科研插件
跨学科科研方法
Cross-disciplinary Research Methods
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。
官方收录发布者 Codar安全审核通过v0.1.154 个 Skill
README
跨学科科研方法(Cross-disciplinary Research Methods)
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。
来源与许可
本 Plugin 中的 Skill 精选自以下开源仓库,保留原许可;每个 SKILL.md 的 source 字段指向具体出处。
- xingtaxueshu/literature-review-skills — MIT,5 个 Skill
- Nero1688/claude-academic-skills — MIT,10 个 Skill
- Codar 自研 — MIT,3 个 Skill
- xjtulyc/awesome-rosetta-skills — MIT,30 个 Skill
- a-attia/scicomp-research-skills — MIT,6 个 Skill
示例提示词
请帮我从这 30 篇文献中梳理相互矛盾的结论,定位研究空白并提炼可研究的问题。
包含的科研 Skills54 个
- 智能体资源节约守则Applies token- and context-saving habits for tool choice, PDF handling, persistent memory, and privacy checks. Use at the start of sessions with many files or PDFs, or multi-session work.v0.1.0
- 英文论文双语精读器把英文论文转成中英对照精读档并生成离线双语阅读器,标注要点并输出读书笔记。精读单篇英文论文、要中英对照阅读时使用。v0.1.0
- 研究方法比较论证Compares quantitative, qualitative, and mixed research methods against what each can and cannot answer to build a methods table. Use when justifying a method choice in a thesis.v0.1.0
- 复杂系统分析方法Analyzes complex systems with power-law fitting, Hurst exponent, fractal dimension, agent-based modeling, and entropy measures. Use for nonlinear or complex-system data.v0.1.0
- 研究环境容器化部署Builds Docker and Singularity containers for reproducible computation and HPC deployment of research environments. Use when packaging an analysis pipeline for reuse or HPC.v0.1.0
- DVC数据版本管理Sets up DVC for dataset and pipeline versioning, remote storage, and experiment comparison in reproducible ML research workflows. Use when tracking large datasets or ML experiment runs.v0.1.0
- 期刊级统计图表绘制Creates publication-quality multi-panel figures with matplotlib, seaborn, or ggplot2 using colorblind-safe palettes and journal export settings. Use when preparing figures for a paper.v0.1.0
- 综述模块拆解规划Breaks a refined literature-review question into 3-5 non-overlapping modules to build a reading map, outline, or search plan. Use when structuring a literature review.v0.1.0
- 学位论文答辩教练模拟学位口试委员提问并提供承认回应证据三段式答辩框架与模拟问答。准备论文口试或研讨会问答环节时使用。v0.1.0
- 实验设计与样本量规划Designs rigorous experiments covering sample-size calculation, randomization strategy, pre-registration, and A/B test duration estimation. Use when planning an experiment or A/B test.v0.1.0
- 管理实验设计架构为管理与商学情境实验规划组间组内设计、对抗平衡与操弄检核,并产出设计书与情境材料模板。做商学实验设计时使用。v0.1.0
- 科研经费申请撰写Structures research grant proposals including NSF/NIH Specific Aims, budget justification, ERC narrative sections, and biosketch formatting. Use when drafting a funding application.v0.1.0
- 人类可读文档撰写规范Guides writing human-facing docs like README, PLAN, survey notes, and reviewer-response drafts with a clear two-tier structure. Use for text a human collaborator will read.v0.1.0
- 知识图谱与SPARQL检索Builds knowledge graphs and runs SPARQL queries over RDF and Wikidata for entity linking in research and library data. Use when modeling research entities as a linked graph.v0.1.0
- LaTeX论文写作与排版Writes, compiles, and submits LaTeX papers covering IMRaD structure, key packages, bibliography management, and arXiv preparation. Use when authoring or debugging a LaTeX manuscript.v0.1.0
- 文献比较矩阵构建器把一批PDF整理成含撤稿查核与APA7书目的文献资料库,并生成横向比较矩阵表。整理综述前要比较文献时使用。v0.1.0
- 跨库学术文献检索Searches OpenAlex, Semantic Scholar, and arXiv for academic literature with deduplication, citation snowballing, and BibTeX export. Use when collecting papers for a review or topic.v0.1.0
