YU QIAN
Paper Imitation & Pub. Expert
📚 Paper Imitation & Pub. Expert Develop an inspiring paper into your own high-quality original work step by step. Ideal for graduate students seeking to draw inspiration from excellent papers in other disciplines for topic migration, structural reconstruction, and submission optimization. 🔍 Inspiring Literature Identification: Analyze the reusable title mechanisms, problem awareness, chapter structure, theoretical framework, research methods, evidence organization, and language style of the model paper. 🔄 Interdisciplinary Paradigm Transfer: Build a 'source domain—target domain' transfer matrix to determine which ideas can be transferred and which theories, concepts, cases, and conclusions must be reconstructed. 🧠 Original Contribution Modeling: Identify literature gaps, distill core propositions and mechanisms, and check whether the paper merely changes the research object or applies a generic framework. 🧭 Research Design Planning: Supports theoretical research, case studies, qualitative research, quantitative research, literature reviews, policy text analysis, and mixed methods research. 🛡️ Real Evidence Gate: Do not fabricate data, samples, interviews, cases, statistical results, literature, or DOIs; without real evidence, do not generate false empirical conclusions. ✍️ Evidence-Driven Writing: Build argument chains via 'proposition—evidence—citation—rebuttal', generate original content chapter by chapter, and clearly mark research materials that need to be supplemented. 📈 Continuous Paper Evolution: Record each round of revisions, material gaps, and maturity changes according to L1 (topic conception), L2 (research plan), L3 (evidence formation), L4 (submission draft), and L5 (ready for submission). 🧑⚖️ Triple Simulation Review: Identify rejection risks from the perspectives of a theoretical reviewer, a method reviewer, and a target journal reviewer, and form specific revision strategies. 📨 Complete Submission Loop: Assist in generating the final paper, citation verification table, cover letter, innovation point statement, author response, revision index, and related declaration templates. ✨ Learn the paradigm, write original content, and enhance real submission competitiveness.
Inspiration Visualization
Quickly turn an idea into a high-fidelity, testable visual draft, which can be further developed into an academic research model with evidence auditing, construct validation, and method matching, along with a structured formal diagram.
AFP Prompt Engineering OS
AFP Prompt Engineering OS Forge your ideas, materials, experience flows, reference prompts, or SOPs into a runnable, auditable, testable, publishable, and iterable AI Skill. This is not an ordinary prompt generator. It is a prompt engineering architect, Skill product manager, and quality auditor built into the conversation. Just give it a task, a piece of material, a workflow, or even a vague idea, and it will automatically help you complete: 🔍 Identify task type, determine material path 🧱 Break down workflows, extract stages, actions, and decision points 🧠 Build Constants, Variables, and If-Then decision trees 🛠️ Assemble into AFP structured system prompts 🛡️ Execute quality gates, stress tests, and version releases 🔁 Supports subsequent compression, upgrades, and adaptation for GPT, Gem, and Skill From now on, prompts are no longer just 'writing a good sentence,' but an AI work system that is engineered, designed, tested, released, and iterated.
Pre-submission Quality Check v2.0
Comprehensive pre-submission quality check system for journal papers. Features a six-dimensional parallel review (structure, logic, methods, language, citations, journal alignment) plus four enhanced modules: journal profile analysis, AIGC risk recheck, abstract smart rewrite, and desk-reject risk radar. Simulates a senior reviewer's perspective, outputting a structured issue list, severity grading, submission readiness score, and desk-reject probability estimate.
Layer-by-Layer Prompt Workshop
Transforms vague requirements into well-structured, logically coherent high-quality prompts. Built on the 'Constants + Variables + Algorithms' model and the 'Onion Peeling' method, it supports 6 arrangement schemes, 4 output formats, automatic decision matrix matching, and features an iterative verification closed-loop and anti-pattern warnings.
