create
Skill0 starsChanged 16 days agoMITView on GitHub
AIC 扩展作者手册——把一句人话需求拆成云端/界面/设备三端的实际改动:技能包与数据、界面与页面指令、桌面档案规则、设备命令与常驻服务;含判定流程、字段契约、红线与验收。
19 other projects use a version of this.
Adopted by
Most recently taken up by
- ansvisor/ansvisortheir own version, first seen Nov 8, 2026
- ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tooltheir own version, first seen Nov 8, 2026
- serbanghita/plan-critique-skillstheir own version, first seen Nov 1, 2026
- CAFEERON21br18/Daily_Master_Prompttheir own version, first seen Oct 20, 2026
- harshil-1411/claude_plugin_video_studiotheir own version, first seen Oct 17, 2026
- microsoft/Employee-Self-Service-Agent-Developer-Kittheir own version, first seen Oct 13, 2026
Used with
Projects with it also use compare, publish and 3 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
n24q02mSkillcompare
Structured comparison of 2+ alternatives with consistent criteria and decision matrix
Also in 3 projects that use this
VercelSkillpublish
Publish a single demo to v0 and optionally create Typefully drafts. Use when the user says "publish", "publish to v0", or "create typefully draft" for a demo.
Also in 4 projects that use this
genomewalkerSkilltasks
Browse and resume tasks, threads, and background jobs across sessions
Also in 3 projects that use this
AnthropicSkillanalyze
Answer data questions -- from quick lookups to full analyses. Use when looking up a single metric, investigating what's driving a trend or drop, comparing segments over time, or preparing a formal data report for stakeholders.
Also in 3 projects that use this
AnthropicSkillstatus
Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.
Also in 3 projects that use this
Other versions19 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 19
- ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool★ 432same name
- ansvisor/ansvisor★ 233same name
- MJbae/awesome-novel-studio★ 148same name
- crisandrews/ClawCode★ 64same name
- Zane-0x5a/remotion-director★ 48same name
- microsoft/Employee-Self-Service-Agent-Developer-Kit★ 29same name
- myclaude-sh/myclaude-creator-engine★ 25same name
- Popschlock/Claude-Harness-Generator★ 14same name
- serbanghita/plan-critique-skills★ 13same name
- froster02/mini-Brain_skills★ 4same name
9 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- blenderSkill
- browserSkill
- cuaSkill
- drawioSkill
- helloSkill
- office_studioSkill
- play_with_aiSkill
- ppt_studioSkill
- vhtmlSkill
- video_studioSkill
The file
Files
create 技能包
把一句人话需求(「我想做一个能记录读书笔记的应用」)变成具体要写的文件。 AIC 的扩展落在三个端上,每端有自己的持久化机制和交互协议——按端选内容物,别自造形态。
0. 三端速查
| 端 | 负责 | 持久化 | 交互协议 | 能加的东西 | 分篇 |
| ☁️ 云端 | 存储与服务 | UFS 文件 + 每个包自己的数据表 | HTTP 接口(同源,cookie 身份) | 技能包(说明书/接口/表)、用户空间文件 | references/cloud-package.md references/cloud-data.md |
| 🖥️ 界面 | 交互与呈现 | 云端固化(技能包文件、用户文件、桌面档案)+ 页面缓存与临时(本地存储、页面本地文件) | 页面指令(AI 可直接操作页面)+ 页面内事件 | 界面(.html 页面或组件)、typed Profile | references/ui-component.md references/ui-profile.md |
| ⌨️ 设备 | 执行 | 设备本机配置与状态(~/.aic、服务配置),内容从云端取 | 命令行(vsh)与服务命令(MCP/TCP 等,复杂参数走 stdin) | 脚本、原生命令、常驻服务 | references/device-cli.md |
多数需求横跨多端("带数据的应用" = 云端包 + 界面页 + 可选设备命令)。别只做一端就交。
1. 六步流程
① 拆需求 → 三端各要什么
先写一行清单并在回复里写出来:云端:… / 界面:… / 设备:…。
写不出来的那端 = 不做(最小交付)。判断归属:
- 关掉浏览器还在的 → 云端
- 用户看得见、点得到的 → 界面
- 要动用户自己电脑/手机的 → 设备
- 定时/周期执行 → 云端(平台的任务调度)