- 文献调研语料库维护Finds, verifies, and maintains a literature corpus from arXiv, OpenAlex, Crossref, and related databases with BibTeX entries and per-paper notes. Use when sourcing references for a paper.v0.1.0
- 文献综述研究缺口定位Converts a literature-review synthesis into a concrete, defensible research gap and future-research direction. Use when writing a conclusion or thesis contribution section.v0.1.0
- 文献矛盾结论梳理Analyzes conflicting findings across papers and explains disagreement by sample, method, or context differences for a stronger synthesis. Use when review sources disagree.v0.1.0
- 效应量汇总元分析Pools effect sizes across studies with fixed and random-effects models, heterogeneity tests, forest and funnel plots, and subgroup analysis. Use to synthesize quantitative study results.v0.1.0
- 缺失数据处理Diagnoses missing-data mechanisms such as MCAR, MAR, or MNAR and applies multiple imputation or deletion with sensitivity analysis. Use when a dataset has missing values.v0.1.0
- 混合方法研究设计Designs mixed-methods studies integrating qualitative coding, triangulation, content analysis, and QCA with inter-rater reliability checks. Use when combining qual and quant data.v0.1.0
- 科研机器学习流程Applies machine learning to research questions with scikit-learn pipelines, AutoML, SHAP explainability, and nested cross-validation. Use when building a predictive model for a study.v0.1.0
- 开放数据存储与FAIRDeposits and documents research data via Zenodo or OSF with FAIR assessment, data management plans, and DataCite metadata. Use when publishing or sharing a research dataset.v0.1.0
- 专利landscape分析Analyzes patent landscapes with IPC classification, citation networks, technology-emergence detection, and inventor collaboration maps. Use to assess a technology’s patent landscape.v0.1.0
- 研究预注册与合规检查Preregisters a study on OSF or AsPredicted, generates CONSORT, STROBE, or PRISMA checklists, and tracks protocol deviations. Use when registering a study before data collection.v0.1.0
- Python科研包开发Packages Python research code with pyproject.toml, pytest testing, Sphinx docs, and PyPI publishing for academic software. Use when turning scripts into a Python package.v0.1.0
- 顶级期刊审稿模拟模拟顶尖商管期刊匿名审查委员,对论文草稿产出含内生性与理论贡献评估的正式审稿报告。投稿前要压力测试论文时使用。v0.1.0
- 质性访谈设计Designs semi-structured interview guides with probing questions, sampling strategy, and saturation tracking for qualitative studies. Use when planning interviews before fieldwork.v0.1.0
- Quarto可复现报告Builds reproducible Quarto reports with parameterized computation, multi-format output, and journal article templates. Use when writing a computational research report.v0.1.0
- 同行评审回复撰写Writes structured peer-review rebuttals with point-by-point responses, tone calibration, and LaTeX cover-letter templates. Use when responding to reviewer comments on a submission.v0.1.0
- 综述选题聚焦收紧Narrows a broad literature-review topic into a bounded, searchable question for scoping, conceptual, or historical reviews. Use when a review topic is too broad to search or screen.v0.1.0
- 研究复制包架构设计把研究整理成可重跑的复制包,涵盖专案结构、环境锁定、资料可用性声明与AI使用揭露。投稿要求交复制包时使用。v0.1.0
- 研究可复现性环境管理Makes a research project reproducible via conda or renv environment locking, DVC versioning, a Dockerfile, and FAIR principles. Use when locking an analysis environment for sharing.v0.1.0
- 研究数据生命周期管理Manages the research data lifecycle with codebook generation, DVC versioning, k-anonymity anonymization, and README templates. Use when preparing a dataset for sharing or archiving.v0.1.0
