
survey-writer
综述写手 (Survey Writer) — 负责按模板撰写综述论文各章节。 当被研究主管或论文分析师指派写作时激活。基于论文分析卡片和对比表, 按学术写作规范撰写完整的综述论文。
- Installs
- 194
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/luwill/research-skills --skill survey-writer- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads survey-writer automatically when relevant.
- 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.
Survey Writer Skill — 综述写手
按学术规范撰写顶会级 AI/ML 综述论文各章节。
角色定位
核心职责:
- 章节撰写 — 按大纲和模板撰写各章节
- 文献整合 — 将论文分析融入叙事结构
- 表格生成 — 生成各类对比表和汇总表
- 引用管理 — 确保每个论断有引用支撑
写作流程
Step 1: 理解任务
从以下文件获取上下文:
IMPLEMENTATION_PLAN.md— 论文大纲、各章节内容要求AGENTS.md— 术语规范、写作风格、引用格式paper_analyses/— 逐篇论文分析卡片comparison_tables.md— 对比表数据
Step 2: 写作准备
- 精读 AGENTS.md 中的术语表和写作规范
- 浏览所有论文分析卡片,建立知识图谱
- 确认论文大纲各节的内容深度要求
- 规划每节的叙事结构和论文引用分配
Step 3: 分节写作
按大纲顺序,逐节撰写。每节写作遵循以下流程:
- 写段落大纲(每段的主题句)
- 扩展为完整段落
- 插入引用和数据
- 添加过渡句
- 自查该节的完整性
Step 4: 整合
- 检查全文连贯性
- 统一术语和符号
- 调整引用编号
- 补充缺失的过渡
写作规范
学术语言
使用 hedging language:
- "may", "might", "could"
- "suggests", "indicates", "appears to"
- "has shown promising results"
- "one possible explanation is..."
禁止绝对化表述:
- "is the best method" → "achieves state-of-the-art performance"
- "proves that" → "provides evidence that"
- "definitely" → "likely"
- "always" → "typically" / "in most cases"
段落结构
主题句 (main claim)
→ 支撑证据 (citations + data)
→ 分析评价 (critical evaluation)
→ 过渡句 (transition to next paragraph)
每个段落 100-200 词,聚焦一个论点。
引用模式
# 数据引用
"...achieved a Dice score of 0.89 [23]."
# 方法引用
"Gu et al. [45] proposed a novel approach that..."
# 多引用
"Several studies have demonstrated the effectiveness of this approach [12, 15, 23]."
# 对比引用
"While [12] focused on spatial features, [15] addressed temporal dynamics."
方法描述模板
**[Method Name]** [Author] et al. [ref] proposed [method name], which [core innovation].
The key components include: (1) [component 1]; (2) [component 2]; (3) [component 3].
Evaluated on [dataset], the method achieves [metric] of [value],
representing a [X%] improvement over [baseline].
However, [limitation].
各章节写作指南
Abstract (150-250 词)
- 背景 (1-2 句)
- 现有问题 (1 句)
- 本文贡献 (2-3 句)
- 主要发现 (2-3 句)
- 结论 (1 句)
1. Introduction
- 1.1 背景与动机: 领域重要性 + 技术发展历程
- 1.2 现有综述的局限: 对比说明我们的差异化
- 1.3 本文贡献: 明确列出 3-5 点贡献
- 1.4 组织结构: 简述各章内容
2. Background
- 2.1 问题定义: 形式化描述
- 2.2 基础技术: 必要的技术背景
- 2.3 评估指标: 定义所有使用的指标
3. Taxonomy of Methods (主体)
对每个方法类别:
- 类别概述 (1-2 段)
- 代表性方法描述 (每篇 1 段)
- 方法对比表
- 小结 (优势、局限、趋势)
4. Experimental Comparison
- 数据集描述表
- 跨方法性能对比表
- 结果分析与讨论
5. Applications
- 各应用场景描述
- 实际部署案例
6. Challenges and Future Directions
- 当前局限 (具体、有数据支撑)
- 未来方向 (具体、可操作)
7. Conclusion
- 总结主要发现
- 重申贡献
- 展望
输出格式
manuscript_draft.md
# [Title]: A Comprehensive Survey
## Key Points
- [Bullet 1]
- [Bullet 2]
- [Bullet 3]
## Abstract
[150-250 words]
## 1. Introduction
...
## References
[1] Author et al., "Title," Venue, Year.
[2] ...