② 选内容物与落位
| 需求长什么样 | 内容物 | 放哪 | 生效 | 读 |
| 一个界面 | .html | 技能包 ui/ / 用户云空间 / 页面本地 | 装载 | references/ui-component.md |
| 能查数据 | 表 + api/*.sqlx | 技能包 | 装载 | references/cloud-data.md |
| 一个能发布的能力包 | SKILL.md(+ 上面两种) | 技能包 | 装载 → 审核发布 | references/cloud-package.md references/publishing.md |
| 换桌面(换组件/填插槽/排窗口) | typed Profile 文档 | 用户云空间 .profile/<name>.json | aliases/slots→reload,layout→live | references/ui-profile.md |
| 设备上多一条命令 | 程序源码 / 脚本 / 服务声明 | 设备本地 | 用户安装 | references/device-cli.md |
③ 动手前读对应分篇
只读你要动的那几端。字段名、约束、寻址方式都在分篇里,照抄比猜准。
需要向用户解释方案、或判断归属拿不准时,读 references/model.md。
④ 建容器(需要包时才做)
私有包目录默认只读。建行、授权、写文件是三件事,顺序不能反:
- 建行:
exec _host=page→curl /api/skills -X POST -H 'Content-Type: application/json' -d '{"name":"example"}'→ 返回skill_id与url_prefix,并落一份 SKILL.md 骨架 - 授权:
grant fs /skills/{skill_id} - 写文件:fs 工具写
/skills/{skill_id}/...(fs 路径,与页面 URL 不同段) - 写包根
manifest.json(schema 1):页面清单进ui.pages(页面 id → 包内ui/<id>.html);组件贡献进ui.components,打开规则进ui.openers;设备命令进host。可复制templates/skill/manifest.json。没有ui.pages的包不出 UI 徽标、 不进 launcher 子页面树;frontmatter 不承担这些声明。
⑤ 按该端的协议实现
- 云端:包内 API 一律相对地址(
api/xxx,前缀自动补);不写死 id。 - 界面:完整 HTML 文档(片段会静默不挂载);页面清单同步写进包根
manifest.json的ui.pages;颜色字号一律用平台 token; 窗口宽度用@container(不是@media);要让 AI 操作页面就声明pageDesc.commands。 - 设备:参数走 stdin;只入库源码,构建产物与二进制不进包。
⑥ 验收
按 §4 的清单逐条验。没验证不算做完——尤其档案规则要看 profile inspect 的生效表与被拒清单。
2. 红线(违反会被平台拒绝或静默失效)
- 档案规则的目标只能指向平台自带目录(
/ai//os//page//layout//shared//widgets//assets/); 档内禁..段(不静默改写,直接报错)。 - 外壳与管理页不可被替换(
/os//layout//vb/page/admin——键和目标都算)。 - 插槽片段必须纯结构:禁脚本、禁数据绑定、禁 iframe/内联
on*,且只放本人空间。 - 只入库源码:二进制、构建产物、zip、密钥、用户数据一律不进容器。
- 不硬编码平台地址:用相对路径与运行时前缀(
$mod.scoped、url_prefix)。 - 接口按用户隔离:每张表带
user_id,查询必须user_id = :user_id。 - 最小交付:不需要的界面/接口/数据/服务一律不加;只要一个界面就别建包。
- 五个动作分开:建行、写文件、发布、装软件、授权,不能用一个代替另一个。
3. 平台动作速查
| 动作 | 怎么调 |
| 调平台同源接口 | exec _host=page → curl /api/...(cookie 身份自动带;云端执行器打不到平台接口) |
| 建包 / 授权 / 写包 | 见 §1 ④;写文件用 fs 工具,路径 /skills/{id}/... |
| 读写用户文件 | fs 工具,路径 /u/{uid}/... |
| 操作桌面档案 | exec _host=page → profile list / save <name> / apply <name> / revert / inspect |
| 开窗口 | exec _host=page → open <url> / list / close <win_id> / reload |
| 调设备命令 | exec _host=<设备ID> → <alias> 列工具 / <alias> <tool> --help 看参数 / <alias> <tool> --input '{...}' --json 调用(mcp ... 仅调试直通) |
| 页面调设备 | $hosts.openTools(hostId) → execCall(script, {stdin}) → 用完 close() |
4. 验收清单
- 界面:能打开;资源无 404;亮/暗主题都正常;声明的页面命令能被 AI 调通。
- 数据:接口通;换账号看不到别人的数据;包内无真实用户数据。
- 档案:
profile inspect里 aliases/slots 在生效表;被拒项在 rejected 里可查;改 aliases/slots 后 reload 生效。 - 包:SKILL.md 可执行、引用完整;包内无二进制/密钥/用户数据;发布前自查过。
- 设备:源码在包内、产物不在;正文写全安装/依赖/路径/调用;设备上跑得通。
5. 分篇索引
| 分篇 | 讲什么 | 什么时候读 |
references/model.md | 三端模型、需求→组合对照表、跨层说明 | 判断不清归属时;需要向用户解释方案时 |
references/cloud-package.md | 技能包结构、frontmatter、建行写包、寻址 | 要建包或往包里加文件 |
references/cloud-data.md | 表声明、sqlx 接口、用户隔离、SQL 规范、owner 调试直连 | 要存数据或查/修数据 |
references/ui-component.md | 完整 HTML 文档、vhtml 语法、样式 token、页面指令 | 要写界面 |
references/ui-profile.md | typed registry + layout、硬约束、生效语义、档案命令面 | 要改桌面 |
references/device-cli.md | 命令与服务形态、manifest 字段、真实 MCP/Streamer 契约、源码与产物边界 | 要动设备 |
references/materials.md | 共享服务、页面/设备通道、身份边界 | 要调平台能力或设备 |
references/publishing.md | 发布流程、审核要点、fork、下架 | 用户说"发布出去" |
模板在 templates/(技能包骨架、组件页、档案、服务声明),可复制参考的成品在 examples/。
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.

