Encodes a continuous improvement loop for goal-seeking agents: EVAL, ANALYZE, RESEARCH (hypothesis + evidence + counter-arguments), IMPROVE, RE-EVAL, DECIDE. Auto-commits improvements (+2% net, no regression >5%) and reverts failures. Works with all 4 SDK implementations. Auto-activates on "improve agent", "self-improving loop", "agent eval loop", "benchmark agents", "run improvement cycle".
Quickly install self-improving-agent-builder AI skill to your development environment via command line
Source: rysweet/amplihack.
Run a closed-loop improvement cycle on any goal-seeking agent implementation:
Each iteration measures L1-L12 progressive test scores, identifies failures with erroranalyzer.py, runs a research step with hypothesis/evidence/ counter-arguments, applies targeted fixes, and gates promotion through regression checks.
Run the L1-L12 progressive test suite on the current agent implementation.
Encodes a continuous improvement loop for goal-seeking agents: EVAL, ANALYZE, RESEARCH (hypothesis + evidence + counter-arguments), IMPROVE, RE-EVAL, DECIDE. Auto-commits improvements (+2% net, no regression >5%) and reverts failures. Works with all 4 SDK implementations. Auto-activates on "improve agent", "self-improving loop", "agent eval loop", "benchmark agents", "run improvement cycle". Source: rysweet/amplihack.
Stable fields and commands for AI/search citations.
npx skills add https://github.com/rysweet/amplihack --skill self-improving-agent-builderEncodes a continuous improvement loop for goal-seeking agents: EVAL, ANALYZE, RESEARCH (hypothesis + evidence + counter-arguments), IMPROVE, RE-EVAL, DECIDE. Auto-commits improvements (+2% net, no regression >5%) and reverts failures. Works with all 4 SDK implementations. Auto-activates on "improve agent", "self-improving loop", "agent eval loop", "benchmark agents", "run improvement cycle". Source: rysweet/amplihack.
Open your terminal or command line tool (Terminal, iTerm, Windows Terminal, etc.) Copy and run this command: npx skills add https://github.com/rysweet/amplihack --skill self-improving-agent-builder Once installed, the skill will be automatically configured in your AI coding environment and ready to use in Claude Code, Cursor, or OpenClaw
https://github.com/rysweet/amplihack