Project Review Assistant
Helps review projects
Description
A streamlined project review Skill. After receiving the application, abstract, or core materials, it first determines whether the project falls under 'goal-oriented basic research' or 'free-exploration basic research,' then generates formal review comments targeting only the three official review questions for that type. It emphasizes whether the scientific question is valid, whether the innovation points are concise, whether the logical chain is clear, and whether the research foundation and feasibility support the innovation. It strictly anchors to facts, does not fabricate, and must state if materials are insufficient.
Related Skills
View all
MOE Counselor Review v2.4.0
This Skill does not write your application for you; instead, it pre-screens the questions the review panel would ask: whether your identity is compliant, whether the project limit is violated, whether the research question withstands a one-sentence challenge, whether the research approach collapses by the second paragraph — each item turned into an actionable revision checklist. It incorporates the original text of the 2026 edition of 90 key research directions and 7 clusters of implicit weight tables, and is grounded in the risk map of previous years' special project reviews. Annual hard constraints such as document number, funding amount, research period, submission limit, etc., are verified by default against the current year's official notice — no hardcoding. ## What it does - Formal compliance hard check: identity as full-time counselor, submission limit, funding amount, research period, and other knockout gates (annual parameters based on the current year's official notice) - Sequential referencing diagnosis: for the 「(Reliant Direction N)」 at the end of the title, perform item-level compliance check — sequence validity + three-tier direction-title alignment (strong / moderate / weak) + cluster-level risk warning - Research question stress test: use 「So what?」 and 「What exactly is the difference from existing research?」 as two knives to pre-screen for the review panel - Research approach reverse deconstruction: mark paragraph by paragraph 「how this will be questioned」 rather than 「this is well written」 - Innovation authenticity diagnosis: which of 「first / systematic / breakthrough / fill a gap」 would be debunked by a literature search - Actionable revision checklist: prioritised next steps ## What it does not do - It does not choose your topic for you - It does not generate the application body - It does not 'polish' language - It does not tell you 'this topic is valuable' — no one on the review panel will compliment you like that ## How it differs from similar tools Other project review Skills on the platform assume you are applying for the National Social Science Fund or MOE general projects — the funding amounts, project limits, and identity requirements are all wrong. If you use them, your application will be revised against the wrong standards. This Skill is currently the only reverse review engine on the marketplace specifically for the 'MOE College Counselor Research Special Project', and it incorporates the original 2026 edition of 90 guidelines + 7 clusters of implicit weight tables; the 2025 edition is retained as a historical version, and cross-year applications can use 'sequential referencing diagnosis' for alignment. ## Who it is for - Full-time college counselors preparing to apply for the 2026/2027 MOE Counselor Research Special Project - Heads of student affairs departments (compliance gate before school-level preliminary review) - Applicants who have finished a draft and want the most critical eye to review it again ## Who it is not for - Those who want to generate an application with one click - Those applying for the National Social Science Fund or MOE general humanities and social science projects (please use the corresponding general Skill) - Those who haven't started writing yet — reverse review requires an object to review Version: v2.4.0 | Incorporated 2026 edition of 90 guidelines original text + 7 clusters classification + sequential referencing diagnosis | Annual hard constraint parameters subject to official notice ([Document Number Pending]) | Review engine has undergone multiple rounds of stress testing and retrospective upgrades
Grant Proposal Review PRO V2.0
