yishan-io
OrganizationMake development work feel lighter.
Categories
Indexed Skills (14)
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.
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.
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.
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.
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.
systematic-debugging
Use when investigating a bug, test failure, build failure, flaky behavior, or unexpected runtime issue before proposing or implementing fixes.
test-driven-development
Use when implementing a feature, bug fix, or behavior change where automated tests should drive the implementation before production code is written.
writing-plans
Use when you have approved requirements for a multi-step task and need a concrete implementation plan before touching code.
editing-whiteboards
Use when creating or modifying Excalidraw whiteboard files (.excalidraw) — drawing diagrams, or adding, moving, restyling, or removing shapes, arrows, and text by editing the scene JSON directly.
context-task
Use when work needs a tracked Local Task during research, planning, execution, review, or user-directed completion.
executing-plans
Use when you have an approved plan and can execute it in the current session without the full subagent workflow.
finishing-task
Use only when the user explicitly asks to complete a tracked Local Task and the task needs a durable outcome.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.