Menu
Report research results in a form other agents can act on. Use at the end of every Explorer session.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
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.