Research & Search
Research agent skills teach AI agents to gather and synthesize information properly: literature reviews, competitive analysis, web research with citations, and structured summaries. Each SKILL.md encodes a method, not just a prompt, so results stay consistent across runs.
-
thedixitjain Skill History Of ReligionsUse when targeting History of Religions or deciding whether a comparative-historical religious-studies manuscript fits this venue. Encodes the journal's fit, its comparative-method and primary-source bar, textual/philological and morphological expectations, house style and review norms, official-submission re-check, and desk-reject heuristics.
2 -
thedixitjain Skill Hlr Preemption CheckUse when verifying that a Harvard Law Review (HLR) argument has not already been made — the law-review "preemption check" run across SSRN, Westlaw/Lexis, HeinOnline, and Google Scholar BEFORE drafting. Confirms originality and refines the claim; it does not draft the thesis (hlr-thesis-and-contribution) or the literature engagement in the body.
2 -
brycewang-stanford Skill Hpca ReproducibilityUse when strengthening HPCA reproducibility: pinning the result chain from simulator commit through config, workload, sampled region, and statistics, building one manifest per figure, recording machine state for silicon runs, and keeping the environment resurrectable for the IEEE artifact-badging round.
1k -
thedixitjain Skill Iccv Topic SelectionUse when deciding whether a computer-vision project should target ICCV, weighing the biennial odd-year cadence and its two-year option cost, what the Marr Prize lineage says about ICCV taste, honest odds at 24% acceptance, and when to hold work for CVPR, ECCV, WACV, or a journal instead of forcing the March deadline.
2 -
brycewang-stanford Skill Icde ReproducibilityUse when strengthening reproducibility evidence for an IEEE ICDE data-engineering paper: pinning hardware, storage devices, software versions, datasets and workload generators, seeds, and variance protocol; ensuring baseline-tuning fairness; tracing figures to raw logs; and packaging supplemental material whose availability ICDE scores.
1k -
thedixitjain Skill Icdm ReproducibilityUse when strengthening reproducibility for an ICDM (IEEE International Conference on Data Mining) paper - seeds, configs, compute and data reporting, and an anonymized reproduction package that survives the Research Track's triple-blind regime while every detail fights for room inside the single 10-page IEEE all-inclusive cap.
2 -
thedixitjain Skill Icdm Topic SelectionUse when deciding whether a project is a strong ICDM (IEEE International Conference on Data Mining) fit, choosing among its Research, Applied, and Blue Sky tracks, and comparing ICDM with KDD, SDM, CIKM, WSDM, WWW, ICDE, or the ML flagships by contribution type, sponsor community, and the data-mining routing calendar seen from ICDM's June deadline.
2 -
thedixitjain Skill Icdt ReproducibilityUse when strengthening the verifiability of an ICDT (International Conference on Database Theory) paper — the theory-venue analogue of reproducibility — covering complete and self-contained proofs, exact models and assumptions, claim-to-proof mapping, matching upper and lower bounds, consistency between the LIPIcs paper and the arXiv full version, and honest labeling of what is proved versus conjectured.
2 -
thedixitjain Skill Iclr ReproducibilityUse when strengthening reproducibility for ICLR papers, including seeds, variance, compute, datasets, implementation details, ethics statements, and reviewer-verifiable evidence. Use when writing the ICLR reproducibility statement, when a reviewer says a result is not verifiable, or when mapping each representation-learning claim to a seed, split, and command so anyone reading the permanent OpenReview record can check it.
2 -
thedixitjain Skill Icml Author ResponseUse when drafting ICML rebuttals and reviewer-author discussion replies under OpenReview double-blind constraints, where authors respond after initial reviews, reviewers may then have one additional discussion round, no revised paper can be uploaded during the period, and responses must stay anonymous. Use to triage objections by soundness, originality, significance, clarity, ethics, and reproducibility for the AC.
2 -
thedixitjain Skill Icml ReproducibilityUse when strengthening ICML reproducibility evidence, including code/data availability, random seeds, compute disclosure, appendix evidence, impact-statement support, and reviewer-facing reproducibility claims.
2 -
thedixitjain Skill Icml Topic SelectionUse when deciding whether a manuscript fits ICML, choosing the main research track versus the ICML Position Papers track or another venue (NeurIPS, ICLR, AISTATS, UAI, COLT, MLSys, TMLR, JMLR), or rerouting an ML paper based on its contribution type, strength of evidence, theory-versus-empirical balance, and interest to the broad ICML machine-learning community. Use before committing effort to an ICML submission.