🎯 Core Functionality Overview This is an intelligent review and optimization system specially designed for national social science, education ministry, and provincial grant applications. It simulates the thinking mode of a senior review expert with 15 years of experience, ensuring academic rigor and competitiveness through three core mechanisms. 🔧 Three Core Mechanisms 1️⃣ 12-Step Structured Methodology Covers the full lifecycle of grant proposal review: Phase 1-3: Basic Diagnosis - In-depth analysis of announcement (funding priorities, review criteria, application requirements) - Cross-disciplinary type judgment (precise identification of 8 types) - Research GAP five-dimension identification (theory/methodology/empirical/policy/technology) Phase 4-7: Core Element Review - Research question TMAQ model analysis (theory/methodology/approach/question four dimensions) - Research objective SMART principle test - Research content framework completeness assessment - Research approach type matching (6 types) Phase 8-10: Deep Quality Enhancement - Precise extraction of key difficulties (distinguish criteria + breakthrough paths) - Innovation point seven-dimension mining - Feasibility seven-dimension argumentation Phase 11-12: Overall Optimization - Nine-dimension quality check (academic rigor, innovativeness, feasibility, etc.) - Comprehensive optimization suggestions and final report 2️⃣ Dual-Core Adversarial Mechanism (Builder vs Supervisor) Working Principle: - Builder (academic writer): Generates optimization plans based on user materials - Supervisor (top journal reviewer): Challenges Builder's plans with the strictest standards - Adversarial iteration: 3 rounds of confrontation to ensure plans are robust Application Scenarios: - Innovation point mining: Builder proposes innovation points → Supervisor questions novelty → iterative optimization - Feasibility argumentation: Builder designs plan → Supervisor challenges feasibility → supplementary argumentation - Literature citation: Builder cites literature → Supervisor verifies authenticity → ensure academic standards 3️⃣ Literature Authenticity Verification Mechanism Two working modes: Mode A: Placeholder Mode (Default) - Use markers like [Literature Placeholder-001] in place of specific references - Output a Literature Requirement List specifying search requirements for each placeholder - User searches and fills in real references Mode B: Real-Time Verification Mode - Call Google Scholar to verify literature authenticity in real time - Generate Literature Verification Report (authenticity/relevance/authority scores) - Ensure every citation is traceable Preventing AI Hallucination: - Prohibits fabricating authors, journals, DOIs - All references must be verified or marked as placeholders - Guarantees academic integrity bottom line 💡 Core Value and Applicable Scenarios ✅ Key Pain Points Addressed 1. Academic sloppiness: AI-generated content often includes fake references, logical gaps 2. Insufficient innovation: Difficulty uncovering true academic innovation points 3. Weak feasibility: Research plans lack systematic argumentation 4. Cross-disciplinary difficulty: Interdisciplinary topics often fall between two stools 🎓 Target Users - University faculty (social sciences, education, humanities) - Researchers (applying for national and provincial grants) - Academic teams (needing systematic review processes) 📋 Typical Workflow 1. Input: Upload announcement + proposal draft 2. Review: System executes 12-step structured analysis 3. Adversarial: Dual-core mechanism iteratively optimizes key sections 4. Verification: Literature authenticity check 5. Output: Complete review report + optimization suggestions + literature list 🔍 Differences from Traditional Review | Dimension | Traditional Human Review | Expert Review System | |-----------|------------------------|----------------------| | Review depth | Depends on personal experience | 12-step structured + 9D QC | | Academic rigor | Hard to fully audit | Literature verification + dual-core adversarial | | Innovation mining | Subjective judgment | 7-dimension systematic analysis | | Feasibility argumentation | Experience-driven | 7-dimension item-by-item argumentation | | Consistency | Varies by individual | Standardized process | | Efficiency | Days to weeks | 1-2 hours for initial review | The core advantage of this system is: it makes the tacit knowledge of a 15-year senior review expert explicit, structured, and replicable, enabling every user to receive top-level expert review services.
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.
Project Review Assistant
Helps review projects
Description
A streamlined project review Skill. After receiving the application, abstract, or core materials, it first determines whether the project falls under 'goal-oriented basic research' or 'free-exploration basic research,' then generates formal review comments targeting only the three official review questions for that type. It emphasizes whether the scientific question is valid, whether the innovation points are concise, whether the logical chain is clear, and whether the research foundation and feasibility support the innovation. It strictly anchors to facts, does not fabricate, and must state if materials are insufficient.
