Literature Review Builder
Organize papers and identify research gaps
Literature Review Builder
Organize papers and identify research gaps
Showcase
Description
Help graduate students, early-career faculty, and researchers turn a pile of scattered literature (PDFs, notes, keywords) into a logically clear literature review where every claim can be traced and used directly in a paper. The three-step source-tracing method guides you through scope definition, individual paper extraction, and four-line weaving, providing templates and editable intermediate outputs throughout without fabricating citations. Ideal for research proposals, thesis background chapters, and grant applications when you are stuck organizing too many papers or finding research gaps.
Recommended by
Dancang
Why we love this skill
Uses a three-step method of scope cards, literature cards, and four-thread weaving to turn scattered references into a verifiable and traceable review framework, avoiding ungrounded summaries and fabricated citations while clearly extracting research gaps.
Best for
Ideal for graduate students, early-career researchers, and academics preparing proposals, literature reviews, or grant foundations.
How to use this Skill
Provide your input
Provide PDFs, references, notes, titles, or keywords related to your topic, along with the review's purpose, research questions, scope, and citation rules.
Run the Skill
The tool first helps define the search scope, extracts viewpoints, methods, conclusions, and limitations per paper, and then organizes the material while preserving source tags.
Review your result
Receive an editable literature review draft, literature cards, paragraph-to-source mapping tables, and an evidence-backed research gap list.
Related Skills
View all
Literature Review Assistant
Writing a literature review is an inevitable challenge for graduate students—but turning information from 50 papers into a logically structured review, rather than a mere summary list, relies on methodology, not brute force. Tell it your research direction and the core papers you've already read. It first builds a framework—field map, thematic sorting, debates and gaps—then, after your confirmation, helps organize the language chapter by chapter. It doesn't write the paper for you, but helps you present the papers you've read with academic logic. ✨ Core Capabilities 1. Review framework generation: Introduction → Field map → Thematic sections → Debates and gaps → Outlook, standard academic structure 2. Field map: Sort domain development by timeline/school of thought, highlight milestone papers 3. In-depth thematic analysis: Individual paper introduction + intra-group comparison + overall contributions and limitations 4. Debate and gap analysis: At least 3 points of debate + 3 research gaps, with specific literature sources 5. Academic writing norms: Citation format, bilingual terminology, critical language rather than mere description 📱 Use Cases - Literature review chapter for graduate thesis/proposal writing - Related Work section of journal papers - Quick literature overview + structured notes when entering a new field - Used in combination with "论文速读笔记" and "论文双模研读" to form a "Read → Analyze → Synthesize" literature workflow ⚠️ Note: This skill does not perform real-time academic search. You need to provide information on papers you have already read (title/author/key points), and it helps you organize and write.
ResearchThesis Topic & Intro v3.2
Read in 10 seconds: turn a vague observation into a defensible topic, then into an introduction that can pass review. Throughout, it uses only the real materials you provide — no fabricated references. Trigger words: thesis topic, topic selection, introduction, research gap, academic writing, thesis proposal, topic selection before literature review. Applies to: journal papers / dissertations / conference papers / course papers, across all disciplines — humanities and social sciences, STEM, agriculture, medicine, and life sciences. Up and running in 3 minutes: lock in your discipline and starting point → shape the topic layer by layer → strict evidence-chain gate → module-by-module introduction → ratchet finalization. [Division of labor with other skills] The health check comes first, writing comes after, and polishing comes last. This skill handles the middle stretch: topic shaping + introduction draft. It does not write the full paper (that's the Academic Paper Full-Process Writing System v4.x), and it does not polish language sentence by sentence (that's the Academic Paper Three-Track Polishing System v8.x). [Six gates] 1. Discipline placement: classify into one of four categories — 1A humanities/arts, 1B social sciences, 2A STEM, 2B agriculture/medicine/life sciences — and load the corresponding red-line norms; for category 2B, ethics review status is always checked. 2. Stage positioning: are you at a vague observation, have a unit but no angle, have an object but no theory, lack a method, lack a viewpoint, or only lack an introduction? Start from the corresponding gate instead of starting over from scratch. 3. Topic shaping: research unit → dimension compass → theoretical perspective → research method → research viewpoint, locked layer by layer; before locking each layer, first judge whether the previous layer holds. 4. Strict evidence-chain gate: before the introduction, your references are registered into an M1/M2… material library, each entry verified on four elements — author/year/title/locator; if fewer than 3 references are registered in the conversation, the system refuses to generate the research-gap statement — not a downgrade, a refusal. 5. Module-by-module generation: the introduction is produced in five inverted-pyramid modules, and each module must be annotated with citation numbers [Mn]; no source, no sentence. 6. Ratchet finalization: only versions that have passed receive credit; qualifying modules are locked and no longer changed; scores only go up, never down. [Deliverables] A '[Topic Keyword] · Topic & Introduction' document + a sentence-level traceable citation mapping table + a ⚠️ to-verify checklist + an AFP archive code. The archive code works across four systems — the proposal health-checker, the v4.x full-process system, and the three-track polishing system — so switching skills doesn't require re-stating your discipline, topic, journal, or material library. [Explicitly not done] It does not fabricate authors, years, volumes, issues, page numbers, or DOIs; any bibliographic records retrieved online are marked ⚠️ to-verify and can only be written into the reference list after you verify them; it makes no promises of acceptance or passing review. Authorship and responsibility are yours — please verify every citation and data point.
Paper Quick Note Generator
A 30-page paper due for tomorrow's group meeting; 40 papers to review for literature survey, each read from scratch, only to forget key points and lose that quotable line. Half of research time is spent on 'reading.' Paste an arXiv link or paper text and instantly receive a structured speed-reading note ready for use. ✨ Core Capabilities 1. Six-part speed-reading framework: Research Question / Core Method / Main Innovation / Key Conclusion / Limitations & Doubts / One-Sentence Summary 2. Automatically extracts 'quotable quotes' with location markers; copy directly for literature reviews. 3. Contribution breakdown: What's new compared to existing work, explained in plain language. 4. Critical perspective: Methodological flaws, overclaims, reproducibility risks pointed out point by point. 5. Optional outputs: Group meeting presentation outline / literature card / draft review paragraph / multi-paper comparison table. 6. Chinese-English terminology glossary, not machine-translated. 📱 Use Cases Graduate student thesis proposals and literature reviews, group meeting paper sharing, researchers tracking frontiers, tech professionals diving into technical papers; output can be posted on Zhihu or WeChat public accounts as academic content to attract readers. Make papers thinner—so you spend more time thinking than slogging through text.
Information
- Version
- v3
- Last updated
- Runtime credits
- Usage-based
- Models
- Auto
- Use cases
- Writing & contentResearch & analysisLearning & education
- What you get
- ReportDocumentData
