skills.rest
cyberpunk042
cyberpunk042COMMUNITY
Explore all skills by this author →
GitHub

infra-search

Configure and optimize multi-surface search pipelines for AICP across KB, code, and wiki sources.

Updated Mar 26, 2026
Search Tags:#grep#embedding#semantic-search#code-search#kb-search#rerank#localai
One-click install
npx skills add https://github.com/cyberpunk042/devops-expert-local-ai --skill infra-search
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: infra-search
Source: https://github.com/cyberpunk042/devops-expert-local-ai/tree/main/.claude/skills/infra-search
Command: npx skills add https://github.com/cyberpunk042/devops-expert-local-ai --skill infra-search

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manage and optimize multi-surface search for AICP, enabling semantic KB search, code-aware code search, and wiki-page lookup.

Core Features & Use Cases

  • Semantic KB search via LocalAI Collections embedded with nomic-embed, and reranked by bge-reranker.
  • Source code search using Grep/Glob with Claude Code integration and treesitter awareness.
  • Wiki page search through the second-brain CLI (python3 -m tools.view search) for lexical lookup across wiki content.

Quick Start

Load and configure semantic search surfaces to improve KB relevance.

Frequently Asked Questions about infra-search

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

FAQPage Schema
How do I configure semantic search across my knowledge base using LocalAI Collections?▼

Semantic KB search with LocalAI Collections uses nomic-embed for embeddings and bge-reranker for relevance reranking, accessible via the aicp --kb search command and aicp_kb_search_collection MCP tool.

What is the best way to search source code with grep and treesitter awareness?▼

Source code search uses Grep and Glob integrated with Claude Code, applying treesitter awareness to parse and query code structures for precise results across your codebase.

Can I search wiki pages locally using a second-brain CLI tool?▼

Wiki page search runs through the second-brain CLI using python3 -m tools.view search, performing lexical lookup across wiki content to find matching pages.

Do I need nomic-embed and bge-reranker to set up multi-surface search pipelines?▼

Yes, semantic KB search requires nomic-embed for generating embeddings and bge-reranker for the reranking stage, both running through LocalAI Collections to deliver relevant results.

How does multi-surface search orchestration work across KB, code, and wiki sources?▼

Multi-surface search orchestration configures separate pipelines for each source: LocalAI Collections for KB, Grep/Glob for code, and the second-brain CLI for wiki, enabling unified search across all surfaces.

Why does my semantic KB search return irrelevant results after embedding with nomic-embed?▼

Without the bge-reranker reranking stage applied after nomic-embed embedding, semantic KB search results may lack relevance; ensure the reranking pipeline is properly configured in LocalAI Collections.

Related Skills

Explore More Software Engineering Skills→
patricio0312revpatricio0312rev
5

vector-db-setup

Configure Pinecone, Chroma, pgvector, and Qdrant vector databases for semantic search.

Community
Advanced
JhabbigJhabbig

rag-implementation

Build retrieval-augmented generation systems that ground LLM answers in external knowledge.

Community
Advanced
JasonLoJasonLo

ss-validate-skills

Validate Claude Code skills for frontmatter, naming, and structural rules.

Community
Intermediate
an8079an8079
4

vector-search

Implement vector search with FAISS, Milvus, Qdrant, and Weaviate databases.

Community
Advanced