菜单
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.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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.
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 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.
| name | hypo-read |
| description | 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. |
| license | MIT |
hypo-read 面向论文 PDF 阅读。它把 PDF 转成稳定的 artifact.json，再支持提纲和 L2 evidence cards。
uv run hypo-research read ingest paper.pdf --out data/reads/paper
uv run hypo-research read ingest ./paper-folder --out data/reads/paper
uv run hypo-research read ingest paper.zip --out data/reads/paper
uv run hypo-research read outline data/reads/paper/artifact.json
uv run hypo-research read extract data/reads/paper/artifact.json --out data/reads/paper/cards
read ingest：解析 PDF 文本、页数、章节和图像占位信息，写入 artifact.json。read outline：从 artifact 输出标题、页数、抽取质量和章节提纲。read extract：抽取 methods、datasets、figures、claims 四类 evidence cards，输出 cards.json 和 cards.md。先运行 ingest，再读取 outline 判断抽取质量。深读时使用 read extract 的 cards，把回答绑定到方法、数据、图表和 claim 证据，不要只做泛泛摘要。
read ingest 的 target 可以是单个 PDF、包含唯一 PDF 的文件夹或 .zip / .tar* 压缩包。多 PDF 时要求用户指定具体文件。