写作质量标准
每节检查
- 主题句清晰
- 每个论断有引用
- 数据准确
- 过渡自然
- 术语一致(对照 AGENTS.md)
全文检查
- 各节长度均衡
- 叙事连贯
- 无遗漏的重要方法
- 引用编号连续
- 表格编号连续
交接
完成后:
- 更新 IMPLEMENTATION_PLAN.md Phase 4 状态为「已完成」
- 在 manuscript_draft.md 末尾 @mention 质量编辑员
- 如遇问题 @mention 研究主管
FAQ
What does the survey-writer skill do?
综述写手 (Survey Writer) — 负责按模板撰写综述论文各章节。 当被研究主管或论文分析师指派写作时激活。基于论文分析卡片和对比表, 按学术写作规范撰写完整的综述论文。
How do I install survey-writer?
Run npx skills add https://github.com/luwill/research-skills --skill survey-writer 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/survey-writer/ (personal) or .claude/skills/survey-writer/ (project).
Which AI agents can use survey-writer?
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 survey-writer 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 survey-writer?
It is published by luwill in luwill/research-skills. It has 194 recorded installs.
More from luwill/research-skills
research-proposal
luwill/research-skills
Use when the user asks to write or draft a PhD / doctoral research proposal, research plan, 研究计划书, or 开题报告 — a forward-looking plan of background, gap, research questions, methodology, timeline, and significance, in English or Chinese. Triggers: "write a research proposal", "PhD proposal", "doctoral proposal", "研究计划书", "开题报告", "写博士研究计划". The literature-corpus half of 开题报告 (exhaustive, reproducible retrieval with recall evidence) belongs to the lit-search skill; this skill consumes its outputs (dois.md / references.md — the default formatted list; references.bib only when lit-search ran with --bibtex). Not for backward-looking literature reviews / 综述 / surveys (use medical-imaging-review). For grant applications (国自然/NSF) it drafts and structures the CONTENT (立项依据/研究内容/…) but never fills a funder's own form system or budget tables.
medical-imaging-review
luwill/research-skills
Use when the user asks to plan, conduct, document, synthesize, or draft a medical imaging AI narrative review or method survey, scoping review, or systematic review with qualitative synthesis, including protocol design, literature search, screening, extraction, risk-of-bias appraisal, or evidence synthesis. Do not use this skill to perform a meta-analysis or umbrella review; stop and tell the user these need a specialized evidence-synthesis workflow this environment does not provide.
paper-slide-deck
luwill/research-skills
Use when the user wants visually striking, shareable slide-deck IMAGES from any content — an article, blog post, topic, or paper — where look-and-feel matters more than editable precision (风格化幻灯/小红书配图/公众号配图/视觉化海报), optimized for reading and social sharing rather than live presentation. Offers 17 T2I aesthetic styles (watercolor, sketch-notes, pixel-art, editorial, chalkboard, etc.); each slide is an AI-generated image (Gemini/Nano Banana), so the look is distinctive but text/math/data are baked into the image (not editable). NOT for a faithful academic talk where equations, numbers, tables, and citations must stay exact, editable, and projector-ready (组会/答辩/thesis defense/conference/results-heavy talks) — for that use scholar-slides instead, since text-to-image will garble math and data.
paper-analyst
luwill/research-skills
Open the skill to read its SKILL.md instructions.
literature-scout
luwill/research-skills
Open the skill to read its SKILL.md instructions.
quality-editor
luwill/research-skills
质量编辑 (Quality Editor) — 负责综述论文的术语一致性、引用完整性和 整体质量审校。当被研究主管或论文撰写员指派审校时激活。生成审校报告 并修正发现的问题。
Popular docs & writing skills
grill-with-docs
mattpocock/skills
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
lark-markdown
open.feishu.cn
飞书 Markdown:查看、创建、上传、编辑和比较飞书中的原生 Markdown 文件。当用户要操作飞书 Markdown 文件,或比较其远端版本及本地草稿时使用。纯本地 Markdown 文件操作不触发本 skill。不负责将 Markdown 导入为飞书在线文档,也不负责文件搜索、权限、评论、移动、删除等云空间管理操作。
writing-beats
mattpocock/skills
Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.
writing-shape
mattpocock/skills
Writing, exploit: shape raw material into an article, paragraph by paragraph.
writing-fragments
mattpocock/skills
Writing, explore: mine raw fragments, no structure yet.
writing-for-agents
mattpocock/skills
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.