Evidence-Based Self-Help Coach
A self-help support system v3.2 for anxiety, compulsive worry, repeated checking, stress, sleep difficulties, low mood, and more. It includes three working modes (emotional companionship, specific strategies, exercise guidance), 14 classic psychological self-assessment scales (with first-time use guidance), compulsive cycle interruption, risk triage, and medical preparation functions. Scale assessments are for self-understanding only and do not constitute a professional diagnosis.
NSFC Proposal Coach (Flagship)
Senior NSFC proposal overall editing coach + Interceptive reviewer + Systems science philosophy advisor. Integrates all features of NSFC Proposal Writing Coach [Ultimate Edition] and [Enhanced Edition], using AFP v1.0 multi-core adversarial engine architecture (A-execution + B-audit + E-evolution), covering Youth, General, and Regional categories. 🎯 Three knowledge foundations: Wang Laigui's systems science philosophy + Xu Changqing's Proposal Song 22 Rules + Huang Zhonglian's 250 Questions Error Detection Rules 32 Selected, aligned with 2026 NSFC latest policies. 🔧 Ten-stage full pipeline: S1 Define Topic → S2 Project Rationale → S3 Scientific Question Refinement → S4 Research Content → S5 Plan/Technical Route/Innovation/Annual → S6 Research Basis and Feasibility → S7 Compliance Self-check → S8 Abstract Final Review → S9 Global Quality Inspection Export → S10 Review Simulation Defense. Each stage delivers a three-piece set: 'readable draft + structured PACK + self-check conclusion', strictly step-lock progressive. 🚀 Enhanced startup process: Text version skill introduction on first screen (no webpage generated) + Web version 7-field startup questionnaire (generateWebpage) + Three-entry routing (existing topic / vague idea / revise and resubmit) + Material grading mechanism. 🛡️ Six review-level guardrails: Literature triple-state annotation | Anti-drift triangle eight-element engagement | High-risk wording interception (12 minefields) | Compliance five-item self-check | Ethical writing three levels | Single module refinement. 🔬 Multi-core adversarial engine: A-core execution + B-core six-dimensional independent audit (logical consistency, wording compliance, quantity compliance, evidence authenticity, format standardization, anti-drift verification) + E-core evolutionary learning. ⚡ 16 interactive commands: /pick /redo /export /triangle /chain /lint /only /four-types /classify /lint-250 /song-check /hypothesis /review-sim /risk-map /diff /ai-declare. 📋 Category tier hard constraints: Youth Fund 1-2 KSQ/3-4 content blocks/2-3 innovation points, General Program 2-3 KSQ/3-5 content blocks/3 innovation points, Regional Fund follows Youth. 🎓 Applicable users: NSFC applicants aiming to write a submission-ready proposal that withstands reviewer scrutiny sentence by sentence (covering Youth/General/Regional categories).
Meta-AFP Prompt Architect
An engineered meta-prompt generation system v3.0 based on the AFP (Auto-Flow Prompt) methodology. Transforms vague needs into runnable, reusable, iterative, and assetable system-level prompts—running like an operating system, thinking like an expert team, and as stable as military-grade products. Integrates a complete methodology including five generations of prompt evolution, three dimensions of content alchemy, six orchestration algorithms, dual-core/multi-core confrontation, hard rules for independence constraints, five audit principles, regression/stress testing, a security moat (separator isolation, sandwich defense, meta-instruction declaration, black-box encapsulation), a prompt evolution officer self-evolution mechanism, and the AFP asset valuation model (Expertise × Structure × Frequency). Suitable for creating high-value Skills in fields such as academic writing, legal audit, business analysis, content production, sales copywriting, knowledge management, and intelligent agents.
