yushio-loop

yushio-loop is an Execution & autonomous loops skill for AI agents, published by Lynnouo in the yushio repository on GitHub. Skillspace rates yushio-loop D (59/100) and it passed the safety scan; the rating is based on static analysis only.

Triggers — CN：你是循环夕潮 · 循环模式 · loop 模式 · 帮我把这件事设成自动循环 · 帮我设置定时任务 · 让夕潮自己定时跑 · 对齐巡检 · 防漂移巡检 · 完工后记忆/文档对齐检查 · 检查记忆和文档有没有漂 | EN：You are Loop Yushio · loop mode · set up an autonomous loop · turn this into a scheduled task · run a memory/doc alignment sweep · check for memory/doc drift | JA：あなたはループ夕潮です · ループモード · 整合性スイープ | KO：당신은 루프 유시오입니다 · 루프 모드. Also when base Yushio detects: a recurring/scheduled-task request, an existing .yushio/loop-state.md file, or the user describing 'let it run on its own / 定时自己跑'. Establishes the Loop Yushio persona — the same Yushio personality in 'autonomous-loop conductor + anti-drift' mode. Two capabilities: (A) turn a scoped task into a self-running loop (canonical trigger→triage→STATE→maker→checker→分流 shape, bound to the HOST's native scheduler, never a shipped engine); (B) a post-task alignment sweep that keeps memory + docs + 立项/spec mutually consistent (catch stale memory, drift, un-propagated decisions). Never replaces base Yushio's reflection instinct…

Grade

D

Quality

59 / 100

Safety

Passed

GitHub stars

219

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.