Skip to content
Agentmart
Submit a tool

hypo-lint

Check the structural quality of a LaTeX paper project.

Skill by HypoxanthineOvO

IndexedMIT★ 2
Write a review

Chalk Labs

Need help deploying hypo-lint?

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-lint

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

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.

Use cases: documents, 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-lint

What's inside

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

Files (1)

  • SKILL.md

SKILL.md (first lines)

# /hypo-lint — LaTeX 结构检查

脚本负责事实提取,Agent 负责判断。先运行统计提取器得到结构 JSON,再根据规则输出检查报告;如果用户要求修复,则只自动修改明确可修复项。

如果项目根目录存在 `.hypo-research.toml`,可直接读取 `project.main_file`、`project.bib_files`、`lint.disabled_rules`、`lint.fix_rules` 等默认值。

## 参数

$ARGUMENTS
- path: LaTeX 项目路径(必填)
- bib: `.bib` 文件路径(可选)
- project_dir: 显式项目根目录(可选,多文件项目时优先)
- rules: 只检查指定规则(可选,如 `L01,L04,L07`)
- fix: 是否自动修复可修复项(可选,布尔值)

## 工作流

1. 运行统计脚本:

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

如果用户显式给了 `.bib` 文件:

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

多文件项目可直接从主文件或子文件启动:

```bash
uv run hypo-research lint --stats main.tex
uv run hypo-research lint --stats sections/intro.tex
uv run hypo-research lint --stats --project-dir ./paper main.tex
```

2. 读取 JSON 中的 `issues` 数组,逐项报告 L01-L08、L11-L13 的客观违规项。

3. 对 Agent 判断类规则做人工判断:
   - L09:读取 `abbreviations` 中 `has_expansion=false` 的条目,结合 `context_before` / `context_after` 判断首次出现是否缺全称展开。
   - L10:读取 `sections` 标题,按 AP Style Title Case 给出修正建议。

4. 如果 `fix=true`:
   - 自动修复 L01/L02/L03/L04/L05/L06/L11/L13。
   - 修复 L06 时,同步替换全文对应 `\cref{old_label}` / `\ref{old_label}` / `\autoref{old_label}`。
   - 对 L09/L10 仅输出建议 diff,不自动应用。
   - 对 L07/L08/L12 只报告,不修复。

5. 输出最终报告:
   - 问题摘要(errors / warnings / info)
   - 每条问题的位置和修复建议
   - 如有修复,给出已应用的 patch 概要

## 规则表

| ID  | 规则 | 自动修复 |
|-----|------|----------|
| L01 | 禁用 `\ref` / `\autoref`,必须用 `\cref` | ✅ |
| L02 | `\cref` 前必须有 `~`(除非在句首) | ✅ |
| L03 | `\cite` 前必须有 `~`(除非在句首) | ✅ |
| L04 | 浮动体 `figure/table` 必须带 `[htbp]` | ✅ |
| L05 | `\label` 必须在 `\caption` 之后 | ✅ |
| L06 | label 必须有规范前缀 `fig:` / `tab:` / `sec:` / `eq:` | ✅ |
| L07 | 禁用 `tabular` / `tabularx`,优先 `tblr` | ❌ 报告 |
| L08 | 未引用的 label / 未定义的 ref | ❌ 报告 |
| L09 | 缩写首次引用必须有全称展开 | ⚠️ 建议 |
| L10 | 标题 Title Case(AP Style) | ⚠️ 建议 |
| L11 | `Fig.` / `Tab.` / `Eq.` / `et al.` 后正确间距 | ✅ |
| L12 | BibTeX 必填字段缺失 | ❌ 报告 |
| L13 | 连续多空格 / 行尾空格 | ✅ |

## 输出要求

- 默认先基于 `uv run hypo-research lint --stats ...` 的 JSON 输出结论,不要先凭感觉读全文。
- 报告 findings 时按严重性排序,优先列出 `error`。
- 如果用户要求修复,只修明确的结构问题;涉及学术判断的 L09/L10 只给建议,不擅自改写。

## Auto-Fix

The lint skill supports automatic fixing of common issues.

### Dry-run (preview changes)

```bash
uv run hypo-research lint --fix paper.tex
uv run hypo-research lint --fix main.tex
```

### Apply fixes

```bash
uv run hypo-research lint --fix --no-dry-run paper.tex
uv run hypo-research lint --fix --no-dry-run --backup paper.tex
```

### Filter rules

```bash
uv run hypo-research lint --fix --rules L01,L04 paper.tex
```

### Auto-fixable rules

| Rule | Fix |
|------|-----|
| L01 | `\ref` → `\cref` |
| L02 | Insert `~` before `\cite` |
| L03 | Remove redundant prefix before `\cref` |
| L04 | Add `[htbp]` to float environments |
| L05 | Title case for section/caption titles |
| L06 | Delete orphan `\label` |
| L11 | `\toprule` / `\midrule` / `\bottomrule` → `\hline` in `tblr` |
| L13 | Insert `~` before `\cref` |

## Config Support

如果项目根目录存在 `.hypo-research.toml`,优先读取:

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-lint 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-lint?

CallGet help
Cite this page

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