WriteAIGC Reduction & Rewrite v7.0
📚 Academic Paper AIGC Reduction and Quality-Preserving Rewriting Expert v7.0 Designed for graduate students, researchers, and paper authors, this academic text optimization skill operates on a core closed loop of 'source control → process correction → result verification → reverse self-check → iterative re-check'. It systematically diagnoses and optimizes issues such as templated expressions, mechanical logic, vague content, inaccurate terminology, and style inconsistencies while preserving original meaning, technical terms, data, and core conclusions. 🔍📝 🌟 Core Capabilities 🔬 Multi-layer Risk Diagnosis Covers 10 types of universal text fingerprints and assists in identifying common expression patterns of models such as ChatGPT, Claude, DeepSeek, and Wenxin Yiyan. 🧠 Deep Semantic Restructuring Goes beyond synonym replacement to rebuild more natural and in-depth academic reasoning by adjusting proposition expression, information order, argument approach, and evidence organization. ✍️ Quality-Preserving Rewriting Comprehensively applies 13 sentence transformation strategies and 20 methods for cleaning high-frequency templated expressions, improving mechanical sentence structures, repetitive connectors, and overly rigid formatting. 📊 Full-text Structure Diagnosis Through macro-cycle and five key triangles, checks whether research problems, theory, literature review, methods, results, conclusions, and innovation form a complete closed loop. 🧩 Fine-grained Section Adaptation Develops differentiated diagnostic and rewriting strategies for abstract, introduction, literature review, research methods, results, discussion, and conclusion respectively. 🌐 Cross-language Risk Scanning Assists in identifying translationese, passive voice stacking, long sentence nesting, and mixed Chinese-English formatting abnormalities to make Chinese academic expression more natural and accurate. 🔄 Reverse Self-check Loop After rewriting, re-verifies from three aspects: technique distribution, new text fingerprints, and information integrity, to avoid 'becoming more templated' or losing key content. 🛡️ Academic Integrity Protection Does not fabricate literature, data, cases, or policy evidence; separately marks information requiring author verification and reminds users to honestly disclose AI usage. 🎯 Use Cases ✅ Single paragraph or partial section optimization ✅ Targeted modification of marked paragraphs from inspection reports ✅ Polishing of abstract, introduction, literature review, discussion, and conclusion ✅ Full-text AIGC risk feature diagnosis ✅ Language and structure adaptation for target journals ✅ Pre-submission quality review and consistency check 📦 Final Deliverables 📄 Quality-preserving rewritten text 🔎 Risk and issue diagnosis report 🛠️ Rewriting strategy and technique description ✅ Reverse self-check and information integrity report 💡 Items requiring author verification and subsequent revision suggestions 🎓 Original meaning preserved · Logic intact · No fabricated data · Academic quality maintained ⚠️ This skill aims to improve academic expression quality and reduce text risk features. It does not guarantee passage through any specific detection platform or achieving a particular detection score.
NSFC Question Refiner
A deep tool focused on refining 'scientific questions' for NSFC projects. Starting from the researcher's topic, proposal rationale, or vague ideas, it applies the three-step refinement method (Gap → Tension → Question Sentence), the five-component structure for scientific questions, NSFC's four-category classification of scientific questions, anti-drift triangle verification, and pseudo-question blocking mechanisms to systematically distill research intentions into a group of scientific questions that meet NSFC review standards. It supports various project types including General Projects (3-4 scientific questions), Young Scientists Fund (2-3 scientific questions), Key Projects, and others, covering all disciplines such as management science, medicine, psychology, engineering, and information science. Output includes a structured refinement report with the complete five components, logical linkage diagram, KSQ-Gap Mapping Table, and review risk prediction.
NSFC Topic Inspiration Creator
A creative generation tool specialized for topic selection and title formulation in National Natural Science Foundation of China (NSFC) projects. Based on the 'dual-core tension' structural analysis method, a five-dimensional evaluation system, and a four-dimensional scoring matrix, it helps researchers systematically generate project title proposals with academic tension, high review-friendliness, and outstanding innovation, starting from vague research interests. Supports various project types including general programs, youth programs, key programs, and more, covering multiple disciplines.
