Continual agent skill evolution through persistent decision history. Whole-skill optimisation (SKILL.md + scripts + references) with every decision landing as a local Git issue / PR / wiki. Runs on any agentskills.io runtime — Claude Code, Codex, OpenClaw, Hermes.
This repository also configures its own agents. See what SkillHone tells them →
Agent Claude Code ✓ vendor
Validates a problem observed during normal agent work, checks local SkillHone Issues for duplicates, and records one sanitized actionable issue without requiring eval data.