hugging-face-evaluation
[ Official ]hugging-face-evaluation is a skill for managing evaluation results in Hugging Face model cards, supporting multiple data sources and formats.
Browse and install thousands of AI Agent skills in the Killer-Skills directory. Supports Claude Code, Windsurf, Cursor, and more.
hugging-face-evaluation is a skill for managing evaluation results in Hugging Face model cards, supporting multiple data sources and formats.
generate-swimlane-swim-solution is a skill that generates a Lit Element Solution using SwimlaneElement and custom Lit elements
aget-check-evolution is a directory health monitoring skill that checks file counts, types, naming conventions, and disk usage in the .aget/evolution/ directory.
Monitor .aget/evolution/ directory health. Validates file counts, naming conventions, disk usage, and returns health status with alerts on anomalies.
Monitor .aget/evolution/ directory health. Validates file counts, naming conventions, disk usage, and returns health status with alerts on anomalies.
Monitor .aget/evolution/ directory health. Validates file counts, naming conventions, disk usage, and returns health status with alerts on anomalies.
Monitor .aget/evolution/ directory health. Validates file counts, naming conventions, disk usage, and returns health status with alerts on anomalies.
guardian-evolution-system is a design and implementation framework for the evolution of AI companions, from Level 1 Spark to Level 50 Transcendent.
Oris is an AI Self-Evolution Framework for closed-loop software improvement.
agent-evaluation is a LLM-as-judge evaluation framework that scores AI-generated content on 5 dimensions using a 1-5 rubric.
Evaluation is a process of assessing agent systems using different approaches than traditional software
issue-resolution is a systematic process using iterative diagnosis and verified fixes to resolve issues, leveraging technologies like Next.js and Supabase.