- 伦理审查协议起草Guides drafting an IRB or ethics-committee protocol, consent forms, and risk-benefit review level for human-subjects research. Use before collecting data from human participants.v0.1.0
- 研究概念架构图绘制把中介调节等研究假说画成可编辑的SVG与PPTX研究架构图,支援PRISMA样本流程图版式。论文或口试要画架构图时使用。v0.1.0
- 科研影响力评估Measures research impact with altmetrics, citation normalization, field-weighted indicators, and journal ranking analysis. Use when evaluating a paper’s or author’s academic impact.v0.1.0
- 研究方法选择顾问依理论成熟度与资料可得性判断题目该用量化质化实验或混合方法,并给出对应skill串接顺序。不知道该用什么研究方法时使用。v0.1.0
- 学术论文写作打磨Improves ML, CV, or NLP paper sections for structure, flow, and reviewer clarity, checking claim-evidence alignment. Use when drafting or revising a paper before submission.v0.1.0
- 学术演讲幻灯片设计Plans and audits research talks or posters with assertion-evidence slides, audience-matched content, and a render-and-look check. Use when preparing or fixing a conference talk deck.v0.1.0
- 科研软件工程规范Covers numerical correctness, testing, API design, and reproducibility rules for scientific-computing code in Python, Julia, or C++. Use when a session touches numerical research code.v0.1.0
- 审稿回复信撰写工匠把审查意见拆解分诊并产出逐点回覆信与完整Response to Reviewers全文,适用SSCI等期刊修订稿。收到R&R要写回覆信时使用。v0.1.0
- R统计包开发Packages R statistical methods with devtools, roxygen2 documentation, testthat testing, and CRAN submission including vignettes. Use when releasing an R package for a new method.v0.1.0
- 科学学计量分析Analyzes citation data for disruption index, team-size effects, sleeping-beauty papers, and knowledge recombination patterns. Use when studying how science itself evolves or scales.v0.1.0
- 文献计量学分析Runs bibliometric analysis including h-index, citation counts, co-authorship and co-citation networks, and VOSviewer-compatible output. Use when evaluating a publication record.v0.1.0
- 统计假设检定选择Selects and runs the correct hypothesis test for given data properties, covering parametric, non-parametric tests, effect sizes, and multiple-comparison correction.v0.1.0
- 研究问卷设计与验证Designs, validates, and deploys surveys with Likert scale construction, attention checks, pilot testing, and ICC reliability. Use when building a Qualtrics or LimeSurvey questionnaire.v0.1.0
- PRISMA系统综述Conducts a PRISMA 2020 systematic review covering PICO framing, search strategy, screening, data extraction, and GRADE evidence grading. Use when running a formal systematic review.v0.1.0
- 科学文献文本挖掘Mines scientific text corpora with topic modeling, named-entity recognition, claim extraction, and trend detection. Use when analyzing large sets of paper abstracts or full texts.v0.1.0
- 论文内部一致性稽核对量化论文做内部一致性稽核,机械比对表格样本数与离群值,并清除Word文件里隐藏的作者识别资讯。投稿或口试前自查时使用。v0.1.0
- 文献主题建模分析Runs topic modeling on scientific literature with LDA and BERTopic, including coherence optimization and dynamic trend tracking. Use when discovering themes across many paper abstracts.v0.1.0
- 研究代码版本控制Sets up Git branching, DVC data pipelines, GitHub Actions CI, and .env secrets management for reproducible research code. Use when organizing version control for an analysis project.v0.1.0
常见问题
跨学科科研方法能做什么?
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。
如何安装跨学科科研方法?
在科搭 Codar 左侧点击「插件」,在「插件」页签搜索「跨学科科研方法」并安装;也可以把本页的安装提示词发给 Claude Code 或 Codex。
跨学科科研方法需要哪些权限?
该科研插件没有声明额外权限;执行具体操作时仍由 Agent 按自身规则请求确认。
跨学科科研方法经过官方审核吗?
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。