Safer agent skills

Job description data generation with LLM

C · Review first · Execution High

Benchmark any LLM against your data. Pick the best model, then make it better.

C · Review first · Execution High

LLM note

C · Review first · Execution High

GitHub repository yigitcetin/llm_bot; metadata recovered from GitHub Search API.

C · Review first · Execution High

Interpretable and Fine-Grained Fact-Checking for Vietnamese LLM Summaries

C · Review first · Execution High

llmwikify

C · Review first · Execution High

userfaultfd-based MMU illusion — transparent memory virtualization with 7µs page fault latency. Software-Defined NVLink for LLM inference. Part of the TIBET ecosystem.

C · Review first · Execution High

Articulating privacy design by answering LLM-generated multiple-choice questions

B · Good evidence · Execution High

LLM says no, notification is not pushed

C · Review first · Execution High

chat interface for llms; focusing on parallel connections

C · Review first · Execution High

GitHub repository estmon8u/LLM-Wiki-Knowledge-Base; metadata recovered from GitHub Search API.

C · Review first · Execution High

GitHub repository pje00427/llm-project; metadata recovered from GitHub Search API.

C · Review first · Execution High

LLM pipeline for structured prediction from noisy informal messages, with cycle-aware temporal inference and a WhatsApp-native HITL loop. An application to Fleet Tracking in Farming

B · Good evidence · Execution High

saas llm router

C · Review first · Execution High

Stanford-CME295-Transformers-&-LLMs

C · Review first · Execution High

GitHub repository JohnGavin/llmtelemetry; metadata recovered from GitHub Search API.

C · Review first · Execution High

GitHub repository HHepan/llm-finetune-webui; metadata recovered from GitHub Search API.

C · Review first · Execution High

get news from net, analyze them by LLM then report

C · Review first · Execution High

llm wiki

C · Review first · Execution High

A slick CLI companion for [Ollama] — interact with local LLMs from your terminal

C · Review first · Execution High

A Kubernetes operator that autonomously rebalances prefill and decode replica counts in an [llm-d](https://github.com/llm-d/llm-d) P/D disaggregated LLM inference cluster.

C · Review first · Execution High

A Streamlit app that uses OpenAI's LLM for natural language data analysis. Upload CSV files, ask questions in plain English, and get instant insights. Powered by PandasAI, it's designed for quick, code-free exploration of structured data.

C · Review first · Execution High

RAG search CLI for local LLM.

C · Review first · Execution High