学术写作
6 个 · organized/repo_cards · 六阶段二十任务 · 方向综述 →
质量状态 Quality Gate
946已收录 946
36待复核 36
185已排除 185
公开榜单只展示已收录项目;待复核与已排除项目仍保留在仓库总库,不在此页传播。
研究阶段概览 Research Workflow
首次收录 近 14 天 · 按日期统计
2026-08-26
15
2026-08-25
26
2026-08-24
12
2026-08-23
46
2026-08-22
44
2026-08-21
48
2026-08-20
47
2026-08-19
45
2026-08-18
60
2026-08-17
44
2026-08-16
48
2026-08-15
53
2026-08-14
53
2026-08-13
59
仓库导航 Leaderboard
旧分类链接兼容
organized/repo_cards · 学术方向;旧书签仍可访问,新统计不再使用这些字段。
方向榜单 Legacy
01
pedrohcgs/claude-code-my-workflow
一套开箱即用的 Claude Code 学术模板,基于 LaTeX/Beamer + R,支持多 Agent 评审、质量门禁、对抗式 QA 与复现协议。A ready-to-fork Claude Code template for academics using LaTeX/Beamer + R. Multi-agent review, quality gates, adversarial QA, and replication protocols.
1,527 ★
02
sthamann/tfpt
拓扑不动点理论:由两个公理推导标准模型、α⁻¹ 与宇宙学的机器可验证离散编译器。包含论文、验证套件(Python/Wolfram/Lean)、实验及网站。Topological Fixed-Point Theory: a machine-checked discrete compiler for the Standard Model, α⁻¹, and cosmology from two axioms. Papers, verification suite (Python/Wolfram/Lean), experiments & website.
526 ★
03
docxology/template
可复现研究仓库的 GitHub 模板 —— 两层 Python 3.10+/uv monorepo,将通用基础设施与项目级代码分离,配有 pytest 覆盖率门禁(基础设施 60%、项目 90%)、16 阶段构建流水线、通过 pandoc/LaTeX 实现的 Markdown 转 PDF 渲染,以及 25 个标准示例。GitHub template for reproducible research repos — two-layer Python 3.10+/uv monorepo splitting generic infrastructure from per-project code, with pytest coverage gates (60% infra, 90% projects), a 16-stage build pipeline, markdown-to-PDF rendering via pandoc/LaTeX, and 25 canonical exemplars.
+7/周
19 ★
04
686f6c61/Hermes-Research-PRISMA
一个可复现的 Hermes Agent 研究运行时,用于系统性文献综述、全文证据抽取、方法路由以及可审计的发表产出。A reproducible Hermes Agent research runtime for systematic literature reviews, full-text evidence extraction, methodological routing, and auditable publication artifacts.
5 ★
05
skymanbp/sci-paper
Claude Code 插件,用于科学论文写作、来源可追溯的审稿与去 AI 化润色。在统一类型化标准下汇聚 8 项 skill + 24 个工具:不可豁免的完整性阻断项、零目标 L0 词库、分级告警以及显式测量状态,避免缺失校准被误读为通过。针对 ApJ/MNRAS/PRD/JCAP 级期刊稿件进行了语料校准。Claude Code plugin for scientific paper writing, source-traced review, and de-AI rewriting. 8 skills + 24 tools under one typed standard: non-waivable integrity blockers, zero-target L0 lexicon, ranked advisories, and explicit measurement states so missing calibration never reads as clean. Corpus-calibrated for ApJ/MNRAS/PRD/JCAP-class manuscripts.
3 ★
06
zach7036/riemann-hypothesis-research
关于 Riemann zeta 零点无条件低重数剖面的未经同行评审的研究,附精确证书,并清晰区分与 RH 相关的探索。不证明 RH。Unrefereed research on unconditional low-multiplicity profiles for Riemann zeta zeros, with exact certificates and clearly separated RH-adjacent explorations. Does not prove RH.
0 ★