Unitxt
IBM
🦄 Unitxt is a Python library for enterprise-grade evaluation of AI performance, offering the world's largest catalog of tools and data for end-to-end AI benchmarking
Ml AutomationReview before use
214GitHub
OPENAGENTSKILL / DIRECTORY
AI Agent Skills
Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.
Results · “continuous-benchmarking”
49–54 / 54
More filters
Results: 54
Pneuma Skills
pandazki
Co-creation infrastructure for humans and code agents — visual environment, skills, continuous learning, and distribution.
149GitHub
135GitHub
Holon
holon-run
A local workbench for agents doing continuous work across sessions, commands, human input, and external events.
CodingReview before use
123GitHub
XRAG
DocAILab
XRAG: eXamining the Core - Benchmarking Foundational Component Modules in Advanced Retrieval-Augmented Generation
117GitHub
Blackdagger
ErdemOzgen
Blackdagger is a DAG based automation tool specifically used in DevOps, DevSecOps, MLOps, MLSecOps, and Continuous Red Teaming (CART).
DevopsReview before use
116GitHub
External platform skills
Browse external directory →Owner-curated external sources. Not filtered by the scores or compatibility controls above; excluded from GitHub rankings and automatic installation.
No external entries match this query.
Guides & comparisons
- AI agent skills library ↗
- Open source AI agent skills ↗
- Best Codex skills ↗
- Best AI agent skills for stock analysis ↗
- Best Codex skills for web scraping ↗
- Best Claude Code skills for PDF parsing ↗
- Best AI agent skills for football analytics ↗
- OpenAgentSkill vs skills.sh ↗
- OpenAgentSkill vs agentskills.io ↗