Safer agent skills

GitHub repository xiongdi8888/llmdev; metadata recovered from GitHub Search API.

C · Review first · Execution High

A wear os LLM chat client app

C · Review first · Execution High

GitHub repository RonitRon23/llm-book-ecommerce; metadata recovered from GitHub Search API.

C · Review first · Execution High

🛠️ Optimize context management for large language models with efficient reranking and retrieval techniques in Python.

B · Good evidence · Execution High

A CLI test harness for evaluating local LLM code generation on TypeScript problems

C · Review first · Execution High

GitHub repository KimiaGholami/Sparse-LLMs-on-Loihi; metadata recovered from GitHub Search API.

C · Review first · Execution High

CHI 2026: Environmental Determinants of Norm Emergence in LLM Populations

C · Review first · Execution High

Checking Your Understanding of Leading LLMs

C · Review first · Execution High

Meshtastic to Telegram bridge with optional cloud/local LLM replies and Yandex weather

C · Review first · Execution High

LLM Flagship API Pricing Tracker (Jan 2025 — Present)

C · Review first · Execution High

💾 CLI utility to export PostgreSQL schemas to DBML format. Leverage pure SQL introspection to generate declarative data blueprints. Ideal for feeding LLMs, allowing AI to quickly and cheaply understand complex database structures without live querying.

C · Review first · Execution High

GitHub repository anjilinux/project-llmops-fastapi-faiss; metadata recovered from GitHub Search API.

C · Review first · Execution High

Functional emotional architecture for LLMs — 42 systems, 1994 tests, 27 psychological theories. Emergent emotions via 7 ANIMA pillars: predictive processing, global workspace, autobiographical memory, ontogenic development, motivational drives, emotional discovery, computational phenomenology.

C · Review first · Execution High

A four-probe benchmark for measuring attribution faithfulness in multi-factor LLM reasoning. Eight frontier models, CI-verified numeric claims, Zenodo-archived.

C · Review first · Execution High

GitHub repository mdl-systems/cocoro-llm-server; metadata recovered from GitHub Search API.

C · Review first · Execution High

commit messages using local LLM

B · Good evidence · Execution High

本项目是一个本地可运行的 AI 模拟面试系统，支持实时语音面试链路（STT -> LLM -> TTS）、简历解析、面试报告生成，重点针对 WSL2 + NVIDIA GPU 场景做了稳定性与性能优化。

C · Review first · Execution High

⚙️ Explore prompt engineering and security testing for Large Language Models like ChatGPT-5 and Gemini 2.5 in this educational repository.

C · Review first · Execution High

AI-driven autonomous red-blue team cyber operations framework for critical infrastructure defense. LLM-powered attack simulation and AI-augmented defense across energy grids and financial systems with 3D real-time visualization.

C · Review first · Execution High

Uses two LLMs depending on the escalation level and face-api for emotion vectors, which help the model tailor the chats

C · Review first · Execution High

GitHub repository LingengMa/llm-solution-for-code-warnings; metadata recovered from GitHub Search API.

C · Review first · Execution High

LLM Safety Alignment with WaRP

C · Review first · Execution High

ML Engineer - LLM systems, RAG, computer vision in production

C · Review first · Execution High