Instructions file CodexOpenCode
Instructions for sybil-solutions/local-studio: Local Studio is a local-first workstation whose Bun/Hono controller and Next.js/Electron frontend share one controller API for model lifecycle, serving, system state, settings, usage, and agent sessions. Work decisively without asking questions during execution, preserve…
Skill Claude CodeCodex
Search and read the connected Gmail account with Local Studio's read-only tools.
Skill Claude CodeCodex
Inspect the connected Google Calendar account with Local Studio's read-only tools.
Skill Claude CodeCodex
Manage Local Studio automations — scheduled prompts the app re-runs on its own — when the user asks to schedule, pause, resume, edit, inspect or delete recurring work, or asks what a scheduled job has been doing.
Skill Claude CodeCodex
The user's own Chrome — their real window, profile, logins and tabs, driven through the browser extension relay. Load when a task needs a signed-in session, a page they already have open, or anything the headless sandbox browser cannot see.
Skill Claude CodeCodex
Computer use — a headless sandbox browser for opening, reading, and interacting with public web pages. Load when the user asks to browse, search, open a page, inspect a link, or when live web content matters and no sign-in is involved.
Skill Claude CodeCodex
GitHub through the gh CLI that is already installed and signed in on this machine — issues, pull requests, diffs, reviews, Actions runs, code search, and the REST API. Load when the user asks about a repo, an issue, a PR, a review, red CI, or anything on github.com.
Skill Claude CodeCodex
The user's Obsidian vault — searching, reading, creating and appending to their markdown notes, with wikilinks, frontmatter and tags handled the way Obsidian means them. Load when the user mentions their notes, their vault, Obsidian, a daily note, a note by name, or asks you to write something down for them.
Skill Claude CodeCodex
Delegate self-contained work to parallel subagent sessions — when a task splits into independent chunks (research several areas at once, review many files, try approaches in parallel), or when the user asks to fan out, parallelize, or run something in the background.