research-survey
Generates structured literature survey reports from collected papers using a multi-stage pipeline: outline generation (query-type adaptive) → draft survey → section-by-section expansion → summary section refinement → final assembly. Produces survey-grade output with taxonomy-based method analysis, LaTeX formalizations, comparative tables, and dense citations. Use when: user wants a literature review, research survey, field overview, or systematic synthesis of multiple papers. Do NOT use for finding/searching papers (use paper-navigator), generating research ideas (use research-ideation), or writing a paper's Related Work section (use paper-writing).
- Installs
- 301
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/evoscientist/evoskills --skill research-survey- 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 research-survey 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.
Research Survey
Generates high-quality, survey-grade literature reviews from papers collected by paper-navigator.
paper-navigator (collect 30-120 papers)
↓
Stage 1: Generate Outline (query-type adaptive structure)
↓
Stage 2: Draft Survey (outline + top-30 papers)
↓
Stage 3: Expand Sections (draft + all papers, section-by-section)
↓
Stage 4: Generate Section Summaries
↓
Stage 5: Refine Summary Sections (Abstract/Intro/Conclusion)
↓
Stage 6: Assemble + References
When to Use
- User asks for a "literature review", "survey", "field overview", or "systematic review"
- User has collected papers and wants them synthesized into a structured report
- User wants to understand the full landscape of a research field
When NOT to Use
- Finding papers → use
paper-navigatorfirst, then come here - Generating research ideas → use
research-ideation - Writing a Related Work section for a paper → use
paper-writing
Dependency: paper-navigator
This skill requires papers as input. If the user hasn't provided papers, first invoke paper-navigator (Workflow 1, target 30-120 papers) to collect them.
CRITICAL: All paper discovery MUST use the paper-navigator skill and its scripts (scholar_search, citation_traverse, arxiv_monitor, recommend, etc.). Using WebSearch, WebFetch, or any generic web search tool for finding papers is PROHIBITED. Generic web search cannot access Semantic Scholar, citation graphs, or academic recommendation systems. Only paper-navigator provides the academic search infrastructure needed for survey-quality literature collection.
Stage 1: Generate Outline
This is a two-phase process. Different fields have different survey conventions — a clinical systematic review looks nothing like a CS methods survey. First generate a domain-appropriate template, then create the detailed outline.
Phase 1A: Generate Domain-Specific Survey Template
Before outlining, identify the field and adapt the structure:
- Identify the field from the user's goal and collected papers
- Select section names and organization logic using the field-specific conventions in
assets/survey-template.md(e.g., medicine organizes by intervention type and follows PRISMA; chemistry organizes by reaction class; social sciences organize by theoretical perspective) - Add field-specific sections (e.g., Risk of Bias Assessment for medicine, Structure-Property Relationships for materials, Ethical Considerations for human-subjects research)
- Determine comparison table dimensions appropriate to the field
Phase 1B: Create Detailed Outline
With the domain-specific template as the framework, generate the outline:
Query Type Classification
| Type | Example | Structure |
|---|---|---|
| A: Single-topic deep dive | "Catalyst design for electrochemical CO2 reduction" | Intro → Problem Definition → Methods (by mechanism/approach) → Evaluation → Challenges → Conclusion |
| B: Multi-topic parallel | "Drug resistance mechanisms and therapeutic strategies in cancer immunotherapy" | Intro → Topic 1 (definition + methods) → Topic 2 (definition + methods) → Evaluation → Challenges → Conclusion |
| C: Pipeline/stage-based | "From sample preparation to data analysis in single-cell RNA sequencing" | Chapters organized by workflow stages |
Outline Requirements
The outline is NOT a simple heading list — it's a blueprint with meta-instructions for each section. For each ## Section:
- Include
[Instruction: ...]specifying what the section must contain - Specify required tables with field-appropriate columns
- For main body sections: mandate taxonomy by underlying principle/mechanism, NOT chronology
- Include any field-required elements (e.g., PRISMA flowchart for medical systematic reviews, mathematical formalism for physics)
See references/survey-methodology.md for full outline generation rules and assets/survey-template.md for field-specific conventions.
Stage 2: Draft Survey
Generate a complete draft from the outline using the top-30 most relevant papers.
- Use numbered citations [1], [2, 3] throughout
- Follow the outline's meta-instructions strictly
- Each methods section must build a taxonomy and include comparison tables
- Problem definition must include LaTeX formalization (
$$...$$)
Stage 3: Expand Sections
Expand each non-summary section using all collected papers (30-120). This is where survey-grade depth is achieved.