NSFC Writing Coach Enhanced
Derived from multiple NSFC application guide books, several successfully funded proposals, and hands-on writing experience from five General Projects, this full-process interactive coach embodies the dual roles of 'Senior Chief Editor' and 'Intercepting Reviewer.' It integrates Wang Laigui's System Philosophy, Xu Changqing's 22 Proposal Song Verses, Huang Zhonglian's 250-Question Error-Checking Rules, and the latest 2026 NSFC policies. 🎯 Core Positioning: Like a senior reviewer by your side, polishing your proposal from topic selection to submission, sentence by sentence. 🔧 Three Core Mechanisms ① Ten-stage full-link engine (S1 Topic Selection → S2 Project Rationale → S3 Scientific Question Refinement → S4 Research Content → S5 Plan/Technical Route/Innovation → S6 Research Foundation → S7 Compliance Self-Check → S8 Abstract Final Review → S9 Global Quality Inspection & Export → S10 Reviewer Simulation Defense), each stage delivers a 'readable draft + structured PACK + self-check conclusion' combo, strictly step-lock progression. ② Six reviewer-level guardrails: 🔍 Three-state literature annotation (Verified/Unverified/Placeholder only, never fabricated) ｜ 🧭 Anti-drift triangle interlocking (Title ↔ Gap ↔ KSQ ↔ Objective ↔ Content ↔ Method ↔ Innovation ↔ Foundation chain lock) ｜ 🚫 High-risk wording interception (automatically rewrite landmines like 'first-ever' or 'fill the gap') ｜ ✅ Five compliance self-checks ｜ ⚖️ Ethical writing tiering ｜ 🎯 Single-module refinement. ③ Multi-core confrontation engine: A Core execution + B Core audit + E Core evolution, three cores run independently to ensure each stage's output undergoes independent audit. 💡 Differentiated Advantages · Not a template filler — it's a coach that stops you, questions you, and pushes you to revise thoroughly. · No fabricated literature — three-state literature management, unverified never enters the official version. · No topic drift — anti-drift triangle + full-chain interlocking to prevent disconnect. · No one-size-fits-all — automatic tiering by Young Scientists Fund/General Program/Regional Fund for precise adaptation. · Three major rule libraries: Wang Laigui's System Philosophy + Xu Changqing's 22 Proposal Song Verses + Huang Zhonglian's 250-Question Error-Checking Rules. · 2026 policy alignment: Four types of scientific question attribute declarations + AI usage compliance statement. 🎓 Applicable users: NSFC applicants (covering Young Scientists Fund, General Program, and Regional Fund) who aim to write a submission-ready proposal that withstands reviewer scrutiny sentence by sentence. 📋 Two entry points: 'Have a preliminary topic' — start polishing directly ｜ 'Only a vague idea' — provide keywords and get 5 candidate topics laid out.
ResearchNSFC App Writing Coach (Trial)
A lightweight step-by-step coach derived from multiple NSFC application guidebooks, analysis of successful funded proposals, and real writing experience from five NSFC General Projects. It begins with a checkable web questionnaire to quickly collect application category, discipline, and initial idea. Then it proceeds through a six-step main chain with step-lock: Define Title → Project Rationale → Research Objectives and Key Scientific Questions → Research Content → Innovation in Approach → Basic Compliance & Abstract Wrap-up. This ensures no skipping steps, no fabricated references or data, no unsubstantiated claims of innovation, and full chain linkage to prevent disjointedness. Designed for first-time applicants or those who want to quickly navigate the NSFC main chain—low barrier to entry, producing a solid draft that can be submitted.
ResearchPublication Strategist v3.0
An advanced submission strategy system designed for core journals and SCI/SSCI. Building on the J-AFP five-dimensional quantitative diagnosis and paragraph-level refinement from v2.0, it adds a journal selection strategy matrix (with three tiers: stretch, target, and safe journals, plus a gradient submission route), introduces a three-core engine (Critic the reviewer butcher, Mentor the polishing artisan, and Editor the editor's eye) along with a citation-method chain evidence audit (citation verification, literature gap identification, and discipline-specific method deep review), and extends to full-cycle peer review pre-play (multi-persona reviewer attack-defense simulation and point-by-point Response Letter) and a bilingual publishable version. It covers the complete publication closed loop of 'journal selection—diagnosis—audit—restructuring—pre-play—delivery'.
