All authors
Claude Skills by yishan-io
github.com/yishan-io14 skills0 installs27 views
- BrainstormHelps explore ideas before implementation. Use when the user wants to brainstorm features, compare approaches, shape requirements, or discuss tradeoffs before writing code.Votes: 0GitHub stars: 7
- Dispatching Parallel AgentsUse when you have two or more independent tasks, failures, or investigations that can be worked on concurrently without shared state or sequential dependencies.Votes: 0GitHub stars: 7
- Editing WhiteboardsUse 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.Votes: 0GitHub stars: 7
- Receiving Code ReviewUse when receiving code review feedback, before implementing suggestions, especially when feedback is unclear, broad, or may not fit the codebase as-is.Votes: 0GitHub stars: 7
- Requesting Code ReviewUse when finishing substantial code changes, before merging, or at natural checkpoints to request an explicit code review pass.Votes: 0GitHub stars: 7
- Subagent Driven DevelopmentUse when executing a multi-plan-subtask implementation plan by dispatching one fresh builder agent per plan subtask, reviewing each plan subtask before moving on, and keeping controller context narrow.Votes: 0GitHub stars: 7
- Systematic DebuggingUse when investigating a bug, test failure, build failure, flaky behavior, or unexpected runtime issue before proposing or implementing fixes.Votes: 0GitHub stars: 7
- Test Driven DevelopmentUse when implementing a feature, bug fix, or behavior change where automated tests should drive the implementation before production code is written.Votes: 0GitHub stars: 7
- Writing PlansUse when you have approved requirements for multi-step work and need a concrete implementation plan before touching code.Votes: 0GitHub stars: 7
- Context MemoryUse 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.Votes: 0GitHub stars: 7
- Context TaskUse when work needs a tracked Local Task during research, planning, execution, review, or user-directed completion.Votes: 0GitHub stars: 7
- Executing PlansUse when you have an approved plan and can execute it in the current session without the full subagent workflow.Votes: 0GitHub stars: 7
- Finishing TaskUse only when the user explicitly asks to complete a tracked Local Task and the task needs a durable outcome.Votes: 0GitHub stars: 7
- Starting TaskUse when outcome-oriented engineering work may need a tracked Local Task before planning or implementation.Votes: 0GitHub stars: 7