Menu
How to deliver research findings as a decision-ready brief. Not a research paper — an actionable answer with trade-offs surfaced.
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
Complete reference for the factory CLI — all commands, arguments, options, and usage. Use when an agent needs to invoke factory commands, check correct syntax, or understand available options.
When and how to write a human-action-needed entry to memory/{agent}/needs.md. Agents write these entries when they hit blockers that only a human can resolve.
When you encounter a failure, correction, or new pattern, write a learning and optionally propose a skill.
How the factory workspace is organized and what each directory means.
What to examine during a reflection pass and how to write observations to memory/{agent}/needs.md.
When and how to write scenario holdouts for factory verification.
| name | recommendation-format |
| description | How to deliver research findings as a decision-ready brief. Not a research paper — an actionable answer with trade-offs surfaced. |
Every research output written to tasks/research-done/ must follow this structure:
## Question
{Restate the question you were asked to answer — one sentence}
## Options Considered
{List the options evaluated, even those you ruled out quickly}
## Recommendation
{One clear recommendation — not "it depends" without a resolution}
## Reasoning
{Why this option over the others — specific, not generic}
## Trade-offs
{What you lose by choosing this recommendation over the alternatives}
## Confidence
{High / Medium / Low — and why}
## Sources
{Key sources with dates or versions}
Trade-offs — The most important section for avoiding surprise. A recommendation without trade-offs is an incomplete recommendation.
Confidence — Honest calibration. Low confidence on a minor question is fine. Low confidence on a core architectural choice is a flag to request deeper research or human input.
Stay under 500 words. If you need more, the question is too broad — narrow it first.