From hypo-research
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.
How this skill is triggered — by the user, by Claude, or both
Slash command
/hypo-research:hypo-screenThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
对已有调研结果按自定义规则进行筛选、分类、分析。将候选论文池收敛为结构化的分类报告。
对已有调研结果按自定义规则进行筛选、分类、分析。将候选论文池收敛为结构化的分类报告。
如果项目根目录存在 .hypo-research.toml,可复用其中的项目级默认路径和调研配置。
$ARGUMENTS
data/surveys/2026-04-22_fhe_hw/)classified)分类规则用自然语言定义,每行一个类别,格式为 类别名: 定义。
示例:
A: FHE + 大模型推理 + 硬件加速器(ASIC/FPGA/GPU)
B: FHE + 硬件加速器(CNN 或更小规模模型)
C: FHE + 大模型推理(纯软件优化)
D: CIM/PIM + FHE
排除: MPC/GC/OT 为主导方案(非纯 FHE)
path 下的 results.json(或 results.md)中的论文列表未分类recall_checklist:
classified_papers.json: 每篇论文含 {title, authors, year, venue, doi, category, reason}analysis_report.md: 含分类计数、关键发现、类别概览、建议references.bib: 标注类别Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
npx claudepluginhub hypoxanthineovo/hypo-research --plugin hypo-research