Skip to content
Agentmart
Submit a tool

hypo-screen

Screen and classify papers from a Hypo-Research survey output directory using user-defined rules.

Skill by HypoxanthineOvO

IndexedMIT★ 2
Write a review

Chalk Labs

Need help deploying hypo-screen?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/hypoxanthineovo-hypo-screen

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

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.

Use cases: documents, research

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/hypo-screen

What's inside

Skill name
hypo-screen
Description
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.
License
MIT
Instructions
51 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# /hypo-screen — 文献筛选分类

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。

## 参数

$ARGUMENTS
- path: 调研结果目录路径（必填，如 `data/surveys/2026-04-22_fhe_hw/`）
- rules: 分类规则（必填，自然语言描述各类别的定义）
- recall_checklist: 已知重要论文列表（可选，用于检查是否漏掉关键论文）
- output_name: 分类报告输出名（可选，默认 `classified`）

## 规则格式

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：

```text
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）
```

## 工作流

1. 读取 `path` 下的 `results.json`（或 `results.md`）中的论文列表
2. 对每篇论文，根据 title + abstract + venue 判断所属类别：
   - 逐篇标注类别标签
   - 如果无法判断，标为 `未分类`
   - 对可疑 / 边界论文给出简要理由
3. 如果提供了 `recall_checklist`：
   - 检查每篇 checklist 论文是否在结果中
   - 对未命中的论文，用标题精确搜索补全
   - 报告 recall 统计（如 24/24 命中）
4. 生成分类报告：
   - `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
   - 更新 `references.bib`: 标注类别
5. 向用户输出：
   - 分类计数表（如 A=2, B=26, C=17, D=9, 排除=7）
   - 每类的代表性论文（Top 3 by citations）
   - Recall checklist 命中率
   - 数据质量评估（单源论文占比、可疑标记数）
   - 建议后续操作（是否需要补充搜索特定方向）

From HypoxanthineOvO/Hypo-Research, MIT.

More from HypoxanthineOvO/Hypo-Research

Signals

Stars
2
Forks
0
Open issues
0
Last commit (this folder)
Apr 24, 2026 (6 months ago)
Last release
May 9, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/HypoxanthineOvO/Hypo-Research
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from HypoxanthineOvO

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get hypo-screen running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying hypo-screen?

CallGet help
Cite this page

hypo-screen skill. Agent Mart. https://agentmart.dev/skills/hypoxanthineovo-hypo-screen (last updated 2026-10-24)