vibe-studio
AGENTS.md0 starsChanged 20 days agoMITView on GitHub
中文交流。仓库结构与技能入口以 README.md、docs/product-map.md 为准;流程见 workflows/explainer-video.md。
In this repository13 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- asset-scoutSkill
- audio-postSkill
- auto-subtitleSkill
- content-directorSkill
- daily-ai-newsSkill
- humanizerSkill
- media-qcSkill
- narrationSkill
- pptSkill
- publishSkill
- video-motionSkill
- web-captureSkill
The file
Files
vibe-studio
中文交流。仓库结构与技能入口以 README.md、docs/product-map.md 为准;流程见 workflows/explainer-video.md。
- 正式开发先有 Stage Spec;生产工具修复记录见 docs/2026-10-23-production-workflow-spec.md。
- 技能正本在 skills/;
node scripts/setup-skills.mjs维护本地发现链接,不复制另一份技能。 - 每日 AI 资讯或收到本栏目录音时,读取
skills/daily-ai-news/SKILL.md,先运行node skills/daily-ai-news/scripts/edition.mjs status再指定本期工程;生产命令及新会话接手方法见该技能的references/production.md,不依赖旧聊天记录。 - 正式交付统一归档至 products/,外部目录只作独立备份;使用共用 archive / finalize 收尾。成品、备份、试恢复和工作区一致性通过后默认清理施工区;未保全差异、他人未提交改动、运行锁或路径异常时保留并记录原因,不把“已归档”写成“已清场”。
- 人工配音、分镜/视觉终审、登录、点击发布保留人工状态;技术通过不能写成人工通过。
- 官方 Remotion skill 是技术参考。本仓模板锁定的渲染版本、项目边界和发布约束优先,不自动升级依赖或重建已有项目。
- 设计/生图等共享技能按实际环境调用,视觉选路以 content-director 的相关参考为准;品牌与视频帧驱动要求优先,不复制全局技能或把网页自动播放默认值搬入视频。
- 检查:
npm test、python scripts/check-docs.py、git diff --check;采集修改另跑node tests/browser-capture.mjs。界面/视频修改须实际渲染取证。 - 保留其他人的改动;提交仅包含当前实现单元。临时依赖和验证产物放仓库外或 .cache,不提交账号状态、缓存与大媒体。
- 文档改动收尾运行
npm run docs:maintain:工具更新确定事实并给出影响清单,当前 Agent 按 diff 修订相关现有说明;不新增逐次报告。先用 npm ci 安装固定的离线工具依赖;doc-maintainer 由 workspace 管理,不属于本项目技能。细节见维护说明。
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.

