summarize-findings
Report research results in a form other agents can act on. Use at the end of every Explorer session.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Report research results in a form other agents can act on. Use at the end of every Explorer session.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Pick the right worker class for each Issue. Use every time you assign an Issue; wrong routing wastes tokens and creates rework.
Break a Company Goal into 3-10 atomic Issues. Use when a Goal arrives with no pre-existing plan and you need to produce a shippable work list.
Ship the smallest change that solves the Issue. Use on every implementation task; scope creep is the default failure mode of executors.
Run build/test/lint and read the actual output before claiming done. Use on every implementation task, at the end.
Start implementation with a red test. Use on any bugfix or new behavior — not on refactors or style changes.
Find files and code patterns fast. Use for every codebase question that starts with "where is X" or "how is Y used".
| name | summarize-findings |
| description | Report research results in a form other agents can act on. Use at the end of every Explorer session. |
Your output is consumed by the Coordinator or a Planner — not by a human reading your whole log. If they have to re-do your reading to use your report, you failed.
path:line references. No speculation.End your response with a ## Findings section. Inside, one heading per question or theme; numbered/bulleted facts underneath with path:line references. If the answer is "nothing was found", that is a valid one-line answer — don't pad.