agents/openai.yaml
interface: display_name: "Investigate First" short_description: "Find credible cause before editing code" default_prompt: "Use $investigate-first to diagnose this failure before proposing edits."
juliusbrussee/caveman · GitHub
수정하기 전에 원인을 파악하기 어려운 오류를 진단하십시오. 원인을 알 수 없는 오류, 간헐적으로 발생하는 현상, 성능 저하, 또는 증거에 기반한 가설이 필요한 조사 시에 활용하십시오.
프로젝트 폴더에서 아래 명령어를 실행하고, 설치할 에이전트를 선택하세요.
npx skills add juliusbrussee/caveman --skill investigate-first설치 명령을 직접 실행해야 적용됩니다. 지원 에이전트와 필요한 권한·라이선스는 제작자의 안내를 확인하세요.
agents/openai.yamlinterface: display_name: "Investigate First" short_description: "Find credible cause before editing code" default_prompt: "Use $investigate-first to diagnose this failure before proposing edits."
SKILL.md--- name: investigate-first description: Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses. --- # Investigate first Gather evidence before changing product code. - Separate observed symptom from inferred cause. - Trace inputs, state transitions, ownership boundaries, and failure output. - Rank hypotheses by evidence and cheap falsification value. - Do not edit until one credible mechanism explains evidence. - Stop exploration when evidence is sufficient to name cause or exact blocker. Report cause and proof. Make no fix unless task authorizes implementation.