科研 Skill

文献矛盾结论梳理

map-literature-contradictions

Analyzes conflicting findings across papers and explains disagreement by sample, method, or context differences for a stronger synthesis. Use when review sources disagree.

发布者 Codar安全审核通过v0.1.0更新于 2026-11-18

SKILL.md

Map Literature Contradictions

Discipline And Interview Setup

Read discipline-routing.md, then only the selected discipline profile. Reuse the user's existing brief; do not restart intake at each stage. For journalism/communication or information science, use that profile's concepts, extraction fields, and appraisal checks instead of a generic social-science template.

When the user requests "grill me", 追问, or 模拟答辩, read research-interview.md. Ask one decision-relevant question per turn and wait; do not generate the stage deliverable until enough decisions are settled or the user asks to proceed. In quick/no-question mode, record assumptions and continue without inventing answers.

For evidence extraction or drafting, read review-workflow.md. With no sources, give a plan or outline, not a purported synthesis. If reference files are unavailable, retain the source guardrails below and state that discipline guidance is missing.

Goal

Use contradiction as information. Instead of avoiding inconsistent findings, map what researchers agree on, where they diverge, and what hidden conditions or method limits explain the disagreement.

Workflow: Comb Method

  1. Assess convergence within the available corpus, accounting for study quality and overlapping reports. If none is supported, say so; repetition or citation count alone is not consensus.
  2. Separate contradictions from incomparable questions or measures: name the exact conflicting claim only when the studies address a comparable object. Otherwise describe the difference without manufacturing disagreement.
  3. Compare study conditions: inspect object, sample, indicator, method, time window, and context.
  4. Infer why the difference matters: connect the comparison to theory, mechanism, or validity.
  5. Mark explanation boundaries: identify what current methods or data cannot answer.
  6. Convert the boundary into a possible research contribution.

Contradiction Matrix

Use this table when the user provides multiple papers or claims. Leave the status column honest: if the user gave no source for a claim, write "未提供出处" and do not fill in a citation; if a check found nothing, write "未查到".

| Study/claim | Finding | Object/sample | Method | Indicator | Time/context | Possible reason for difference | Source / verification status (出处/核验状态) |
|---|---|---|---|---|---|---|---|
| ... | ... | ... | ... | ... | ... | ... | Author (year) · 用户提供/已核验/未核验 · how verified |

Use the following pattern only when the evidence supports a conditional explanation. Otherwise state that the disagreement is unresolved or the studies are not comparable; do not force this conclusion:

The disagreement is less about whether [factor] matters and more about when it matters. Studies using [sample/method/indicator] tend to find [result], while studies in [context/time] find [different result]. This suggests the effect may be conditional on [boundary], rather than universally positive or negative.

Difference Dimensions To Check

  • Research object: region, industry, population, organization type, development stage.
  • Sample: size, selection method, subgroup, representativeness.
  • Indicator: how the key variable or outcome is measured.
  • Method: cross-sectional, longitudinal, interview, experiment, case, meta-analysis.
  • Time window: policy period, crisis period, before/after intervention, short vs long term.
  • Theoretical lens: rational choice, institutional, social network, capability, cultural, ecological, etc.

Output Format

Provide:

## Consensus

- ...

## Main Contradictions

1. ...

## Contradiction Matrix

| Study/claim | Finding | Object/sample | Method | Indicator | Time/context | Possible reason | Source / verification status (出处/核验状态) |
|---|---|---|---|---|---|---|---|

## 段落草稿(需作者改写并核对来源)

[Draft synthesis paragraph. Start with: "以下为草稿,请改写成你自己的论证,并逐句核对来源后再使用。" Tag every literature-dependent sentence with source and status, or [需补来源]]

## Explanation Boundaries

- Current literature cannot yet explain ...

## 待核实清单

[Unverified sources, "未查到" results, sentences marked [需补来源], and inferences that still need checking; write "无" if empty]

## 给作者的问题

[Judgment calls that belong to the author; write "无" if empty]

The output sections above, and the two closing sections, keep fixed names and order; see references/output-contract.md (a copy bundled in this skill folder).

Guardrails

  • Do not force agreement by selecting only consistent studies.
  • Do not claim a contradiction is solved unless the provided evidence supports the explanation.
  • Distinguish observed differences from inferred importance; label inferences clearly.
  • Source integrity: follow references/source-integrity.md. Every row of the contradiction matrix needs a source and status; do not invent rows to fill the table. Use only sources the user provided or that are verified, tag each with a status (用户提供 / 已核验 / 未核验), write "未查到" instead of completing authors, year, journal, or pages, and put anything unverified in ## 待核实清单. If that file is not available, still apply these rules.

示例提示词

这些文献结论互相矛盾,帮我分析原因并写出更有力的综述段落。

所属插件

跨学科科研方法跨学科通用科研方法:系统综述与元分析、预注册、实验与问卷设计、文献矛盾与研究空白、科学计量与专利分析、可复现研究、答辩与审稿回复。

安装该插件会一并获得同领域的 54 个 Skill / MCP。

同插件的其他科研 Skill

常见问题

文献矛盾结论梳理能做什么?

Analyzes conflicting findings across papers and explains disagreement by sample, method, or context differences for a stronger synthesis. Use when review sources disagree。

如何安装文献矛盾结论梳理?

在科搭 Codar 左侧点击「插件」,在「组件」页签搜索「文献矛盾结论梳理」并安装;在 Claude Code 或 Codex 中可以发送本页的安装提示词,或下载 Skill 包后解压到 ~/.claude/skills 或 ~/.codex/skills。

文献矛盾结论梳理需要哪些权限?

该科研 Skill没有声明额外权限;执行具体操作时仍由 Agent 按自身规则请求确认。

文献矛盾结论梳理经过官方审核吗?

是。SpeedSkills 收录的每个版本都会记录内容摘要与权限声明,当前版本已通过安全审核。