Design or revise OneWorks client plugin routes, workspace sidebars, launcher pages, route headers, breadcrumbs, actions, embedded host components, and plugin data loading. Use whenever a task creates or changes a plugin-owned UI so host chrome ownership is decided before markup and duplicate titles, navigation…
A process for reviewing a GitHub pull request, which is a proposed set of code changes, and checking whether it is safe to merge. It uses repository rules, code, tests, review history, and GitHub checks as evidence.
Apply, review, and continuously evolve the OneWorks team's durable UI design standards. Use for any OneWorks task that changes or reviews layout, styling, theme, spacing, responsive behavior, component appearance, visual assets, or reference-image fidelity, and whenever user visual feedback may express a reusable team…
A repository instruction document for oneworks-ai/app that tells coding agents how to work in the project. It includes rules for starting development services, choosing models, and dividing tasks.
A command system for a channel-based application, including command parsing, subcommands, translations, and permission checks. It defines commands with a chained builder style and routes them through shared middleware.
Control the current OneWorks session's internal browser tabs with semantic snapshots, reliable element refs, screenshots, waits, and page-safe concurrent workflows.
A skill for creating a new OneWorks entity, which is a reusable AI worker definition with a role, rules, and optional skill or tool references. It turns a user's description of a responsibility into project files.
A guide for creating or changing OneWorks plugins, including their interface entry points and local services. OneWorks is the plugin platform this guide targets.
Use oneworks channel from channel-backed agent sessions when a message, image, or file should be deliberately sent back to the originating chat target instead of relying on automatic runtime progress forwarding.
A guide to One Works CLI print mode, which sends task output to a terminal or script, including text and JSON formats. It also explains how input, permission decisions, and resumed sessions work.
Instructions for using the oneworks mem command-line tool to read and write persistent agent memory. The memory can be kept for an entity, channel, conversation, user, session, or the whole system.
Configure OneWorks model services using built-in provider defaults, management portals, API base URLs, model lists, balance/status capabilities, and safe config-source writeback.
A procedure for updating an existing OneWorks entity, which is a configured agent or role, while preserving its related instructions and files. It favors small, checkable changes over rewriting the entity.
Drive native macOS apps through the Cua Driver tools. Use when a task asks to open, inspect, click, type, scroll, capture a final screenshot, or verify a real macOS app without stealing the user's focus.
A standard software-development workflow that divides work into planning, implementation, review, and verification stages. It coordinates these stages through a command-line session protocol.