skills
AGENTS.md1 starsChanged 35 days agoNo licenceView on GitHub
所有执行者使用云端编译后,必须执行 cloud-build-cleanup 技能:交付最新完整产物并验证可获取后,清理自己创建且已不再使用的云端临时缓存、中间编译文件和重复旧构建产物,回读确认清理结果。禁止遗留无归属的长期缓存;保留源码、签名材料、必要证据和最新正式包,不影响正在使用的机器或其他任务。不通过提高付费预算替代可以完成的旧存储清理,也不把删除缓存等同于清零累计用量。 本文件是可供团队复用的通用工作约定,不绑定个人账号、设备、磁盘路径或项目。具体环境约束放在对应项目文档或技能中,不在全局规定统一外盘路径。 以下原则在系统、平台安全规则和实际工具权限范围内执行;不得将用户约定解释为绕过这些边界。 在内部快速核对,不机械地向用户逐项复述: 只有必要授权或关键选择缺失、工具硬性阻断、继续会造成明确且不可控的重大损害,或同范围安全路径已用尽时,才暂停相关工作。说明具体阻塞、已完成进度及所需最小决定,不把局部阻塞当作全部停工的理由。
In this repository47 other files it gives its agents.
- apk-touch-feedbackSkill
- app-release-stability-gateSkill
- bot云机编译,kemi box真机验证Skill
- capcutSkill
- cloud-build-cleanupSkill
- dual-screen-video-wallpaperSkill
- game-playtestSkill
- game-studioSkill
- hbbv-server-build-deploySkill
- kemi-apple-app-store-releaseSkill
- kemi-box-linux-optimizationSkill
- kemi-harmony-phone-developmentSkill
- kemi-hbbc-developmentSkill
- kemi-hbbc-releaseSkill
- kemi-mac-remote-debugSkill
- kemi-market-integrationSkill
- kemi-market-publishSkill
- kemi-microsoft-store-releaseSkill
- kemi-remote-office-acceptanceSkill
- kemi-remote-office-hour-acceptanceSkill
- kemi-remote-office-releaseSkill
- kemi-send-common-releaseSkill
- kemi-send-releaseSkill
- kemi-server-portsSkill
- kemi-storage-cleanupSkill
- kemi-windows-device-labSkill
- kemi-windows-remote-signingSkill
- kemi-windows-two-node-releaseSkill
- linux-desktop-build-acceptanceSkill
- newlink-common-releaseSkill
- product-launch-motionSkill
- project-about-pageSkill
- public-app-distributionSkill
- remotion-promo-video-factorySkill
- rust-linux-cross-buildSkill
- threejs-animationSkill
- threejs-geometrySkill
- threejs-lightingSkill
- threejs-performanceSkill
- three-webgl-gameSkill
- vibekits-cluster-deploymentSkill
- vibekits-cluster-room-deploySkill
- vibekits-cluster-workSkill
- vibekits-fleet-compatibilitySkill
- vibekits-remote-nodeSkill
- vibekits-remote-simulatorSkill
- web-3d-asset-pipelineSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

