Plan types, function inputs and outputs, and module boundaries before implementation. Compare structurally different designs from multiple AI models, document the chosen approach, and guide coding while tracking changes to the agreed design.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing a complex feature before coding
• Comparing alternative module structures
• Keeping implementation aligned with design decisions

Generate several candidate solutions in parallel, compare them against concrete criteria, and choose a base. Combine useful parts from other candidates, then verify the final artifact and document why each major choice was made.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare multiple designs before choosing a direction
• Explore different implementations of the same task
• Combine useful elements from competing drafts

Turn recurring work habits and communication preferences into a personal agent skill. It combines evidence from workspace conversations with direct questions, then drafts or updates instructions for how agents should work with you.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Capture preferred response length and tone
• Document testing and review expectations
• Update personal instructions as work habits change

Monitor an open pull request, fix failing automated checks and merge conflicts, and address straightforward review feedback. Recheck after updates, report the resulting status, and hand decisions requiring design judgment back to the user.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Following up on an open PR without repeated prompts
• Fixing failed automated checks and rechecking results
• Addressing straightforward review comments

Checks whether performance measurements support a speedup, slowdown, or technology choice. It examines bottlenecks, production settings, errors, repeatability, and completed work, then guides reporting with run counts, ranges, and a clear verdict.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking before-and-after performance claims in a PR
• Comparing libraries or configurations fairly
• Investigating suspicious benchmark results

Investigate what a code change could break beyond the edited files. Trace downstream effects, identify the key assumption behind its safety, and test that assumption with real code while clearly reporting unresolved risks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking the wider impact of a small code change
• Verifying assumptions about existing code before design
• Testing the safety assumption before merging a change