2 -
thedixitjain Skill Icse Topic SelectionUse when deciding whether a software-engineering project belongs in the ICSE research track or should be routed to FSE, ASE, ISSTA, MSR, ICSME, EMSE/TSE/TOSEM, or an ICSE co-located track such as NIER, SEIP, SEIS, or Demonstrations, based on contribution type, evidence maturity, and audience.
2 -
thedixitjain Skill Ijoc Topic SelectionUse when deciding whether a project is computing-first enough for an INFORMS Journal on Computing (IJOC) submission and which of its 10 technical areas fits. Scopes the contribution to the OR↔computing interface; it does not invent results or citations.
2 -
thedixitjain Skill Ipsn ReproducibilityUse when strengthening IPSN-lineage reproducibility for a hardware/embedded/deployment artifact, covering firmware and board files, pinned toolchains, raw traces and calibration, honest degrees of reproducibility for a physical system, anonymized-but-runnable artifacts, and consistency between the paper and the package.
2 -
thedixitjain Skill Ipsn Topic SelectionUse when deciding whether a sensing/embedded project is an IPSN Information-Processing (IP) contribution or a Sensor Platforms, Tools and Design Methods (SPOTS) contribution, and whether it should go to the IPSN lineage (now the merged SenSys at CPS-IoT Week), a CPS-IoT Week neighbor (RTAS/ICCPS/HSCC), MobiSys/MobiCom, INFOCOM, or a signal-processing journal.
2 -
thedixitjain Skill Isca ReproducibilityUse when making an ISCA paper's results regenerable — pinning simulator versions and local patches, archiving per-figure configuration manifests, recording workload provenance and sampling seeds, quantifying run-to-run variation on real hardware, and keeping the environment resurrectable through the February window.
2 -
thedixitjain Skill Itcs ReproducibilityUse to make an ITCS paper's mathematics independently checkable — complete proofs of every central claim, self-contained definitions, pinned dependencies on prior results, and a matching full version on arXiv/ECCC/ePrint — the pure-theory analogue of a reproducibility package.
2 -
thedixitjain Skill Jaar Topic SelectionUse when deciding whether a project fits the Journal of the American Academy of Religion (JAAR) and how to frame it. JAAR's bar is broad and fundamental interest to the study of religion across traditions and methods — a contribution only to one subfield will be returned for reframing before review. Frames the question; it does not do the research.
2 -
thedixitjain Skill Jacs Results FramingUse when the chemical advance and its significance are not yet sharp for a Journal of the American Chemical Society (JACS) manuscript. Shapes the narrative and claims — it does not generate new data or fix characterization gaps.
2 -
thedixitjain Skill Jais Topic SelectionUse when deciding whether a question fits the Journal of the Association for Information Systems (JAIS) and which of its seven manuscript categories to target. Locks the IS phenomenon, the unit of analysis, and the category before theory work begins; it does not build the theory (jais-theory-development) or invent citations.
2 -
thedixitjain Skill Jape Topic SelectionUse when deciding whether a project fits the Journal of Applied Econometrics (JAE) — an applied (not pure-theory) journal publishing empirical, replicable work that applies or develops econometric techniques on real data. Tests scope fit, the replicability requirement, and the Research vs. Replication Article tracks before you commit.
2 -
thedixitjain Skill Jcrd Author Response在收到《计算机研究与发展》(Journal of Computer Research and Development, JCRD) 外审意见、需要撰写审稿意见答复与修回说明时调用。覆盖多轮修回(初审→外审→复审→终审)下的逐条回应结构、把每条意见映射到正文可追踪修改、双盲评审下不泄露作者身份的中性措辞、对分歧意见的礼貌反驳与折中、修改稿标红/修订说明的组织、以及专题稿件面向客座编辑的补充答复。适用于把一份带修改意见的 JCRD 稿件转化为一份让责任编辑与外审专家能快速核对的修回材料的场景。
2 -
thedixitjain Skill Jcrd Reproducibility在为《计算机研究与发展》(Journal of Computer Research and Development, JCRD) 稿件构建可复现性与实验可重复证据时调用。覆盖环境与依赖版本固定、随机种子与非确定性控制、数据集版本与抽取日期钉死、大模型/API 输出缓存、硬件与度量口径记录、双盲下的匿名可运行材料、诚实的可用性说明,以及让外审专家在不联系作者情况下重跑主结果的组织方式。适用于把一份 JCRD 中文稿件的实验做到可被第三方在受控条件下重复、并经得起外审可复现质疑的场景。
2 -
thedixitjain Skill Jcrd Topic Selection在为一份计算机学科中文稿件判断是否投《计算机研究与发展》(Journal of Computer Research and Development, JCRD)、以及投常规栏目还是对口专题时调用。覆盖本刊征稿范围与稿件类型匹配、专题(special topic)组稿机制与当期专题主题对接、综述与原创的形态选择、与姊妹刊(计算机学报、软件学报、自动化学报、电子学报、计算机科学)的选路,以及专题客座编辑与截稿时间表的核对。适用于在动笔前判断选题与栏目定位、把工作放到最匹配的落点以提高录用概率的场景。
2 -
thedixitjain Skill Jebo Topic SelectionUse when deciding whether a behavioral, experimental, or organizational question fits the Journal of Economic Behavior & Organization (JEBO) rather than a sibling outlet, and how to frame it. Sharpens scope and the behavioral hook; it does not invent evidence, editors, or citations.
