Agent skill
Local Deep Research Guide
Deep research agent searching 10+ sources with local or cloud LLMs
OpenClawData & Analytics
wentorai307
Agent skills
Reusable instructions for compatible AI agents.
Explore by field
Loading catalog totals…Counts cover every published resource in this section. A resource can belong to several fields and platforms.
Resources
Search resultsAgent skill
Model Sovereignty
This skill should be used when the user asks about "local models", "custom models", "fine-tuning", "self-hosting models", "model selection", "which model should I use", "data privacy and models", "LoRA", "RAG vs fine-tuning", "Ollama", "vLLM", or wants guidance on whether to build, host, or custo...
OpenClawData & Analytics
Habitat-Thinking34
Apache-2.0View resource
Agent skill
lm-evaluation-harness - LLM Benchmarking
lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).
OpenClawData & Analytics
CUexter2
Agent skill
vLLM - High-Performance LLM Serving
vLLM: high-throughput LLM serving, OpenAI API, quantization.
OpenClawData & Analytics
CUexter2
Agent skill
LLM-Assisted Dataset Curation
Use locally-hosted LLMs (vLLM/SGLang) for dataset filtering, quality scoring, rewriting, labeling, and synthetic data generation. Covers LLM-as-judge scoring, structured output filtering, batch inference pipelines, and 2025-2026 techniques (DataRater, perplexity filtering, curriculum scoring, LLM...
OpenClawData & Analytics
mkurman312
Agent skill
local-llm-expert
Master local LLM inference, model selection, VRAM optimization, and local deployment using Ollama, llama.cpp, vLLM, and LM Studio. Expert in quantization formats (GGUF, EXL2) and local AI privacy.
OpenClawData & Analytics
Satya136-dvsn1
Agent skill
vLLM Ascend Model Adapter
Adapt and debug existing or new models for vLLM on Ascend NPU. Implement in /vllm-workspace/vllm and /vllm-workspace/vllm-ascend, validate via direct vllm serve from /workspace, and deliver one signed commit in the current repo.
OpenClawData & Analytics
vllm-project2,206
Apache-2.0View resource
Agent skill
vLLM - High-Performance LLM Serving
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
OpenClawDevelopment & Engineering
davila727,917
Agent skill
vLLM - High-Performance LLM Serving
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
OpenClawDevelopment & Engineering
Dicklesworthstone1,169
Agent skill
Deployment Skill
Serve a quantized or unquantized LLM checkpoint as an OpenAI-compatible API endpoint using vLLM, SGLang, or TRT-LLM. Use when user says "deploy model", "serve model", "start vLLM server", "launch SGLang", "TRT-LLM deploy", "AutoDeploy", "benchmark throughput", "serve checkpoint", or needs an infe...
OpenClawDevelopment & Engineering
yo-steven0
Apache-2.0View resource
Agent skill · Reference
llm-serving-patterns
Agent skill for ML / AI Engineer, Data Engineer, Backend Developer, published by melodic-software. Project details and file access are provided by the publisher.
OpenClawDevelopment & Engineering
melodic-software79
Agent skill · Reference
llm-serving-patterns
Agent skill for ML / AI Engineer, Data Engineer, Backend Developer, published by melodic-software. Project details and file access are provided by the publisher.
OpenClawDevelopment & Engineering
melodic-software79
Not specifiedView resource
No matching resources
Try a broader search or clear some filters.
Platform labels describe intended use. Read each resource's author credits, requirements and available access methods.