Section Expansion Targets
| Section Type | Target Length | Focus |
|---|---|---|
| Methods | 6000+ words per paradigm chapter | Technical narratives, mechanism analysis, comparison tables |
| Evaluation | 3500+ words | Benchmark taxonomy, metric analysis, SOTA summary |
| Challenges | 3000+ words | Problem definition + evidence + opportunity per challenge |
| Applications | 3000+ words | Real-world use cases with specific achievements |
| Problem Definition | 2000+ words | LaTeX formalization, constraints, assumptions |
| Other | 2500+ words | Default |
Expansion Rules
- Thematic coherence: Keep same themes and narrative flow as draft — don't introduce unrelated topics
- Cite comprehensively: Use as many relevant papers from the full collection as possible
- Survey-grade depth: Multi-paragraph technical narratives per method family, not shallow bullet points
- For each paradigm/method family, include:
- Technical narrative: How it works, theoretical assumptions, nuances between papers
- Critical analysis: Why effective, trade-offs, failure modes
- Comparative analysis table: Method | Core Mechanism | Key Advantage | Limitation | Performance
Stage 4: Generate Section Summaries
After all content sections are expanded, generate a condensed summary for each major section:
- Summarize each expanded section in 150-300 words
- Preserve the key taxonomy, representative methods, and main trade-offs
- Keep citation anchors so later summary sections remain grounded
These section summaries become the shared context for the final abstract, introduction, and conclusion.
Stage 5: Refine Summary Sections
After all content sections are expanded, refine the summary sections (Abstract, Introduction, Conclusion):
- Use all section summaries as context to rewrite Abstract, Introduction, Conclusion
- This ensures summary sections accurately reflect the full survey content
Summary Section Standards
Abstract (300-500 words):
- Continuous narrative, NO bullet points or bold labels
- Must cover: background → gap → scope → key findings → outlook
Introduction:
- Continuous narrative, NO subsections or bullet points
- Must cover: research background → why traditional methods fail → method summary → scope & organization
Conclusion:
- Summarize findings, state which paradigm is most promising
- Respond to user's original research goal
- Provide clear "next step" recommendation
Stage 6: Assemble Final Survey
Assemble sections in outline order, then append formatted references:
**1. Title** (Year). _Authors_. *Venue*. Citations: N. [[Link]](url)
Save to /artifacts/survey-{topic}-{date}.md.
Core Quality Principles
-
Build taxonomy, don't enumerate: Cluster papers by technical mechanism, not chronology. This is the defining characteristic of a survey vs. a summary.
-
Critical insight over description: For EVERY method, analyze WHY it works, WHAT trade-off it makes, WHERE it fails. This separates survey-grade writing from shallow summaries.
-
Goal-centric filtering: Every piece of information must answer "How does this help achieve the research goal?" Discard information that doesn't serve the goal, even if it's interesting.
-
Strict terminology fidelity: Use the user's exact technical terms. Do NOT drift to related but different concepts.
-
Dense citations: Ground ALL claims with numbered citations [X]. Nearly every sentence should reference at least one paper.
-
Zero vagueness: Replace generic statements with specific method names, dataset names, metric values, and problem descriptions.
-
Visual structure: Use Markdown tables extensively — paradigm comparison, intra-paradigm method comparison, benchmark tables, metric tables.
Reference Materials
| Resource | Location | Purpose |
|---|---|---|
| Multi-stage pipeline details | references/survey-methodology.md | Full methodology: outline rules, section standards, expansion targets |
| Section quality checklist | references/section-quality-checklist.md | Per-section verification checklist before finalizing |
| Survey output template | assets/survey-template.md | English Markdown template with section structure, table formats, and placeholder guidance |
Handoff
| From → To | When |
|---|---|
paper-navigator → here | Papers collected, user wants synthesis |
Here → research-ideation | Survey reveals research gaps worth pursuing |
Here → paper-writing | Survey informs Related Work section of a paper |
Here → paper-planning | Survey provides literature context for story design |
FAQ
What does the research-survey skill do?
Generates structured literature survey reports from collected papers using a multi-stage pipeline: outline generation (query-type adaptive) → draft survey → section-by-section expansion → summary section refinement → final assembly. Produces survey-grade output with taxonomy-based method analysis, LaTeX formalizations, comparative tables, and dense citations. Use when: user wants a literature review, research survey, field overview, or systematic synthesis of multiple papers. Do NOT use for finding/searching papers (use paper-navigator), generating research ideas (use research-ideation), or writing a paper's Related Work section (use paper-writing).
How do I install research-survey?
Run npx skills add https://github.com/evoscientist/evoskills --skill research-survey 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/research-survey/ (personal) or .claude/skills/research-survey/ (project).
Which AI agents can use research-survey?
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 research-survey 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 research-survey?
It is published by evoscientist in evoscientist/evoskills. It has 301 recorded installs.
