Openclaw Nim Skill — Development skill for Claude Code
OpenClaw skill for offloading heavy tasks to NVIDIA NIM models and saving context tokens.
How to install Openclaw Nim Skill
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open d-wwei/openclaw-nim-skill and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Openclaw Nim Skill does
OpenClaw skill for offloading heavy tasks to NVIDIA NIM models and saving context tokens.
Alternatives in Development
- Om Standup — Morning kickoff 4.6k ★
- Code Review Graph — Local knowledge graph for Claude Code 3.7k ★
- Antigravity Claude Proxy — Proxy that exposes Antigravity provided claude / gemini models, so we can use them in Claude Code and OpenClaw 3.5k ★
README
OpenClaw NVIDIA NIM Skill
🚀 **Token-Saving Superpower for OpenClaw/Claude Code**
This skill integrates the **NVIDIA NIM (Inference Microservices)** platform into your OpenClaw environment. It allows you to "outsource" heavy tasks like summarization, long-form explanation, or deep reasoning to specialized models (GLM-5, Kimi-k2.5, DeepSeek R1, etc.) for FREE, saving up to 90%+ of your main agent's context tokens.
🌟 Features
- Multi-Model Support: Switch between top Chinese and Global models instantly.
- Zero Dependencies: Pure Python implementation using
urllib. - Token Efficiency: Keeps your main conversation lean by handling long inputs/outputs externally.
📦 Installation
- Clone this repo into your
skills/directory. - Get your free API Key from NVIDIA Build.
- Add
export NVIDIA_API_KEY="your-key"to your.zshrcor.bashrc.
🛠 Usage
In your OpenClaw session:
"Use /nim with kimi to summarize this long file: [path]"
Or via CLI:
python3 scripts/nim_call.py kimi "Summarize the history of AI"📜 License
MIT
Related Skills
Nim
Mostra o estado dos endpoints NIM de biologia da NVIDIA — quais respondem, quais mudaram de slug, quais sua li
Gain
Show how many context tokens mcp-multiplexer is saving you (startup withholding + on-demand schema serving)
Drupal Prime
Load full project context into session (debug/overview — heavy, ~2500 tokens)
Recursive Decomposition Skill
Handle long-context tasks (100+ files, 50k+ tokens) through recursive decomposition strategies based on RLM re
Free Claude Code
Nemo Code — FREE Claude Code alternative. NVIDIA open models + Claude Code CLI framework. One command install.
Claude Short Answer Skill
Initiate with /short - A Claude Code skill that switches output to summary-only mode - cutting reasoning, walk
Related Agents
Frame Describer
Describes video frames as detailed text. Used when frame_mode is "descriptions" to convert visual frames into
Mock Generator
Generates mock API responses and test data using local Ollama models. Saves cloud tokens.
Hephaestus
Autonomous deep implementation worker. Full tool access for complex coding tasks. Explores codebase patterns,
