MCPInstall

check-review-alignment

当用户明确要求"核查/优化综述 {主题}review.tex 的正文引用"或"运行 check-review-alignment"时使用。通过宿主 AI 的语义理解逐条核查引用是否与文献内容吻合,只在发现致命性引用错误时对"包含引用的句子"做最小化改写,并复用 systematic-literature-review 的渲染脚本输出 PDF/Word。核心原则:不为了改而改,无法确定是否为致命性错误时保留原样并在报告中警告。⚠️ 不适用:用户只是想生成系统综述正文(应使用 systematic-literature-review);用户只是想新增/核对 BibTeX 条目(应使用专门的 bib 管理流程)。

Installs
97
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/huangwb8/chineseresearchlatex --skill check-review-alignment
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads check-review-alignment automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Check Review Alignment

与 bensz-collect-bugs 的协作约定

  • 当用户环境中出现因本 skill 设计缺陷导致的 bug 时,优先使用 bensz-collect-bugs 按规范记录到 ~/.bensz-skills/bugs/,严禁直接修改用户本地 Claude Code / Codex 中已安装的 skill 源码。
  • 若 AI 仍可通过 workaround 继续完成用户任务,应先记录 bug,再继续完成当前任务。
  • 当用户明确要求“report bensz skills bugs”等公开上报动作时,调用本地 gh 与 bensz-collect-bugs,仅上传新增 bug 到 huangwb8/bensz-bugs;不要 pull / clone 整个 bug 仓库。

定位

  • 用于检查已有 {主题}_review.tex 的正文引用是否真的与对应论文内容一致。
  • 只在确认存在致命错误时最小化改写“包含该引用的句子”。
  • 渲染 PDF/Word 依赖 systematic-literature-review;准备结构化输入不依赖该 skill。

输入

  • work_dir:包含 *_review.tex 与 .bib
  • 可选 --tex:指定 tex 文件名

输出

  • {work_dir}/.check-review-alignment/ai_alignment_report.md
  • {work_dir}/.check-review-alignment/ai_alignment_input.json
  • 修改后的 {主题}_review.tex
  • 新生成的 {主题}_review.pdf
  • 新生成的 {主题}_review.docx

修改边界

  • P0:必须修,允许最小改写或修正错误 bibkey
  • P1:仅警告,不改写
  • P2:完全跳过
  • 禁止:
    • 改写未包含引用的句子
    • 整段重写
    • 引入新 bibkey(除非修复错误 key)
    • 伪造论文内容

工作流

1. 依赖检查

  • 只有执行渲染时才强制检查 systematic-literature-review
  • 若只是 --prepare,不要求渲染依赖可用

2. 预检与定位

  • 找到 *_review.tex 与对应 .bib
  • 缺任何核心文件时立即停止

3. 结构化上下文抽取

cd /path/to/check-review-alignment
python3 scripts/run_ai_alignment.py --work-dir "/path/to/work_dir" --prepare
  • 生成 ai_alignment_input.json
  • 输入中至少包含:句子、bibkey、文献元信息、DOI/URL、PDF 摘要段或 BibTeX 摘要

4. AI 语义核查

  • 证据优先级:PDF 摘要段 > BibTeX abstract/title > 仅从句子推断
  • 每条引用都要判断是否为:
    • fake_citation
    • wrong_citation
    • contradictory_citation
    • weak_support
    • overclaim
    • style_issue
  • 无法确认时保持原样,并记录到 Warnings

5. 报告

  • 报告至少包含:
    • Summary
    • 具体细节
    • Critical Fixes (P0)
    • Warnings (P1)
    • Rendering Result
  • 每条引用的细节至少包含:标题、DOI、原句、文献实际内容、合理性评估、问题级别

6. 渲染

cd /path/to/check-review-alignment
python3 scripts/run_ai_alignment.py --work-dir "/path/to/work_dir" --render

核心原则

  • 不为了改而改
  • 无法确认时不动
  • 只改必要句子
  • 保留所有 LaTeX 命令结构

参考与验证

  • 配置见 config.yaml
  • 脚本入口:scripts/run_ai_alignment.py
  • 渲染依赖:systematic-literature-review

FAQ

What does the check-review-alignment skill do?

当用户明确要求"核查/优化综述 {主题}review.tex 的正文引用"或"运行 check-review-alignment"时使用。通过宿主 AI 的语义理解逐条核查引用是否与文献内容吻合,只在发现致命性引用错误时对"包含引用的句子"做最小化改写,并复用 systematic-literature-review 的渲染脚本输出 PDF/Word。核心原则:不为了改而改,无法确定是否为致命性错误时保留原样并在报告中警告。⚠️ 不适用:用户只是想生成系统综述正文(应使用 systematic-literature-review);用户只是想新增/核对 BibTeX 条目(应使用专门的 bib 管理流程)。

How do I install check-review-alignment?

Run npx skills add https://github.com/huangwb8/chineseresearchlatex --skill check-review-alignment in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/check-review-alignment/ (personal) or .claude/skills/check-review-alignment/ (project).

Which AI agents can use check-review-alignment?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is check-review-alignment safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains check-review-alignment?

It is published by huangwb8 in huangwb8/chineseresearchlatex. It has 97 recorded installs.

More from huangwb8/chineseresearchlatex

View all →

systematic-literature-review

huangwb8/chineseresearchlatex

当用户明确要求"做系统综述/文献综述/related work/相关工作/文献调研"时使用。AI 自定检索词,多源检索→去重→AI 逐篇阅读并评分(1–10分语义相关性与子主题分组)→按高分优先比例选文→自动生成"综/述"字数预算→资深领域专家自由写作(固定摘要/引言/子主题/讨论/展望/结论),保留正文字数与参考文献数硬校验,强制导出 PDF 与 Word。支持多语言翻译与智能编译(en/zh/ja/de/fr/es)。

nsfc-justification-writer

huangwb8/chineseresearchlatex

Open the skill to read its SKILL.md instructions.

Docs & Writing379 installs

nsfc-research-content-writer

huangwb8/chineseresearchlatex

Open the skill to read its SKILL.md instructions.

Docs & Writing307 installs

nsfc-research-foundation-writer

huangwb8/chineseresearchlatex

Open the skill to read its SKILL.md instructions.

Docs & Writing235 installs

nsfc-abstract

huangwb8/chineseresearchlatex

当用户明确要求"写/润色 NSFC 标书摘要""生成中文摘要和英文摘要""把中文摘要翻译成英文摘要"时使用。输出中文、英文两个版本(英文必须是中文的忠实翻译版),同时输出标题建议(1个推荐标题+5个候选标题及理由)。中文摘要默认≤400字符,英文摘要默认≤4000字符。输出方式:将结果写入工作目录下的 NSFC-ABSTRACTS.md。⚠️ 不适用:用户只想翻译一段与标书无关的通用文本(应直接翻译);用户只想写立项依据/研究内容/研究基础正文(应使用对应 nsfc 系列 skill)。

205 installs

nsfc-reviewers

huangwb8/chineseresearchlatex

Open the skill to read its SKILL.md instructions.

191 installs

Popular code quality & workflow skills

View category →

grill-me

mattpocock/skills

A relentless interview to sharpen a plan or design.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

handoff

mattpocock/skills

Compact the current conversation into a handoff document for another agent to pick up.

domain-modeling

mattpocock/skills

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

codebase-design

mattpocock/skills

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

diagnosing-bugs

mattpocock/skills

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.