skills.rest
ruvnet
ruvnetCOMMUNITY
Explore all skills by this author →
Website𝕏@ruvGitHub

chat-format

Formats prompts for multiple LLM providers with HNSW-based context retrieval.

70.1k|8.4k|Updated Jun 2, 2025
Search Tags:#context retrieval#HNSW#multi-provider#lLM#chat template#rAG#prompt formatting
One-click install
npx skills add https://github.com/ruvnet/claude-flow --skill chat-format
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: chat-format
Source: https://github.com/ruvnet/claude-flow/tree/main/plugins/ruflo-ruvllm/skills/chat-format
Command: npx skills add https://github.com/ruvnet/claude-flow --skill chat-format

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Different LLM providers (Claude, GPT, Gemini, Ollama, Cohere) require different prompt and message formats, making multi-provider inference and RAG pipelines tedious to build and maintain.

Core Features & Use Cases

  • Multi-Provider Prompt Formatting: Convert chat messages into the native format for Anthropic, OpenAI, Gemini, Ollama, or Cohere.
  • HNSW Context Retrieval: Create an HNSW index, add documents, and route queries to retrieve relevant context for RAG workflows.
  • Provider Status Checks: Verify provider availability before sending inference requests.
  • Use Case: Build a RAG pipeline that indexes your documentation, retrieves the most relevant passages for a user question, and formats the final prompt for whichever LLM provider is available.

Quick Start

Format my prompt for the OpenAI provider and retrieve relevant context from the indexed documents using HNSW routing.

Frequently Asked Questions about chat-format

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

FAQPage Schema
How do I format prompts for different LLM providers?▼

Call the ruvllm_chat_format tool with your messages and the target provider name. It converts the messages into the native format for Anthropic, OpenAI, Gemini, Ollama, or Cohere.

How to build a RAG pipeline with HNSW context retrieval?▼

Create an HNSW index with ruvllm_hnsw_create, add documents using ruvllm_hnsw_add, then route queries with ruvllm_hnsw_route to retrieve relevant context before formatting the final prompt.

Which LLM providers does chat formatting support?▼

The skill supports Anthropic (Claude), OpenAI (GPT), Google (Gemini), Ollama for local models, and Cohere. Each provider receives messages in its native chat or generate format.

Can I check LLM provider availability before sending requests?▼

Yes, call the ruvllm_status tool to check provider availability. This lets you verify which providers are reachable before formatting and sending inference requests.

When should I use HNSW routing instead of direct prompting?▼

Use HNSW routing when prompts need context from a document collection, such as question answering over documentation. Direct formatting is sufficient when no retrieval augmentation is needed.

Related Skills

Explore More Software Engineering Skills→
patronus-aipatronus-ai
2

rag-implementation

Build RAG systems using vector databases and semantic search.

Official
Intermediate
X-School-AcademyX-School-Academy
19

use-skill-agent

Executes user-defined prompts through the core AI engine and returns plain text output.

Official
Basic
xlelibertyxleliberty

rag-architect

Design and optimize Retrieval-Augmented Generation pipelines for document corpora.

Community
Advanced
jitenkr2030jitenkr2030

LLM

Build multi-turn LLM chat applications using the z-ai-web-dev-sdk.

Community
Intermediate