.claude/skills/make-loopRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
把用户一句大白话的任务,改写成一个写得清清楚楚、能放心让 AI 自己跑的循环(loop)任务说明。结构是三段:目标(我要做什么)→ 过程(它要怎么做)→ 检查迭代(做完检查,再接着改);里面写全五件事:目标是什么、每轮做什么、怎么检查、记录什么、什么时候停。自带这些经验:评审一次给全清单、开发一口气改完;评审用统一的尺子;定期让用户本人看前后对比;刹车写全但不乱停。用户不会写 loop,只要说「帮我变成 loop」「做成循环」「写个 loop」「让它自己一轮一轮改到好」「反复迭代直到没问题」「让它一直跑」,或者丢来一个任务加一句 /make-loop,就用这个技能。适用任何任务。默认只把任务写成 loop,不开始执行;只有用户明确要求现在就在这次对话里执行,并先确认范围,才动手。任务本身的专业知识由当时的对话和其他技能提供。
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
.claude/skills/make-loopRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/make-loopRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/make-loopRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.
clawhub install @ekko237/make-loopclawhub inspect @ekko237/make-loop --version 1.0.1This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
sha256:7a015061571588ad7307d03a595d874a144a89c4d7386463d9423a519694b64finstall.shLICENSEREADME.mdreferences/checklist.mdreferences/examples.mdreferences/template.mdskill-card.mdSKILL.mdAddress ClawHub security scan findings