clean-deliverable
Skill1 starsChanged 2 months agoNo licenceView on GitHub
纯净交付守卫(模型通用)。用于在"生成"或"审查"交付物(幻灯片、文案、报告、邮件、代码等)时, 防止元信息泄漏到成品里——包括自造占位符("符合营销话术的标题")、回声输入(把用户给的 要点/约束/设计依据原样贴进成品)、以及思考过程残留。适用于任何生成式模型(GPT、Gemini、 Claude 及本会话中的我自己)。三种用法:①产出可粘贴到任意目标模型的约束提示词; ②审查并清洗一份已有交付物(含图片类,给出重生成提示词);③我自己生成交付物时的交付前自检。 触发词:纯净交付、清洗交付物、防元信息泄漏、约束提示词、别把要点写进成品、 clean deliverable、anti meta leak。
In this repository21 other files it gives its agents.
- kiakun-skillsSkill
- amap-web-serviceSkill
- bilibili-video-summarySkill
- cc-switch-claude-providerSkill
- chinese-first-dialogSkill
- deliverable-purifierSkill
- folder-to-vector-kbSkill
- game-ui-asset-pipelineSkill
- gpt-image-2-apiSkill
- html-to-pptxSkill
- image-ppt-to-editable-pptxSkill
- pitch-visual-promptingSkill
- player-interaction-designSkill
- ppt-rebuild-workflowSkill
- xiaohongshu-skillsSkill
- xhs-authSkill
- xhs-content-opsSkill
- xhs-exploreSkill
- xhs-interactSkill
- xhs-publishSkill
- xhs-research-bridgeSkill
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.

