cindy
Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.
该技能通过结合官方文档、本地类型定义和实时设备同步,为构建复杂的 iOS 自动化项目(Scripting App)提供了结构化且对代理友好的方法。
A development skill for desktop coding agents such as Codex and Claude Code. It helps agents create, modify, debug, and validate Scripting App projects: TypeScript/TSX scripts, iOS-style pages, native APIs, Widgets, Live Activities, rich notifications, Shortcuts/Share Sheet intents, App Intents, and Safari browser scripts.
Copy or link this repository into the skill directory used by your coding agent. The root SKILL.md is the entry point; it loads only the relevant files under references/, templates/, and checklists/ for each task.
Before writing Scripting-specific code, the skill requires the agent to consult the official LLM documentation index:
For desktop-to-iPhone development, use scripting-cli:
# Requires Node.js 20+
npx scripting-cli start
After the Scripting App connects to the initialized workspace, it synchronizes current .d.ts declarations. The agent should use them to verify exact local TypeScript signatures, imports/globals, event payloads, and TSX props, while using the official documentation for behavioral, permission, and host constraints.
SKILL.md Main routing, API lookup, validation, and safety rules
references/ Focused guides for project lifecycle, UI, native APIs,
Widgets/App Intents, Live Activities, notifications/Intents,
Safari scripts, desktop CLI, and validation/security
templates/ Minimal `script.json`, entry-point, Widget, Intent, and userscript starters
checklists/ Project creation, modification, desktop live-debug, and host E2E checks
llms.txt and the exact official API/capability page.scripting-cli, connect the app, and inspect synced .d.ts files for the connected app version.A development skill for desktop coding agents to build, debug, and validate Scripting App projects.
根据分类、Topic 和编程语言匹配的相似项目。
Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.
Clodex is an open-source, local-first agentic IDE that combines persistent AI tasks, code, terminal, browser, Git, models, memory, and governed execution in one Electron workspace, currently in technical preview.
A hands-on course that walks through building a Pi-style coding agent from scratch across 15 checkpoints, starting from an offline agent trajectory.