chat-format
Format prompts for different LLM providers with chat templates and HNSW-powered context retrieval
Best for RAG workflowsWorks with GitHubLow risk
⌘source
- author
@ruvnet- repo
- ruvnet/ruflo
- language
- TypeScript
★46kstars
5.1kforks
May 5, 2026
✦overview.md
Key Features
- ·Multi-provider prompt formatting
- ·HNSW-powered context retrieval
- ·Provider status checks
- ·Step-by-step pipeline
Use Cases
- →Formatting prompts for a Claude vs GPT comparison test
- →Building a RAG pipeline with HNSW indexing
- →Switching between local and cloud LLM providers
Best for
- ✓RAG workflows
- ✓multi-provider experimentation
Not ideal for
- !simple single-provider prompts
- !non-LLM formatting
name
chat-format
description
Format prompts for different LLM providers with chat templates and HNSW-powered context retrieval
argument-hint:<prompt> [--provider anthropic|openai|local]
allowed-tools:mcp__claude-flow__ruvllm_chat_format mcp__claude-flow__ruvllm_hnsw_create mcp__claude-flow__ruvllm_hnsw_add mcp__claude-flow__ruvllm_hnsw_route mcp__claude-flow__ruvllm_status Bash
Chat Format
Format prompts for multi-provider LLM inference with context retrieval.
When to use
When preparing prompts for different LLM providers (Claude, GPT, Gemini, Ollama) or building RAG pipelines with HNSW-powered context retrieval.
Steps
- Format chat — call
mcp__claude-flow__ruvllm_chat_formatwith messages and target provider - Create HNSW index — call
mcp__claude-flow__ruvllm_hnsw_createfor context retrieval - Add documents — call
mcp__claude-flow__ruvllm_hnsw_addto index documents - Route query — call
mcp__claude-flow__ruvllm_hnsw_routeto find relevant context - Check status — call
mcp__claude-flow__ruvllm_statusfor provider availability
Supported providers
- Anthropic (Claude) — native format
- OpenAI (GPT) — chat completion format
- Google (Gemini) — generative AI format
- Ollama — local model format
- Cohere — generate/chat format
$install
1-click copynpx skills add ruvnet/ruflo --skill chat-formatSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
4/ 5
very goodClear and well structured, with only minor parts that might need a second read.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
4/ 5
highMostly actionable with clear steps; only a few small gaps remain.