yishan-io

brainstorm

Helps explore ideas before implementation. Use when the user wants to brainstorm features, compare approaches, shape requirements, or discuss tradeoffs before writing code.

context-memory

Use when searching or updating durable project memory in `.my-context/`, especially `MEMORY.md`, architecture notes, or other cross-task context that should survive beyond the current task.

context-task

Use when working with a tracked `.my-context/tasks/` record and its task-specific documents during research, planning, execution, review, or user-directed completion.

dispatching-parallel-agents

Use when you have two or more independent tasks, failures, or investigations that can be worked on concurrently without shared state or sequential dependencies.

executing-plans

Use when you have an approved implementation plan and want to execute it directly in the current session without the full subagent-driven workflow.

finishing-task

Use only when the user explicitly asks to finish a tracked `.my-context/tasks/` record and it needs durable wrap-up and memory promotion.

receiving-code-review

Use when receiving code review feedback, before implementing suggestions, especially when feedback is unclear, broad, or may not fit the codebase as-is.

requesting-code-review

Use when finishing substantial code changes, before merging, or at natural checkpoints to request an explicit code review pass.

starting-task

Use when beginning a new piece of work and deciding whether to create a tracked task in `.my-context/tasks/`, especially before research, planning, or implementation on non-trivial work.

subagent-driven-development

Use when executing a multi-task implementation plan by dispatching one fresh builder agent per task, reviewing each task before moving on, and keeping controller context narrow.