agentleFS
Sign inStart free
dss-timedss-time/repo-doctor-skills/skills/research-brief/SKILL.md

research-brief

Skill1 starsChanged 4 months agoMITView on GitHub

Define and answer a bounded research question with a source plan, evidence ledger, cross-checking, conclusions, unknowns, and next steps. Use when gathering or synthesizing evidence is the primary task; use report-writer when supplied material only needs a polished report, and never claim current research without accessible sources or network capability. 围绕有边界的研究问题制定来源计划、建立证据台账、交叉验证并输出结论、未知项和下一步。主要任务是搜集或综合证据时使用；已有材料只需形成正式报告时使用 report-writer；无法访问资料或网络时不得声称完成实时研究。

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read references/productivity-evidence-and-file-safety.md.

    line 10

“Common” is measured: kept by at least 6 in 10 of the 18 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

English

Research Brief

Read references/productivity-evidence-and-file-safety.md. Use assets/research-brief-template.md when no format is supplied.

  1. Define the research question, intended decision, audience, scope, exclusions, deadline, freshness requirement, and evidence standard.
  2. Confirm whether supplied materials and network/search tools are actually accessible. If not, produce a source plan or limited brief and state that current research was not performed.
  3. Prioritize primary, official, and directly authoritative sources; use reputable secondary sources for context and independent corroboration.
  4. Record publisher, title, publication date, event date when different, locator, and access date. Keep short claims linked to their supporting sources.
  5. Cross-check material claims, investigate conflicting dates or figures, and distinguish facts, source assertions, inferences, and recommendations.
  6. Synthesize the answer, confidence, dissenting evidence, unknowns, limitations, and specific next research steps. Do not stretch conclusions beyond scope.

Hand polished long-form reporting from an already supplied evidence set to report-writer.

Output Contract

  1. Research question, scope, deadline, and evidence standard
  2. Key conclusions with confidence
  3. Evidence ledger with publication, event, and access dates
  4. Conflicts and alternative interpretations
  5. Unknowns, limitations, and next steps

简体中文

研究简报

读取 references/productivity-evidence-and-file-safety.md。用户未提供格式时使用 assets/research-brief-template.md。

  1. 明确研究问题、目标决策、读者、范围、排除项、截止时间、时效要求和证据标准。
  2. 确认材料与网络/搜索工具是否真实可用；不可用时只输出来源计划或受限简报，并明确没有完成实时研究。
  3. 优先原始、官方和直接权威来源，用高可信二手来源补充背景和独立验证。
  4. 记录发布者、标题、发布日期、不同情况下的事件日期、定位信息和访问日期，让关键结论可追溯。
  5. 交叉验证重要结论，调查日期或数字冲突，区分事实、来源主张、推断和建议。
  6. 输出结论、置信度、反方证据、未知项、限制和具体下一步，不让结论超出范围。

如果证据已经给全、主要任务是形成正式长报告，应转交 report-writer。

输出契约

  1. 研究问题、范围、截止时间和证据标准
  2. 带置信度的核心结论
  3. 含发布、事件和访问日期的证据台账
  4. 冲突与替代解释
  5. 未知项、限制和下一步

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free