bama
BAMA: Build Any Mac App. Agent skills to research, clone, design, build, optimize, and test native macOS apps with Swift and SwiftUI.
翻譯準備中
尚未偵測到更新。GitHub 發布版本後會顯示在這裡。
個人 GitHub 帳號下公開儲存庫的擁有者可以登入並驗證所有權,自行管理介紹,無需管理員核准。
登入並產生驗證檔案,在 30 分鐘內將其提交至此儲存庫的預設分支。其他分支或分叉儲存庫中的檔案無效。然後在下方檢查檔案,即可無需管理員核准直接管理專案。請保留檔案以維持管理權限。
如需登入,將前往登入頁面。登入後請回到此處,再次點擊所選的驗證按鈕。
在專案資料夾中執行 /nomorevibe verify,即可驗證所有權並自行管理介紹。
一分鐘完成驗證代理技能、AGENTS.md、插件清單和發現索引,適用於Linkbreakers:實體世界的潛在客戶捕獲基礎設施。
AI 翻譯
Agent skills, AGENTS.md, plugin manifests and discovery index for Linkbreakers: lead capture infrastructure for the physical world.
取自儲存庫 README
正在載入完整 README。 以下為已儲存的摘錄。
The single source of truth for everything Linkbreakers exposes to AI agents: skills, agent instructions, plugin manifests and a machine-readable discovery index.
Linkbreakers is lead capture infrastructure for the physical world. Every QR code or link runs a workflow (forms, conditions, password gates, multi-link pages, contact cards) that turns an anonymous scan into an identified visitor.
Any agent supported by the skills CLI (Claude Code, Cursor, Codex, GitHub Copilot, Windsurf, Gemini, Cline and more):
Bundles the skills and the hosted Linkbreakers MCP servers:檢視完整 README ↗The single source of truth for everything Linkbreakers exposes to AI agents: skills, agent instructions, plugin manifests and a machine-readable discovery index.
Linkbreakers is lead capture infrastructure for the physical world. Every QR code or link runs a workflow (forms, conditions, password gates, multi-link pages, contact cards) that turns an anonymous scan into an identified visitor.
Any agent supported by the skills CLI (Claude Code, Cursor, Codex, GitHub Copilot, Windsurf, Gemini, Cline and more):
npx skills add linkbreakers-com/agent-skills
Bundles the skills and the hosted Linkbreakers MCP servers:
/plugin marketplace add linkbreakers-com/agent-skills
/plugin install linkbreakers@linkbreakers
This repository is an Agent Plugin: plugin.json, skills/ and mcp.json at the root.
| Skill | Use it to |
|---|---|
| create-tracked-qr-code | Create a link with a dynamic, tracked QR code (or one that opens a PDF, image or video) and change its destination later |
| build-lead-capture-workflow | Add forms, conditions and pages to a link and wire every branch |
| read-visitors-and-leads | List, filter, sort and export captured visitors, events and funnels |
| send-leads-to-webhooks | Push scans and leads to a CRM or backend in real time |
| identify-visitors-on-your-site | Tie a QR scan to a later signup or purchase with the lbid and identify API |
| manage-custom-domains | Serve links from a branded domain and debug its DNS and certificate |
| use-linkbreakers-cli | Install and script the linkbreakers CLI |
| connect-linkbreakers-mcp | Connect an assistant to the Linkbreakers MCP server with OAuth |
| Surface | Where |
|---|---|
| Agent instructions | AGENTS.md |
| Docs index for LLMs | https://linkbreakers.com/llms.txt |
| MCP server (your workspace, OAuth) | https://mcp.linkbreakers.com |
| Docs MCP server (no auth) | https://linkbreakers.com/mcp |
| REST API | https://api.linkbreakers.com, reference at https://linkbreakers.com/help/api |
| OpenAPI spec | https://api.linkbreakers.com/internal/openapi/api/v1/api.swagger.json |
| CLI | brew install linkbreakers-com/tap/linkbreakers (tap: https://github.com/linkbreakers-com/homebrew-tap), docs at https://linkbreakers.com/cli |
| SDKs | TypeScript (npm i linkbreakers), Python (pip install linkbreakers), Go, Java, Rust: https://linkbreakers.com/help/article/linkbreakers-developer-ecosystem-overview |
discovery.json is the machine-readable index of all of the above, validated by schema/discovery.schema.json. linkbreakers.com reads it at runtime from:
https://raw.githubusercontent.com/linkbreakers-com/agent-skills/main/discovery.json
Its skills[] array is generated from the skills/ folders:
node scripts/build-discovery.mjs # regenerate
node scripts/build-discovery.mjs --check # what CI runs
Add a folder under skills/ with a SKILL.md whose frontmatter has name (same as the folder) and description, regenerate discovery.json, and open a pull request. Ground every step in the real API: check the OpenAPI spec rather than guessing.