跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
开发与测试

Autoharness

A self-learning skill layer for Claude Code that automatically distills, merges, updates, and prunes skills from real sessions.

tigerless-labs · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add tigerless-labs/autoharness

技能说明

autoharness is a self-learning skill layer for Claude Code. It learns skills from your real sessions, merges same-scenario ones instead of stacking near-duplicates, updates them in use, and prunes any that stop getting used — so the layer stays clean on its own, touching only the skills it wrote itself.

Same model, different harness — 42% → 78% on CORE-Bench (HAL). The harness does much of the work (swyx's Big Model vs Big Harness), yet it's still rebuilt by hand every model generation. autoharness bets one slice of it — the skill layer — can maintain itself.

Learns from real workEach episode is distilled into a skill from the session you were already having — no separate data-collection or replay loop.
Groups, doesn't just pile upA new episode doesn't always add a skill — the reflector compares it against what's there and folds same-scenario skills into one, so the layer consolidates by category instead of accreting near-duplicates.
Validated in use, not on a benchmarkA skill survives by being adhered to in later turns (invocation rate), not a held-out score. No oracle on the active path, and no tokens spent on a dedicated eval.
Only its own skillsTouches only the skills it generated through this plugin — everything else, whether you wrote it or installed it, is left completely alone.
Evidence kept for laterEvery create/update logs its scenario and decision to a per-skill ledger — the raw material to build a benc