Use when working with macOS GUI apps, desktop automation, background clicks, drag or canvas tasks. Agents run JavaScript in one open session through scripts/cu.mjs (code mode, no MCP registration); the engine is OpenAI's Codex Computer Use when the ChatGPT…
Atlassian, Rovo, Robo, Teamwork Graph, TWG, Jira, Confluence; REA reverse engineering, MCP-to-CLI integration; GitHub, gh, issues, pull requests; Notion, ntn, pages, databases; Slack, chat, messaging, Block Kit; Exa, web search, semantic search, contents;…
Automate the user's logged-in Chromium browser: read pages, fill forms, scrape data, operate tabs, test a UI, or debug a website. Requires the bsk CLI and browser extension.
Maintain a local JSON-backed progress view with live refresh, nested work lists and linked evidence. Use for browser status reports and long-running work dashboards; execution stays with the existing work owner.
Use when designing UX/product flows, researching users or personas, conducting Agentic user research with day-in-the-life simulations, creating wireframes or IA, working with Pencil visuals, or designing agentic CLI UX.
Checkpoint sync: one bounded script run commits, merge-pulls and pushes the current checkout and its dirty submodules, with a Lore commit message per repository. Ordinary sync checkpoints everything dirty; paths after -- are an explicit optional limit.…
Use when a task, agent brief, UX route, CDO plan, wave, or sprint needs relevant local skill material, or when selected material's applicability and loading must be checked.
Use when coordinating a multi-step goal across agents, skills, Lev lifecycle routes, scheduling, research, implementation, review, or human decisions.