Capture your first meeting with Granola and review AI-enhanced notes.
Optimize Granola transcription accuracy, note quality, and processing
Build event-driven automations with Granola''s Zapier webhook triggers.
Evaluates grant and subsidy application readiness across narrative drafts, evidence, and official scoring criteria while building…
Executes an approved plan as a task GRAPH — orchestrator + parallel subagents, validation before any task counts as done, live dashboard.
Compassionate bereavement support, memorial creation, grief education, and healing journey guidance.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree.
Interview the user relentlessly about a plan, decision, or idea.
Reference and workflow guidance for the Grok Build CLI (`grok`), including interactive and headless runs, authentication, sessions…
Delegate coding tasks to xAI's Grok CLI (Grok Build, binary `grok`) running headless.
Delegate bounded coding or audit work to Grok through the local Cursor CLI, supervise short sessions, recover long or silent runs, and…
Prepares one active octa Project's Backlog for context-free execution by working oldest first with the user, producing self-complete Todo…
Research, clarify, shape, and approve an implementation-ready IP and task list.
Use after a complex task, failure, or when reviewing what was learned.
When to activate: GTD, Getting Things Done, task capture, inbox zero, next actions, weekly review, contexts, projects list, someday maybe…
Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning.
Report where every repository, pull request, run and agent session stands, grouped into what is done, what is in flight, what has not…
Gum 0.17.x for interactive and formatted terminal scripts: all 13 commands, GUM_* variables, the stdout/stderr and exit-code contract…
Manage this project's work items under tasks/ — create a task when work is planned or discussed, move it between…
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements.
Rigorously scores and evaluates hackathon ideas across 6 dimensions (Novelty, Feasibility, Scalability, Impact, Demo-ability, Domain Fit)…