chat-format
Format prompts for different LLM providers with chat templates and HNSW-powered context retrieval
Profile →npx skills add ruvnet/ruflo --skill chat-format --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# 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__plugin_ruflo-core_ruflo__ruvllm_chat_format` with messages and target provider 2. **Create HNSW index** — call `mcp__plugin_ruflo-core_ruflo__ruvllm_hnsw_create` for context retrieval 3. **Add documents** — call `mcp__plugin_ruflo-core_ruflo__ruvllm_hnsw_add` to index documents 4. **Route query** — call `mcp__plugin_ruflo-core_ruflo__ruvllm_hnsw_route` to find relevant context 5. **Check status** — call `mcp__plugin_ruflo-core_ruflo__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
- When to use
- Steps
- Supported providers
What does the chat-format skill do?
Format prompts for different LLM providers with chat templates and HNSW-powered context retrieval
How do I install it?
Run `npx skills add ruvnet/ruflo --skill chat-format --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From ruvnet/ruflo, a repository with 67,015 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.