Using Helloscholar
Use when starting any conversation - establishes how to find and use hello-scholar skills across all skill groups, requiring skill invocation before ANY response including clarifying questions
Takeoff
|
Writing Plans
Use when you have a spec or requirements for a multi-step task, before touching code
Subagent Driven Development
Use when executing implementation plans with independent tasks in the current session
Requesting Code Review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Record Experiment
记录实验运行指令和结果。Use when a new experiment identity will launch, or when an existing recorded run has material state/evidence changes: train, eval, test, benchmark, model inference/generation/prediction, ablation, reproduction, failed/invalid/stopped/negative result, or derived report. Includes checkpoint/model outputs. Hard gate: no persistent experiment record, no launch.
Landing
|
Brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Crash Audit
|
Handoff
Compact the current conversation into a handoff document for another agent to pick up.
Test Driven Development
Use when implementing any feature or bugfix, before writing implementation code