Browsing:

copyleftdev

Distributed adversarial behavioral security evaluation framework for LLMs - Swarm-based parallel probing with cryptographic consensus

comet-ml

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

qte77

A Multi-Agent System (MAS) evaluation framework using PydanticAI that generates and evaluates scientific paper reviews through a three-tiered assessment approach: traditional metrics, LLM-as-a-Judge, and graph-based complexity analysis.

mgaldino

review-paper is a specialized AI agent skill designed for editors to review and evaluate manuscripts using a dual-agent approach

sunholo-data

Benchmark Manager is a skill that manages AILANG evaluation benchmarks with features like prompt integration, debugging, and best practices for AI model evaluation.

xxl-novels

manuscript-reviewer is a specialized AI agent skill designed for evaluating manuscripts based on specific platform requirements, applying weighted assessments and generating detailed review reports

hoanghd218

ck:research is a research methodology that follows a phased approach, including scope definition and systematic information gathering, to provide concise and honest research results.

VjayRam

dspy-expert is an AI Agent skill designed to help developers build and optimize programs using the DSPy framework. It emphasizes simple program structure, measurable iteration through a dataset→metric→compile loop, and compatibility with local OpenAI endpoints like Ollama, vLLM, and LM Studio.

atondwal

Taiga-api is a Python-based interface for querying the Taiga evaluation platform API, enabling developers to retrieve job results, transcripts, and problem runs.

d-o-hub

TEST - A modular Rust-based self-learning episodic memory system for AI agents, featuring hybrid storage with Turso (SQL) and redb (KV), async execution tracking, reward scoring, reflection, and pattern-based skill evolution. Designed for real-world applicability, maintainability, and scalable agent workflows.