codex

Research Toolkit

Academic research, patent disclosure, Nature-oriented writing, citation, figure, and ITASCA simulation tools.

5 on GitHubby research-toolkit maintainersv0.3.74MITupdated todayProductivity

Plugin research-toolkit in ToddModica/upstream-skills. Commands read from the repo's manifest — today.

This plugin runs code on your machine — it starts local MCP servers. The exact commands are listed below; read them before installing.

What it installs

Skills (27)

  • academic-paper-reviewer

    Multi-perspective academic paper review with dynamic reviewer personas. Runs a 5-seat, role-separated review panel (Journal-Fit Reviewer + 3 peer-review roles + Devil's Advocate) with field-specific expertise; role separation is not a claim of independent error processes. Supports full review, re-re

  • academic-paper

    12-agent academic paper writing pipeline. 11 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure/rebuttal-audit). 6 paper types, 5 citation formats, bilingual abstracts, LaTeX/DOCX-via-Pandoc/PDF output. Style Calibration + Writing Quality Ch

  • academic-pipeline

    Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory, cove

  • academic-research-suite

    ARS-Codex research, writing, manuscript review, study screening, and experiments. Use for deep research, literature or systematic reviews, meta-analysis, research questions, drafts, revisions, roadmaps, abstracts, citations, integrity checks, peer review, research-to-paper. Screen records: sr-screen

  • deep-research

    Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 8 modes: full research, quick brief, paper review, lit-review, fact-check, three-way literature scan, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers resear

  • nature-academic-search

    Search literature across sources, verify or manage citations, and build MeSH strategies or citation-impact audits. Use for 文献检索、引文核对、参考文献管理、严格他引 and evidence-backed citer profiles; not for translating a paper or drafting manuscript prose.

  • nature-citation

    Find and verify Nature/CNS-family literature supporting manuscript claims, with claim-to-source mapping and reference-manager export. Use for Nature系列引用、CNS支撑文献、分段补引用 when this journal scope is requested; use broader literature search for unrestricted sources.

  • nature-data

    Draft or audit manuscript Data/Code Availability statements, dataset access routes, repository plans, and FAIR metadata. Use for 数据可用性声明、数据共享、数据仓库选择 and dataset citations; not general data cleaning or statistical analysis.

  • nature-figure

    Create, revise, audit, and export manuscript scientific figures in Python or R. Use for 论文配图、科研绘图、多面板图 and submission-ready plots, or explicitly requested AI-generated graphical abstracts and mechanism schematics. Not for interactive dashboards, data cleaning, or statistics-only analysis.

  • nature-paper2ppt

    Create or improve a Chinese academic PPTX from a scientific paper or research reading notes, with source figures and speaker notes. Use for 论文做PPT、文献汇报、组会PPT and paper-based conference or defense presentations.

  • nature-polishing

    Polish, translate, or tighten existing academic prose while preserving facts, terminology, and evidence boundaries. Use for 论文润色、学术翻译、正文精简, or manuscript LaTeX layout fixes. Use nature-writing when the main task is drafting new sections or rebuilding the manuscript argument.

  • nature-reader

    Create source-grounded Chinese-English paper readers with aligned text, figures, tables, and equations. Use for 全文翻译、中英文对照、论文精读 or source-linked questions about a paper; respect a requested excerpt or question without generating a full reader.

  • nature-response

    Draft, audit, or revise responses to peer review, revision cover letters, and marked-manuscript or LaTeX revision packages. Use for 审稿意见回复、逐点回复、返修信、 rebuttals and edits to existing response drafts. Initial-submission materials belong to nature-writing; simulated peer review belongs to nature-reviewe

  • nature-writing

    Draft or restructure scientific manuscript arguments, sections, and initial-submission materials from author-provided evidence. Use for 论文写作、章节起草、论证重构、正文压缩、首次投稿材料. Use nature-polishing for language-only edits to existing prose and nature-response for post-decision correspondence.

  • patent-disclosure-skill

    中国专利技能:挖掘专利点并撰写发明/实用新型/外观设计交底书;将已有交底改写为申请文件四件套;规划发明母案与分案并核对原始披露;依据发明人材料衔接交底与申请;按著录项目检索公布公告,点名海外时检索美欧日韩等海外专利;解读中国及海外专利文献;基于已入库解读生成专利地图;对照审查政策撰写简报;辅助审查意见答复;编制权利要求对照表底稿(不构成法律意见)。| China patents: mine patent points and draft invention/utility-model/design disclosures; convert an existing disclosure into

  • patent-application

    申请文件:把已有交底写成权利要求书、说明书、摘要与说明书附图;规划发明母案与分案并核对原始披露。四件套须指定交底目录。内容争议写入问题清单,交付后请确认须摘要清单。已有产出上改稿则另存新时间戳目录。须显式触发。

  • patent-chart

    权利要求对照表:独权拆成技术特征,逐格比对对比文件/产品/标准,附证据与强弱。用于无效对照、FTO 初筛、侵权/EoU、SEP、可专利性底稿。须点名。不出法律意见。

