Self-hosted alternatives to agent-self-evaluation

A

agent-self-evaluation

Use after completing any non-trivial task

agent-self-evaluation is an agent skill from ECC, Affaan Mustafa's open-source agentic engineering toolkit, listed on skills.sh. It has the agent rate its own work on a five-axis rubric after a non-trivial task, to catch omissions and overconfidence before you do. A skill is a SKILL.md file of instructions (sometimes with scripts and reference notes) that an AI agent loads only when a task calls for it, so the agent knows the steps to follow and what to avoid. It is free and open source.