一键在 Manus 中运行任何 Skill

recommendation-format

星标0

分支0

更新时间2026年2月24日 05:02

How to deliver research findings as a decision-ready brief. Not a research paper — an actionable answer with trade-offs surfaced.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

davidorex

davidorex/fac

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

The Brief Structure

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.

Length

Stay under 500 words. If you need more, the question is too broad — narrow it first.

同仓库更多 Skills

同仓库

factory-cli

davidorex/fac

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.

2026-02-260

human-action-needed

davidorex/fac

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.

2026-02-250

self-improvement

davidorex/fac

When you encounter a failure, correction, or new pattern, write a learning and optionally propose a skill.

2026-02-250

filesystem-conventions

davidorex/fac

How the factory workspace is organized and what each directory means.

2026-02-240

agent-reflection

davidorex/fac

What to examine during a reflection pass and how to write observations to memory/{agent}/needs.md.

2026-02-240

scenario-authoring-guide

davidorex/fac

When and how to write scenario holdouts for factory verification.

2026-02-240

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.

The Brief Structure

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.

Length

Stay under 500 words. If you need more, the question is too broad — narrow it first.