llm-config — Claude Code skill: what it does, how to install
Configures RuVLLM local inference and manages in-memory MicroLoRA and SONA adapters using quality feedback scores.
npx skills add ruvnet/ruflo --skill llm-config -a claude-codeWhat llm-config does
This skill configures offline RuVLLM deployments through MCP tools. It checks runtime status and generates local model parameters. Training datasets are not used here.
Instead of full training runs, adapters update small in-process weights from numeric quality signals between 0.0 and 1.0. These adapters live strictly inside MCP server memory. A restart wipes them out immediately. You have to track returned IDs and recreate instances yourself.
Both adaptation tools fail if @ruvector/ruvllm-wasm is missing. When status checks return wasm.available: false, install the dependency via npm i -g @ruvector/ruvllm-wasm. This tooling cannot export adapter files or fine-tune hosted API models.
What it helps with
- generate configuration parameters for RuVLLM local inference
- spin up low-rank MicroLoRA adapters with rank settings from 1 to 4
- set up SONA real-time adaptation instances with custom hidden dimensions
- adjust in-memory weights using numeric quality feedback scores
Example prompts for the agent
- Check RuVLLM status and generate a configuration for my local model
- Create a MicroLoRA adapter with rank 2 and input dimension 1024
- Pass a quality score of 0.85 to update the SONA adapter instance sona_1
How to install llm-config
1Skills CLI (Vercel)
npx skills add ruvnet/ruflo --skill llm-config -a claude-code2Manually: put the files in place
~/.claude/skills/llm-config/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/llm-config/
1Skills CLI (Vercel)
npx skills add ruvnet/ruflo --skill llm-config -a codex2Manually: put the files in place
.agents/skills/llm-config/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add ruvnet/ruflo --skill llm-config -a cursor2Manually: put the files in place
.cursor/skills/llm-config/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install ruvnet/ruflo llm-config2Manually: put the files in place
.github/skills/llm-config/SKILL.md1Skills CLI (Vercel)
npx skills add ruvnet/ruflo --skill llm-config -a gemini-cli2Platform CLI
gemini skills install https://github.com/ruvnet/ruflo --path plugins/ruflo-ruvllm/skills/llm-configManually: put the files in place
.devin/skills/llm-config/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add ruvnet/ruflo --skill llm-config -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about llm-config
How to install llm-config in Claude Code?
Run npx skills add ruvnet/ruflo --skill llm-config -a claude-code. This installs the skill file into ~/.claude/skills/llm-config/SKILL.md.
What does llm-config do?
It prepares RuVLLM configs and manages runtime MicroLoRA and SONA adapters that adjust in memory via feedback scores.
Does llm-config save adapter checkpoints to disk?
No. MicroLoRA and SONA instances reside in MCP server RAM and reset whenever the process restarts.
Source text
SKILL.md · MIT
--- name: llm-config description: Configure RuVLLM local inference helpers: generate a config, and create and adapt in-process MicroLoRA and SONA instances from quality signals. Use when you need local, air-gapped inference tooling, not for fine-tuning hosted models. argument-hint: "[--model MODEL] [--adapter microlora|sona]" allowed-tools: mcp__plugin_ruflo-core_ruflo__ruvllm_generate_config mcp__plugin_ruflo-core_ruflo__ruvllm_status mcp__plugin_ruflo-core_ruflo__ruvllm_microlora_create mcp__plugin_ruflo-core_ruflo__ruvllm_microlora_adapt mcp__plugin_ruflo-core_ruflo__ruvllm_sona_create mcp__plugin_ruflo-core_ruflo__ruvllm_sona_adapt Bash --- # LLM Configuration Configure RuVLLM for local inference and fine-tuning. ## When to use When you need to configure local LLM inference, create MicroLoRA adapters for task-specific fine-tuning, or set up SONA for real-time adaptation. ## Steps 1. **Check status** — call `mcp__plugin_ruflo-core_ruflo__ruvllm_status` to see current model and adapter state. If `wasm.available` is `false`, install the add-on first (`npm i -g @ruvector/ruvllm-wasm`, or without `-g` in a project) — the MicroLoRA and SONA tools cannot run without it 2. **Generate config** — call `mcp__plugin_ruflo-core_ruflo__ruvllm_generate_config` with model parameters 3. **Create MicroLoRA** — call `mcp__plugin_ruflo-core_ruflo__ruvllm_microlora_create` with `inputDim`, `outputDim`, `rank` (1-4, default 2) and `alpha` 4. **Adapt MicroLoRA** — call `mcp__plugin_ruflo-core_ruflo__ruvllm_microlora_adapt` with `loraId` and a `quality` signal (0.0-1.0), optional `learningRate` and `success`. It takes a feedback score, not a training set 5. **Create SONA** — call `mcp__plugin_ruflo-core_ruflo__ruvllm_sona_create` with `hiddenDim` (default 64), `learningRate` and `patternCapacity` 6. **Adapt SONA** — call `mcp__plugin_ruflo-core_ruflo__ruvllm_sona_adapt` with `sonaId` and a `quality` signal (0.0-1.0) ## MicroLoRA vs SONA | Feature | MicroLoRA | SONA | |---------|-----------|------| | What it is | Ultra-light LoRA adapter, rank 1-4 | Instant adaptation loop (the tool describes <1ms cycles) | | Input | `quality` feedback per call | `quality` feedback per call | | Persistence | None: instances live in the MCP server's memory and are lost on restart | None: same | Neither tool fine-tunes a hosted model or writes adapter files; both adjust small in-process weights from quality scores. Keep the returned `loraId` / `sonaId` for later calls, and re-create them after a restart. For the repo's measured SONA latency see `docs/reviews/intelligence-system-audit-2026-05-29.md`.
© ruvnet · MIT · ruvnet/ruflo
