literature-helper-polsci

Build systematic literature databases using OpenAlex API. Phased workflow for search, screening, snowballing, annotation, and synthesis with structured user interaction.

深度研究 — 13 agent 协作：研究问题定义、系统性检索、偏差评估、综合分析、引用编译

Agent skill stack for manuscripts targeted at The Journal of Politics (JOP) — a leading general-interest political-science journal published by the University of Chicago Press for the Southern Political Science Association (SPSA), founded in 1939 and one of the oldest and most widely read journals in the discipline. JOP is theoretically innovative and methodologically diverse across all subfields (American politics, comparative politics, formal theory, international relations, methodology, political theory, public administration, and public policy), and it is distinctive in two operational ways: it enforces strict PAGE limits rather than word counts — Research Articles no longer than 35 double-spaced 12-point pages including text, footnotes, references, and tables/figures, Short Articles no longer than 10 pages, and an Online Appendix capped at 25 pages — and it makes acceptance contingent on replicability, with a JOP replication analyst assigned at conditional acceptance who assesses the deposited materials in the JOP Dataverse (Harvard Dataverse) before publication, rejecting manuscripts that are not replicable. Facts covered include double-blind review, Editorial Manager submission, the 150-word abstract cap, 4-5 keywords, and the readme + dataset(s) + codebook + code single-zip replication package made public at the time of publication. Covers political-science topic selection, cross-subfield literature positioning, theory and argument building, research design across causal inference / experiments / formal / qualitative work, data-analysis norms, exhibits, JOP-style writing within the page budget, the replication and data-access policy, the review process, submission preflight, and R&R rebuttals. Bilingual en / zh-CN docs.

Multi-agent orchestrator for academic writing: 12 specialist agents and 30 writing principles for review, research, drafting, polishing, bibliography auditing, and literature surveys.

PhD-level research capabilities: literature review, multi-source investigation, critical analysis, hypothesis-driven exploration, quantitative/qualitative methods, and lateral thinking

Production-grade academic research pipeline for Claude Code: research → write → review → revise → finalize. 4 skills, 27 modes, 39-agent ensemble, v3.7.3 + v3.8 L3 claim-faithfulness gate, v3.9.0 cross-index triangulation, v3.10 triangulation policy layer, v3.11 deterministic citation verification gate (#182).