/carson-sweet/sweetclaude --skill reindex-rag
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Reindex RAG
Source: https://github.com/carson-sweet/sweetclaude/tree/main/skills/corpus-rag-reindex
Command: npx skills add https://github.com/carson-sweet/sweetclaude --skill reindex-rag

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill resolves issues with corrupted, outdated, or missing RAG embeddings by providing a structured, safe way to rebuild your project's knowledge base from source files.

Core Features & Use Cases

  • Targeted Reindexing: Choose between rebuilding canonical documentation, raw inbox files, or the entire corpus.
  • Safety Guardrails: Includes preflight checks to ensure the project is properly initialized and prevents accidental index deletion without user confirmation.
  • Use Case: If you have updated your documentation or notice that the AI is failing to retrieve relevant context, use this skill to refresh the underlying vector index.

Quick Start

Run the corpus-rag-reindex skill to rebuild your project RAG collections from the source files.

Frequently Asked Questions about Reindex RAG

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I rebuild corrupted RAG vector embeddings from source files?▼

To rebuild corrupted RAG vector embeddings, reindex the project corpus by parsing source files and updating the embedding index. This synchronizes your knowledge base with updated documentation or recovers lost vector data safely.

When do I need to reindex my RAG corpus?▼

You need to reindex your RAG corpus when existing embeddings are corrupted, lost, or failing to retrieve relevant context. It is also required to synchronize the vector index after updating source documentation or project content.

Can I choose specific files to reindex or must I rebuild the entire corpus?▼

You can perform targeted reindexing to rebuild specific parts of the project, choosing between canonical documentation, raw inbox files, or the entire corpus, rather than forcing a full rebuild of all source files.

Do I need an active MCP RAG server configuration to reindex embeddings?▼

Yes, repairing and rebuilding RAG collections requires an active MCP RAG server configuration and valid project state initialization. The skill includes preflight checks to verify this environment before safely executing the reindex.

Are there safety guardrails to prevent accidental index deletion during reindexing?▼

Safety guardrails include preflight checks ensuring proper project initialization and requiring explicit user confirmation before proceeding, preventing accidental index deletion when rebuilding your RAG vector collections.

Related Skills

Explore More Software Engineering Skills→
flashpoint493flashpoint493
1

VibeCollab — Setup Instructions for AI Assistants

Install and configure VibeCollab with MCP Server support for AI-assisted workflows.

Community
Intermediate
zerwizzerwiz

chroma

Stores embeddings and metadata in a vector database for semantic search and retrieval.

Community
Intermediate
projectedanxprojectedanx
1

qmd

Indexes and queries local markdown files and transcripts via hybrid BM25, vector embeddings, and LLM reranking search engine.

Community
Advanced
minh2004pdminh2004pd
18

docker-reset

Reset Qdrant vector data and mem0 memories via docker compose.

Community
Intermediate