Journal Submission Refinement Architect v2.0 (Advanced Version)
A dynamic, adaptable review, restructuring, and step-by-step revision system for any target academic journal. It accurately diagnoses manuscript publication suitability using a J-AFP five-dimensional quantitative scoring system (intent alignment, theoretical contribution, methodological standardization, result conversion, and format compliance). Employing a dual-core engine (Critic + Mentor) model, it helps authors bridge the gap between "self-indulgent writing" and "standardized works conforming to review logic." It supports a fully engineered workflow, from journal profiling and title reshaping to logical pressure application, table of contents finalization, and step-by-step revision.
ResearchJournal Review Dual-Core
The Uni-AFP Scholar Architect is a highly engineered academic writing assistant system designed to bridge the gap between self-indulgent writing and the review logic of top-tier journals. At its core is a dynamic Journal-AFP (J-AFP) assessment, with two collaborative engines: Critic, which simulates rigorous peer review to precisely identify pseudo-issues, logical gaps, and methodological flaws, applying dimensional reduction logical pressure and rejection risk interception; and Mentor, acting as a seasoned editor, responsible for table of contents restructuring, de-AI-ed academic context refinement, and paragraph-level control. Driven by this dual-core synergy, the system deeply repairs structural weaknesses in manuscripts, providing a solid theoretical foundation and rigorous deductive logic, helping authors overcome the academic publication gap and efficiently produce standardized high-quality works that align with target journal preferences.
Academic Writing Engineering
An engineering collaborative agent for scholarly manuscript writing across disciplines, covering monographs, textbooks, chapters, institutional texts, management manuals, practical guides, and academic practice texts in natural sciences, engineering, humanities and social sciences, business, law, education, medicine, and more. It does not directly write the main text but follows a seven-stage engineering workflow: task scope diversion → outline lock-in → resource compilation → logical review → section-by-section writing → section-by-section confirmation → full-chapter consolidation. This ensures stable chapter structure, sufficient supporting references, consistent terminology, and precise, plain language, delivering robust manuscripts suitable for formal publication and core journal style. Core capabilities: • Four task scope types: full book / single chapter / outline only / special tasks (consolidation, de-AI rewriting, review response, etc.) • Three approaches for top-level outline: user-provided, system-designed, or editorial board style lock-in • Three differentiated options for second/third-level outlines (normative basic / logic-enhanced / practice-applied) plus a compound recommendation mechanism • LAF-7 seven-dimensional logical review (system completeness, hierarchy symmetry, sentence standardization, title conciseness, cross-chapter repetition rate, terminology standardization, publishing suitability) • Word count weight and title density matching to prevent fragmentation from overly dense third-level headings • Reference compilation and online verification (policies, standards, regulations, literature, cases, data) • Gated manuscript writing (refuses to write if any gate condition is not met) • Section-by-section writing, section-by-section confirmation, full-chapter consolidation and final review • Expert-level de-AI rewriting: diagnosis (generic words, sentence regularity, mechanical connectors, concept stacking, missing context, terminology drift) + rewriting (alternating long/short sentences, qualifiers, reduce template numbering, strengthen causal chains and logical closure) Discipline adaptation: Automatically switches to the corresponding discipline's language style based on the user's academic background and terminology system (e.g., STEM focuses on mechanisms and experiments, business on strategy and cases, law on statutes and precedents, education on theory and classrooms, medicine on evidence-based practice and procedures, etc.) without imposing a fixed disciplinary framework. Target audience: Authors of academic monographs, textbook editors, series editorial committee members, industry practitioners, graduate and doctoral supervisors, researchers and professionals undertaking the writing of management manuals, institutional compilations, and practical guides.