Academic research assistant toolkit for survey, search, screening, citation traversal, LaTeX lint/fix, bibliography verification, polishing, translation, and check pipelines.
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.
Expand a literature candidate pool by traversing the citation graph from seed papers. Uses Semantic Scholar and OpenAlex APIs to discover citing and cited papers, deduplicates, and outputs results compatible with /hypo-screen. Use this whenever the user wants to find papers connected to known seed papers, asks for citation-network expansion, or needs a Litmaps / Connected-Papers-style discovery step between survey and screening.
Check the structural quality of a LaTeX paper project. Use this whenever the user wants to lint, review, normalize, or auto-fix LaTeX structure issues: labels, refs, floats, citations, table environments, spacing, BibTeX fields, title case, or abbreviation expansion. Run the stats extractor first, let the script collect objective facts, then apply Agent judgment for abbreviation and title-case recommendations, and optionally patch auto-fixable issues.
Polish academic English in LaTeX papers. Use this whenever the user wants to improve wording, clarity, concision, sentence flow, paragraph transitions, or section-level writing quality in a paper, rebuttal, abstract, or technical draft. Run the stats extractor first, let it surface long sentences and repetitive openings, then have the Agent perform the actual language rewrite.
Screen and classify papers from a Hypo-Research survey output directory using user-defined rules. Generates a classification report with per-paper labels, category counts, and an analysis summary.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
学术文献调研 AI Skill 包,在 Codex CLI 或 Claude Code 中一键调用,三源并行检索、自动去重验证、生成结构化报告。
/hypo-survey 等命令直接调用,Agent 自动完成全流程git clone https://github.com/HypoxanthineOvO/Hypo-Research.git
cd Hypo-Research
uv sync
./install-skills.sh
没有 uv?
curl -LsSf https://astral.sh/uv/install.sh | sh
git clone https://github.com/HypoxanthineOvO/Hypo-Research.git
cd Hypo-Research
uv sync
./install-skills.sh
/plugin marketplace add HypoxanthineOvO/Hypo-Research
/plugin install hypo-research@hypoxanthineovo-hypo-research
当前 Codex skill-installer 的稳定方式是从 GitHub repo/path 安装一个 skill bundle:
$skill-installer https://github.com/HypoxanthineOvO/Hypo-Research/tree/main/.agents/skills/hypo-research
说明:
# Semantic Scholar API Key — 大幅提升搜索速率,不设置也能用
export SEMANTIC_SCHOLAR_API_KEY="your-key-here"
# 申请: https://www.semanticscholar.org/product/api#api-key-form
项目级配置文件也支持:
uv run hypo-research init
uv run hypo-research init --dir ./paper
优先级:CLI 参数 > .hypo-research.toml > 环境变量 > 内置默认值。
Packaging 入口:
.claude-plugin/marketplace.jsonplugins/hypo-research/.claude-plugin/plugin.json.agents/skills/hypo-research/SKILL.mdHypo-Research provides 8 Skills organized into two modules:
| Skill | Command | Description |
|---|---|---|
/hypo-survey | uv run hypo-research search | Comprehensive literature survey with multi-source search, deduplication, and verification |
/hypo-search | uv run hypo-research search | Quick targeted search for specific papers or topics |
/hypo-screen | Agent-driven (no standalone CLI) | Filter and classify papers by relevance criteria |
/hypo-cite | uv run hypo-research cite | Citation graph traversal — expand references and citations from seed papers |
| Skill | Command | Description |
|---|---|---|
/hypo-lint | uv run hypo-research lint | LaTeX structure checking — 13 rules covering \cref, floats, labels, tblr, title case, spacing, and more |
/hypo-verify | uv run hypo-research verify | Citation verification — check .bib entries against Semantic Scholar and OpenAlex |
/hypo-polish | uv run hypo-research lint --stats | English polishing — full-document scan or targeted section rewriting (Agent-driven, uses chapter_stats) |
/hypo-translate | uv run hypo-research lint --stats | Bilingual maintenance — sync/cn2en/en2cn modes for % 中文注释 + English paragraph pairs |
/hypo-check | uv run hypo-research check | Writing pipeline — lint, auto-fix, verify, and save an aggregated report |
/hypo-survey — 综合文献调研完整的多源文献调研。Agent 自动设计查询、扩展关键词、三源并行检索、去重验证、生成报告。
| 参数 | 必填 | 说明 | 示例 |
|---|---|---|---|
topic | ✅ | 调研主题 | "NeRF real-time rendering" |
year_range | 年份范围 | 2020-2026(默认近 5 年) | |
sources | 数据源 | all / s2 / openalex / arxiv |
示例:
/hypo-survey topic="NeRF real-time rendering" year_range=2020-2026
Agent 会自动:
"neural radiance field real-time"、"instant NGP"、"3D Gaussian splatting acceleration"📊 检索完成
- 论文数:142(87 verified,55 single-source)
- Top 5:
1. Instant-NGP (2022, SIGGRAPH, citations=1847)
2. 3D Gaussian Splatting (2023, SIGGRAPH, citations=956)
3. Plenoxels (2022, CVPR, citations=892)
4. TensoRF (2022, ECCV, citations=634)
5. Mip-NeRF 360 (2022, CVPR, citations=587)
- 输出目录:data/surveys/2026-04-22_nerf_realtime/
/hypo-screen — 文献筛选分类按自定义规则对调研结果进行筛选、分类、分析。将大候选池收敛为结构化的分类报告。
| 参数 | 必填 | 说明 | 示例 |
|---|---|---|---|
path | ✅ | 调研结果目录 | "data/surveys/2026-04-22_fhe_hw/" |
rules | ✅ | 分类规则(自然语言) | 见下方示例 |
recall_checklist | 已知重要论文列表 | "Cinnamon, Hydra, ARK, ..." |
示例:
npx claudepluginhub hypoxanthineovo/hypo-research --plugin hypo-researchHypo-Workflow for Claude Code. The plugin namespace is intentionally `hw`; plugin-root commands map /hw:* to existing workflow Skills.
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
This skill should be used when users need to generate ideas, explore creative solutions, or systematically brainstorm approaches to problems. Use when users request help with ideation, content planning, product features, marketing campaigns, strategic planning, creative writing, or any task requiring structured idea generation. The skill provides 30+ research-validated prompt patterns across 14 categories with exact templates, success metrics, and domain-specific applications.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.