Skip to content
Agentmart
Submit a tool

hypo-polish

Polish academic English in LaTeX papers.

Skill by HypoxanthineOvO

IndexedMIT★ 2
Write a review

Chalk Labs

Need help deploying hypo-polish?

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-polish

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

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.

Use cases: documents, writing, research, agent-building

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-polish

What's inside

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

Files (1)

  • SKILL.md

SKILL.md (first lines)

# /hypo-polish — 学术英文润色

语言判断完全由 Agent 负责。脚本只负责统计章节信息和定位可疑区域。

如果项目根目录存在 `.hypo-research.toml`,可直接读取 `project.main_file` 作为默认输入文件。

## Parameters

$ARGUMENTS
- `path`: LaTeX 文件或项目目录,必填
- `project_dir`: 显式项目根目录,可选;多文件项目推荐
- `mode`: `full` 或 `targeted`,可选,默认 `full`
- `target`: section 标题或行号范围,`mode=targeted` 时可选但强烈建议提供
- `apply`: 是否直接改文件,可选,默认只输出建议

## Workflow

1. 先运行统计提取器:

```bash
uv run hypo-research lint --stats <path>
```

对于多文件 LaTeX 项目,`<path>` 可以是 `main.tex` 或任一子文件;必要时补 `--project-dir ./paper`。

2. 在 `mode=full` 下:
   - 读取 `chapter_stats`
   - 优先关注:
     - `avg_sentence_length > 25`
     - `long_sentences`
     - `paragraph_starts` 中重复过多的开头词
     - 同级章节中明显过长或过短的部分
   - 输出按章节组织的润色建议

3. 在 `mode=targeted` 下:
   - 先定位用户指定的 section 或行号范围
   - 对该范围逐句润色
   - 输出原文 vs 修改稿的完整段落 diff

4. 如果 `apply=true`:
   - 只在用户明确要求时直接改 `.tex`
   - 优先保持术语、符号、引用、LaTeX 结构不变
   - 不擅自改公式、label、cite key

## Output Format

`mode=full` 时使用:

```markdown
# Polish Report

## Section: Introduction
- Lines 34-41: sentence is too long; split into two sentences.
  Original: ...
  Suggestion: ...
  Reason: ...
```

`mode=targeted` 时使用:

```markdown
# Targeted Polish

## Original
...

## Revised
...

## Notes
- Improved transition
- Removed repetition
```

## Style Guidelines

- 优先简洁表达,少用空泛修饰词,如 `very`, `really`, `quite`, `clearly`
- 优先主动语态,除非被动语态更符合学术写作场景
- 避免连续多句以相同主语开头,尤其是重复的 `We`
- 避免 `it is` / `there are` 这类弱开头
- 术语前后一致,不随意切换同义表达
- 句子过长时优先拆句,而不是堆叠逗号和从句
- 不改变技术结论,只改善表达

## Examples

**Example 1**

Input:

```text
/hypo-polish path="paper.tex" mode=full
```

Output:

```markdown
## Section: Introduction
- Lines 18-19: repeated `We` openings weaken rhythm.
- Line 24: split the 48-word sentence into two shorter sentences.
```

**Example 2**

Input:

```text
/hypo-polish path="paper.tex" mode=targeted target="Method" apply=false
```

Output:

```markdown
## Original
We propose a design and we evaluate the design and we compare it with prior work.

## Revised
We propose the design, evaluate it thoroughly, and compare it with prior work.
```

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
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

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-polish 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-polish?

CallGet help
Cite this page

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