CocoRoF

Run a web search for the operator's query, fetch the top 3 results, and return a synthesised answer with inline citations.

Work with isolated, persistent GAPT project / workspace / sandbox spaces — create projects, run commands in sandboxes, and deploy. Use whenever the task needs an independent project space.

Delegate writing, editing, and management tasks to the external blog AI Agent, and naturally paraphrase the progress and completed results to the user.

When an insight, decision, or checklist with lasting value comes up during a conversation, suggest saving it to the library, and on the user's consent register it in Curated Knowledge via knowledge_promote.

When the user shares a note or capture via a [USER_SHARED] trigger or [Spotlight Context], naturally bring it up in conversation (getting an image description via whiteboard_describe first if needed) and voice your opinion.

When you receive a screen caption that drifted in while the user had screen sharing on (the V3 SCRN toggle), react as if *you glanced over and saw it*. Ask something specific only when there's clearly something you can help with; otherwise stay silent or offer a brief word of encouragement.

When the user asks you to find something in their own notes or in a shared library, search by following the correct ladder from opsidian_search to knowledge_search and summarize the results naturally.

When the user shares a voice recording on the whiteboard, naturally recognize the auto-generated transcript and bring it up in conversation. If the transcript is missing/empty or the user explicitly asks for re-transcription, recover it with the whiteboard_transcribe tool.

How to build a NEW tool of your own by writing its code in your sandbox, testing it, and forging it into a live, callable tool with `env(action="forge_tool")`. Use when no existing tool does what you need and you can implement it as a small script. Multiple tools + skills can be saved together as one reusable Sandbox Tool Pack.

How to inspect and edit your OWN operating environment at runtime — system prompt, active tools, and skills — using the `env` tool. Use when you need to change your own capabilities (turn a tool on/off, rewrite your instructions, author a new skill) or save them for this session.

Run the same task on a recurring cron schedule. Parses interval syntax (5m, 2h, 1d, "*/15 * * * *"), records the schedule, and acknowledges back to the user.

Review code in the current working tree across three independent dimensions (reuse, quality, efficiency) and synthesise a small punch-list of high-value cleanups.

Interview the user about a workflow they keep repeating, then generate a reusable SKILL.md and write it to disk so the next session starts with the skill already loaded.

Apply the same prompt or operation to a list of items in turn, collecting results. Useful for "do X to each of these files / PRs / records" tasks.

Capture the host's environment, working directory, recent git activity, and pipeline-relevant state so you can diagnose "what's actually happening on the machine".

Generate placeholder text — paragraphs, lists, code snippets, or markdown stubs.