  • patent-disclosure

    中国专利交底书:发明/实用新型/外观设计的专利点挖掘、轻量查新与成文、保护型1+N专利布局。

  • patent-docket

    按发明人/工程师给的材料一趟写出交底书和申请文件;申请问题清单上的缺口最多改三轮。缺技术事实就问人,不编。触发:交底申请一起做、从零出交底和申请、一条龙、帮写交底再出申请、按清单改、会稿、案卷、/patent-docket。

  • patent-exam-policy

    给交底用的政策简报:对照国知局近期口径,说明对交底写法/本稿的影响,并提示申请书式。技能进化仅为旁路,默认只改交底包,须另点名才改文件。

  • patent-map

    专利地图:基于通俗解读已入库的 Obsidian 案例,点名后打开五种图。地形按 bge-small-zh 向量摊开。

  • patent-oa

    审查答复辅助:审查意见问答与草稿;库薄时引导案例入库。须显式触发。

  • patent-reader

    专利通俗解读:中国或海外(美欧日韩等)公开号 / PDF 成通俗笔记、图谱与 Obsidian 入库。

  • patent-search

    专利著录检索:中国专利公布公告(发明人、申请人、分类号、名称、摘要;也可从单图或权利要求生成名称/摘要关键字后查询);用户点名海外时,用 Google Patents 检索美欧日韩等海外专利。

  • scipilot-cite-skill

    SciPilot Skills 家族的文献检索与引用插入技能。支持两种输入模式—— 模式 A:读取用户的 Word(.docx) 或 LaTeX(.tex) 论文,在正文对应章节插入引用; 模式 B:接收用户给出的一段话/一个观点/一个论断,输出能支撑它的参考文献列表 (不修改文档)。两种模式都通过 Semantic Scholar、OpenAlex、Crossref 三源 并行检索真实文献,DOI + 多源交叉验证真实性,然后按用户指定格式(IEEE/APA/ Nature/Vancouver/GB-T-7714 等)输出。每次交付前都强制运行 Gate 8 末端幻觉 门控审计,FAIL 即

  • scipilot-figure-skill

    SciPilot Skills 家族成员,负责科研数据可视化——但定位不是"画图工具", 而是"可视化顾问"。先做数据剖析(列类型/样本量/分布/异常值/分组结构/相关性), 再结合用户的论证目标推荐图型,主动拦截科研画图的经典错误(小样本画均值柱掩盖 分布、双 Y 轴、饼图、Y 轴不当截断、rainbow 色图、把分类点连成折线等),最后 产出 Nature / Science / IEEE / Elsevier / PNAS / 中文核心期刊级别的成图。 覆盖纯数据图:折线、柱状、散点、箱线 / 小提琴、热力图、误差棒、分布图(直方 图 / KDE)、相关性矩阵 / 散点矩阵、多面板组合。

  • scipilot-writing-skill

    SciPilot Skills 家族的学术论文写作与润色技能,定位是把"顶刊编辑 + 严苛审稿人" 装进你的写作流程。覆盖全链路写作任务:中英互译润色、缩写/扩写、英文/中文表达润色、 逻辑检查、去 AI 味(humanize)、逐章节起草(Title/Abstract/Introduction-CARS/ Methods/Results/Discussion/Conclusion/Limitations)、图/表标题生成、实验结果分析、 审稿人视角自检、cover letter(投稿信)、response-to-reviewers(rebuttal 审稿回复)。 与同类"prompt 清单"

MCP servers (1)

  • itasca-mcp

    runs: uvx itasca-mcp

View source on GitHub

More from ToddModica/upstream-skills

All 10 plugins →

Upstream presentation, document, PDF, image, Bilibili, PowerShell, frontend design, and Codex skill-development utilities.

11 skills

5

Editorial diagrams in your brand, as self-contained HTML and SVG. Architecture, flowcharts, sequence, state machines, ER and database schemas, timelines, swimlanes, org charts, Gantt, Wardley maps, user journeys, service blueprints, UML class, lifecycle phase maps, and charts from bar, line and scatter to Sankey, treemap and heatmap, plus many more. Redraws draw.io, Mermaid, Excalidraw and PlantUML files. Exports SVG and PNG.

1 skill · 7 commands

5

Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.

6 skills

5

Chinese and English prose editing, natural-language style checks, and evidence-aligned academic narrative guidance.

5 skills

5

Keep rejected wording and session residue out of final deliverables.

1 skill · hooks

5

tavotto

codex

画论文级 matplotlib 图,并用 Tavotto 的 MCP 工具微调:改图例位置、字号线宽、刻度,跑出版规范预检,导出真矢量 PDF。所有改动都是 override,不动你的 Python 源码。

1 skill · 1 MCP server

5

Similar plugins

caveman

claude

Talk like caveman. Cut filler. Keep technical details explicit.

22 skills · 1 command · 3 agents · hooks

JuliusBrussee/caveman 119,462

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

pake

claudecodex

Package any website or local web build into a lightweight desktop app with Pake CLI.

1 skill

tw93/Pake 63,463

Maintain Research Toolkit?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins10 plugins