2 -
thedixitjain Skill Jeem Topic SelectionUse when scoping or scope-testing a Journal of Environmental Economics and Management (JEEM) manuscript — confirming the environmental/resource mechanism is load-bearing and the question clears the field-journal bar before any analysis is finalized. Decides fit and routes; it does not invent evidence or citations.
2 -
thedixitjain Skill Jegeo Tables FiguresUse when exhibits — especially maps — for a Journal of Economic Geography (JEG) manuscript are dense, decorative, or do not answer the spatial question. Makes maps and tables argue; it does not invent results.
2 -
thedixitjain Skill Jhe Referee StrategyUse when pre-morteming a Journal of Health Economics (JHE) manuscript against the objections its health-economist referees raise before submission. Anticipates and disarms likely pushback; it does not draft the response letter after a decision (jhe-rebuttal) or run the submission preflight.
2 -
thedixitjain Skill Jle Referee StrategyUse when anticipating the objections a law-and-economics referee at The Journal of Law and Economics (JLE) will raise, so a manuscript pre-empts them before submission or addresses them in revision. Plans the defense around JLE's single-blind process; it does not draft the response letter (jle-rebuttal) or run the submission preflight (jle-submission).
2 -
thedixitjain Skill Jmcb Topic SelectionUse when deciding whether a monetary, banking, credit, or macro-finance question belongs at the Journal of Money, Credit and Banking (JMCB) rather than a sibling, and how to frame its policy stakes. Locks the question and outlet fit; it does not invent evidence or citations.
2 -
thedixitjain Skill Jmgmt Review ProcessUse when you need to understand or set expectations for the Journal of Management (JOM) editorial and masked-review process — desk screening, the developmental R&R culture, the Review Issue track, and reading a decision letter. Explains the process; it does not draft the response letter (jmgmt-rebuttal).
2 -
thedixitjain Skill Jmis Topic SelectionUse when deciding whether a question is the right shape for a Journal of Management Information Systems (JMIS) manuscript — an IS-management or economics-of-IS problem, not a generic tech study or a pure CS contribution. Pressure-tests fit and outlet choice before theory work begins; it does not build the mechanism (jmis-theory-development).
2 -
thedixitjain Skill Joap Topic SelectionUse when deciding whether an I-O / applied-psychology project fits the Journal of Applied Psychology (JAP) and which article type to target. JAP wants a genuine theoretical contribution to work-and-organizational science backed by rigorous measurement, not a rigorous study with no theoretical advance. Frames the question and tests fit; it does not collect data.
2 -
thedixitjain Skill Jole Topic SelectionUse when deciding whether a research question fits the Journal of Labor Economics (JOLE) — a general-interest labor-economics quarterly — and how to frame it so it matters to labor economists broadly, not just one niche. Tests fit; it does not run the analysis.
2 -
thedixitjain Skill Jonc Author Response当为《通信学报》(Journal on Communications, JOC) 收到的外审与编委会意见撰写逐条答复与修回说明时调用;用于把 Journal on Communications 三审制下的审稿意见转化为可核验的修回材料。指导把大修/小修意见拆成可追踪条目、逐条给出"意见—回应—修改位置"的闭环答复,撰写礼貌而有据的修回说明信、在稿件中做差异标注(修改处标色/标注页行号),处理相互矛盾或超范围的意见、对不认同意见的有据申辩,兼顾本刊三审制多轮修回与月刊排期,帮助把一份通信/网络/信息安全/信号处理方向中文长文的修回材料做到审稿人一眼可核、编委会易于通过的程度。
2
Frequently asked questions
What are Research & Search agent skills?
Research agent skills teach AI agents to gather and synthesize information properly: literature reviews, competitive analysis, web research with citations, and structured summaries. Each SKILL.md encodes a method, not just a prompt, so results stay consistent across runs.
Which Research & Search skills are most installed?
Popular Research & Search skills on SkillMD right now include history-of-religions, hlr-preemption-check, hpca-reproducibility. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Research & Search skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.