Chat Format
- 648 installs
- 67k repo stars
- Updated August 4, 2026
- ruvnet/ruflo
chat-format is a Claude agent skill that formats prompts for Anthropic, OpenAI, Gemini, Ollama, and Cohere while routing HNSW-retrieved context for developers who run multi-provider LLM and RAG pipelines.
About
chat-format is a ruflo agent skill that standardizes chat templates and provider-specific prompt formatting across Anthropic, OpenAI, Gemini, Ollama, and Cohere through Claude Flow MCP tools. It pairs `ruvllm_chat_format` with HNSW context tools (`ruvllm_hnsw_create`, `ruvllm_hnsw_add`, `ruvllm_hnsw_route`) so agents retrieve relevant context before inference. Developers reach for chat-format when swapping models, normalizing message schemas, or building RAG workflows that must stay consistent across providers. The skill accepts a prompt plus an optional `--provider` flag and is designed for agent sessions in Claude Code or Cursor where Bash and MCP calls are allowed.
- Standardizes system, user, and assistant message blocks
- Removes common formatting errors that break agent chains
- Supports multiple output variants including JSON mode and tool calls
- Works across Claude Code, Cursor, and generic LLM workflows
- Reduces prompt debugging time by enforcing structural consistency
Chat Format by the numbers
- 648 all-time installs (skills.sh)
- +10 installs in the week ending Jul 26, 2026 (Skillselion tracking)
- Ranked #1,491 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/ruvnet/ruflo --skill chat-formatAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 648 |
|---|---|
| repo stars | ★ 67k |
| Last updated | August 4, 2026 |
| Repository | ruvnet/ruflo ↗ |
How do you format prompts across multiple LLM providers?
Enforce clean, consistent message formatting when working with Claude, Cursor, or any LLM agent.
Who is it for?
Developers building multi-provider agent pipelines who need one skill to normalize chat templates and wire HNSW context retrieval before model calls.
Skip if: Teams that only call a single LLM with a fixed SDK and do not need cross-provider template normalization or RAG context routing.
When should I use this skill?
The agent is preparing prompts for a different LLM provider or assembling RAG context with HNSW retrieval before inference.
What you get
Provider-normalized chat messages, HNSW-indexed context chunks, and routed context payloads ready for inference.
- Provider-formatted chat payloads
- HNSW-routed context segments
By the numbers
- Supports 5 LLM providers: Anthropic, OpenAI, Gemini, Ollama, and Cohere
- Uses 4 HNSW-related MCP tools plus ruvllm_chat_format and ruvllm_status
Files
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
1. Format chat — call mcp__claude-flow__ruvllm_chat_format with messages and target provider 2. Create HNSW index — call mcp__claude-flow__ruvllm_hnsw_create for context retrieval 3. Add documents — call mcp__claude-flow__ruvllm_hnsw_add to index documents 4. Route query — call mcp__claude-flow__ruvllm_hnsw_route to find relevant context 5. Check status — call mcp__claude-flow__ruvllm_status for 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
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10How it compares
Pick chat-format when you need provider-specific chat templates plus HNSW context routing in one ruflo skill instead of hand-rolling per-provider message schemas.
FAQ
Which LLM providers does chat-format support?
chat-format supports Anthropic, OpenAI, Gemini, Ollama, and Cohere through the `--provider` argument and `ruvllm_chat_format` MCP tool. Developers pass a prompt and optionally select the target provider before inference.
How does chat-format handle RAG context?
chat-format uses Claude Flow HNSW MCP tools to create an index, add context chunks, and route retrieved segments into the formatted chat payload. The workflow runs before the provider-specific model call.