メニュー
Aggregate Codex skill bundle for academic literature search, screening, citation traversal, research ideation, experiment planning, LaTeX lint/fix, bibliography verification, polishing, translation, and one-command paper checks.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | hypo-research |
| description | Aggregate Codex skill bundle for academic literature search, screening, citation traversal, research ideation, experiment planning, LaTeX lint/fix, bibliography verification, polishing, translation, and one-command paper checks. |
| license | MIT |
这个 bundle 打包了 Hypo-Research 的科研工作流，适合通过 Codex 的 GitHub skill 安装流程一次性安装。
一线入口是 hypo-guide、hypo-check、hypo-review、hypo-read：
hypo-guide，再进入直接命令。hypo-check / check --full。hypo-review / review。hypo-read / read ingest|outline|extract。其他 expert skills 仍然是一等入口，适合明确任务或深度串联。
当前 Codex skill-installer 的稳定安装方式是 GitHub repo/path，而不是仓库外部的裸名字注册。
推荐安装命令：
$skill-installer https://github.com/HypoxanthineOvO/Hypo-Research/tree/main/.agents/skills/hypo-research
如果使用底层脚本，对应等价命令是：
python3 ~/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py \
--repo HypoxanthineOvO/Hypo-Research \
--path .agents/skills/hypo-research
本 bundle 内嵌 skill 文档，位于 skills/ 目录：
skills/hypo-guide/SKILL.md — 自然语言路由入口skills/hypo-read/SKILL.md — PDF 结构化阅读和 evidence cardsskills/hypo-survey/SKILL.md — 综合调研skills/hypo-search/SKILL.md — 快速检索skills/hypo-screen/SKILL.md — 筛选分类skills/hypo-cite/SKILL.md — 引文图遍历skills/hypo-idea/SKILL.md — Research idea 生成skills/hypo-challenge/SKILL.md — Idea 苏格拉底式拷打skills/hypo-experiment/SKILL.md — 实验设计skills/hypo-plan/SKILL.md — 科研工作规划skills/hypo-pilot/SKILL.md — 娄萌萌全流程研究领航skills/hypo-project/SKILL.md — 持久化科研项目管理skills/hypo-rebuttal/SKILL.md — Rebuttal 生成skills/hypo-lint/SKILL.md — LaTeX lint + auto-fixskills/hypo-verify/SKILL.md — 引用验证skills/hypo-polish/SKILL.md — 英文润色skills/hypo-translate/SKILL.md — 双语维护skills/hypo-check/SKILL.md — 一键检查 pipelineskills/hypo-presubmit/SKILL.md — 兼容/legacy 提交前检查 wrapperskills/hypo-meeting/SKILL.md — ASR 转写会议纪要 + 术语知识库skills/hypo-review/SKILL.md — 多角色模拟审稿当任务落在以下类别时，先读取对应子 skill，再执行：
hypo-guidehypo-readhypo-survey / hypo-search / hypo-screen / hypo-citehypo-idea / hypo-challenge / hypo-experiment / hypo-plan / hypo-pilothypo-projecthypo-rebuttalhypo-lint / hypo-verify / hypo-polish / hypo-translate / hypo-check / hypo-presubmithypo-meetinghypo-reviewuv run hypo-research <subcommand> [options]
可用子命令：guide, read, search, cite, idea, challenge, experiment, plan, pilot, project, rebuttal, lint, verify, check, presubmit, review, meeting, glossary, init
Aggregate Codex skill bundle for academic literature search, screening, citation traversal, research ideation, experiment planning, LaTeX lint/fix, bibliography verification, polishing, translation, and one-command paper checks.
Run a multi-persona simulated academic review for a LaTeX or PDF paper. Parses paper structure, prepares reviewer-specific prompts, then guides independent reviews, AC meta-review, revision roadmap, and consistency checks.
Run the full writing-quality pipeline for a LaTeX paper project: lint, auto-fix preview or apply, citation verification, and aggregated reporting. Use this when the user wants a submission-readiness check, a one-command writing QA pass, or a structured report summarizing lint and bibliography health.
Route a natural-language research request to the right Hypo-Research workflow. Use this when the user is unsure whether they need check, review, read, search, ideation, project management, or another expert skill. Can execute conservative safe paths with explicit inputs.
Run a unified pre-submission check pipeline for LaTeX papers, combining structure/format checks, LaTeX lint, and bibliography verification into one PASS/WARNING/FAIL report. Use when the user is preparing a paper submission, wants CI-friendly preflight checks, or asks for a complete submission-readiness report.
Ingest academic PDFs into structured read artifacts, render outlines, and extract heuristic evidence cards for methods, datasets, figures, and claims. Use this when the user wants to read, summarize, inspect, or deep-read a PDF.