More from evoscientist/evoskills
paper-review
evoscientist/evoskills
Guides self-review of YOUR OWN academic paper before submission with adversarial stress-testing. Core method: three passes (adversarial deep read; 5-aspect checklist — contribution sufficiency, writing clarity, results quality, testing completeness, method design; mechanical consistency scans and experimental protocol audit of data flow, assumptions, leakage), counterintuitive protocol (reject-first simulation, delete unsupported claims, score trust, promote limitations, attack novelty), reverse-outlining, and figure/table quality checks. Use when: user wants to self-review or self-check their own paper draft before submission, stress-test their claims, prepare for reviewer criticism, or mentions 'self-review', 'check my draft', 'is my paper ready'. Do NOT use for writing a peer review of someone else's paper, and do NOT use after receiving actual reviews (use paper-rebuttal instead). Also runs as a background expert: dispatch it async with a draft path and it reviews end-to-end while
paper-writing
evoscientist/evoskills
Guides writing academic papers section by section using an 11-step workflow with LaTeX templates and counterintuitive writing tactics. Covers Abstract, Introduction, Method, Experiments, Related Work, Conclusion, and Supplementary. Use when: user asks to write or draft a paper section, needs LaTeX templates, wants to improve academic writing quality, optimize novelty framing, or mentions 'write introduction', 'draft method', 'paper writing'. Do NOT use for pre-submission review (use paper-review), experiment execution (use experiment-pipeline), or paper planning/story design (use paper-planning).
research-ideation
evoscientist/evoskills
End-to-end research ideation pipeline: literature grounding → multi-track idea generation (3 personas: innovator/pragmatist/critic) → iterative refinement → ELO tournament ranking → update evo-memory (IDE) → user selects direction → expand into manuscript-quality proposal. Use when: user wants to find a research direction, brainstorm ideas, evaluate idea novelty, design a novel solution, rank/compare research ideas, or generate a research proposal. Do NOT use for finding/searching/reading papers (use paper-navigator), literature survey reports (use research-survey), or planning a paper (use paper-planning).
academic-slides
evoscientist/evoskills
Use this skill for creating or refining an academic slide deck and the talk built around it: structuring a conference talk, thesis defense, lab meeting, or paper-to-slides deck; deciding the narrative arc and slide breakdown; improving slide design and visual hierarchy; planning rehearsal, timing, Q&A, and backup slides; or generating the .pptx. Reach for it when the user is shaping the presentation itself. Do not use for writing the paper, producing standalone speaker notes/scripts/transcripts, making posters, creating isolated figures/charts outside a slide deck, or building non-academic presentations.
paper-rebuttal
evoscientist/evoskills
Guides writing effective rebuttals after receiving peer review feedback. Covers review diagnosis (score-driven color-coding), response strategy (champion identification, common-theme consolidation), tactical writing (18 rules), and counterintuitive rebuttal principles. Use when: user received reviewer scores/comments, needs to write a rebuttal or author response, wants to respond to specific criticism (e.g. 'limited novelty', 'missing baselines'), mentions 'rebuttal', 'reviewer comments', 'author response', or 'respond to reviewers'. Do NOT use for pre-submission self-review (use paper-review instead).
paper-planning
evoscientist/evoskills
Guides pre-writing planning for academic papers with 4 structured steps: story design (task-challenge-insight-contribution-advantage), experiment planning (comparisons + ablations), figure design (pipeline + teaser), and 4-week timeline management. Includes counterintuitive planning tactics (write a mock rejection letter to identify weaknesses before writing, narrow before broad claims, design ablations first). Use when: user wants to plan a paper before writing, design story/contributions, plan experiments, create figure sketches, set a writing timeline, or write a pre-emptive rejection letter for planning purposes. Do NOT use for actual writing (use paper-writing), running experiments (use experiment-pipeline), self-reviewing a finished draft (use paper-review), or finding research problems (use research-ideation).
Popular productivity & automation skills
agent-browser
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
lark-doc
open.feishu.cn
飞书云文档（Docx / Wiki）内容操作：读取、创建、编辑文档，插入或下载图片附件，以及操作思维笔记。用户提供文档 URL/token（包括 doubao.com 的 /docx/、/wiki/）时使用；按 URL 路径/token 而非域名路由；/page/ 是妙搭应用，非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive；随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。
lark-base
open.feishu.cn
飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式（BaseApp/AppMode 页面与组件）、Workspace 目录、workflow、角色权限、模板中心（多维表格模板分类/列表/搜索）；遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps；文件导入/导出转 lark-drive，认证/授权转 lark-shared。
lark-drive
open.feishu.cn
飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签（secure labels）和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用；doubao.com 云空间 URL/token 也按资源路径和 token 路由，不回退 WebFetch。不负责：文档内容编辑（走 lark-doc）、表格/Base 表内数据操作（走 lark-sheets/lark-base）、知识空间节点/成员管理（走 lark-wiki）、原生 Markdown 文件读写/patch/diff（走 lark-markdown）。
lark-shared
open.feishu.cn
Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.
lark-im
open.feishu.cn
飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。