raycast

Build and maintain Raycast extensions using the Raycast API. Triggers on @raycast/api, List, Grid, Detail, Form, AI.ask, LocalStorage, Cache, showToast, and BrowserExtension. Use this repo's references/api/*.md files as the primary source of truth for component specs and API usage.

This skill is a documentation-driven helper for writing Raycast extensions and is internally consistent. Before using code generated from it or installing any extension you build, review the generated code for: (1) uses of Clipboard.readText, getSelectedFinderItems, or environment.supportPath — these access local user data and files; (2) calls to AI.ask or external HTTP endpoints — these will transmit data off-device; and (3) any file-write logic that writes into the extension supportPath. The skill itself does not request secrets or install binaries, but extensions produced from it may legitimately require runtime permissions — ensure you trust the code/source and confirm permission prompts when you run the extension.

Type: OpenClaw Skill Name: raycast Version: 1.0.0 The OpenClaw AgentSkills skill bundle for Raycast extensions is classified as benign. While it exposes powerful Raycast APIs that can access sensitive system resources (e.g., clipboard, browser tabs, file system, window management) and external AI/OAuth services, the documentation and code examples consistently demonstrate their use for legitimate, stated purposes. Crucially, the instructions in `SKILL.md` and API references (e.g., `ai.md`, `browser-extension.md`, `tool.md`) explicitly guide the AI agent to implement security best practices, such as checking `environment.canAccess()` before using restricted APIs and utilizing `Tool.Confirmation` for actions with side-effects. There is no evidence of intentional harmful behavior, data exfiltration to unauthorized endpoints, persistence mechanisms, or obfuscation.