Related Skills
View allMOE Counselor Review v2.4.0
This Skill does not write your application for you; instead, it pre-screens the questions the review panel would ask: whether your identity is compliant, whether the project limit is violated, whether the research question withstands a one-sentence challenge, whether the research approach collapses by the second paragraph — each item turned into an actionable revision checklist. It incorporates the original text of the 2026 edition of 90 key research directions and 7 clusters of implicit weight tables, and is grounded in the risk map of previous years' special project reviews. Annual hard constraints such as document number, funding amount, research period, submission limit, etc., are verified by default against the current year's official notice — no hardcoding. ## What it does - Formal compliance hard check: identity as full-time counselor, submission limit, funding amount, research period, and other knockout gates (annual parameters based on the current year's official notice) - Sequential referencing diagnosis: for the 「(Reliant Direction N)」 at the end of the title, perform item-level compliance check — sequence validity + three-tier direction-title alignment (strong / moderate / weak) + cluster-level risk warning - Research question stress test: use 「So what?」 and 「What exactly is the difference from existing research?」 as two knives to pre-screen for the review panel - Research approach reverse deconstruction: mark paragraph by paragraph 「how this will be questioned」 rather than 「this is well written」 - Innovation authenticity diagnosis: which of 「first / systematic / breakthrough / fill a gap」 would be debunked by a literature search - Actionable revision checklist: prioritised next steps ## What it does not do - It does not choose your topic for you - It does not generate the application body - It does not 'polish' language - It does not tell you 'this topic is valuable' — no one on the review panel will compliment you like that ## How it differs from similar tools Other project review Skills on the platform assume you are applying for the National Social Science Fund or MOE general projects — the funding amounts, project limits, and identity requirements are all wrong. If you use them, your application will be revised against the wrong standards. This Skill is currently the only reverse review engine on the marketplace specifically for the 'MOE College Counselor Research Special Project', and it incorporates the original 2026 edition of 90 guidelines + 7 clusters of implicit weight tables; the 2025 edition is retained as a historical version, and cross-year applications can use 'sequential referencing diagnosis' for alignment. ## Who it is for - Full-time college counselors preparing to apply for the 2026/2027 MOE Counselor Research Special Project - Heads of student affairs departments (compliance gate before school-level preliminary review) - Applicants who have finished a draft and want the most critical eye to review it again ## Who it is not for - Those who want to generate an application with one click - Those applying for the National Social Science Fund or MOE general humanities and social science projects (please use the corresponding general Skill) - Those who haven't started writing yet — reverse review requires an object to review Version: v2.4.0 | Incorporated 2026 edition of 90 guidelines original text + 7 clusters classification + sequential referencing diagnosis | Annual hard constraint parameters subject to official notice ([Document Number Pending]) | Review engine has undergone multiple rounds of stress testing and retrospective upgrades
Grant Proposal Review PRO V2.0
🎯 Core Functionality Overview This is an intelligent review and optimization system specially designed for national social science, education ministry, and provincial grant applications. It simulates the thinking mode of a senior review expert with 15 years of experience, ensuring academic rigor and competitiveness through three core mechanisms. 🔧 Three Core Mechanisms 1️⃣ 12-Step Structured Methodology Covers the full lifecycle of grant proposal review: Phase 1-3: Basic Diagnosis - In-depth analysis of announcement (funding priorities, review criteria, application requirements) - Cross-disciplinary type judgment (precise identification of 8 types) - Research GAP five-dimension identification (theory/methodology/empirical/policy/technology) Phase 4-7: Core Element Review - Research question TMAQ model analysis (theory/methodology/approach/question four dimensions) - Research objective SMART principle test - Research content framework completeness assessment - Research approach type matching (6 types) Phase 8-10: Deep Quality Enhancement - Precise extraction of key difficulties (distinguish criteria + breakthrough paths) - Innovation point seven-dimension mining - Feasibility seven-dimension argumentation Phase 11-12: Overall Optimization - Nine-dimension quality check (academic rigor, innovativeness, feasibility, etc.) - Comprehensive optimization suggestions and final report 2️⃣ Dual-Core Adversarial Mechanism (Builder vs Supervisor) Working Principle: - Builder (academic writer): Generates optimization plans based on user materials - Supervisor (top journal reviewer): Challenges Builder's plans with the strictest standards - Adversarial iteration: 3 rounds of confrontation to ensure plans are robust Application Scenarios: - Innovation point mining: Builder proposes innovation points → Supervisor questions novelty → iterative optimization - Feasibility argumentation: Builder designs plan → Supervisor challenges feasibility → supplementary argumentation - Literature citation: Builder cites literature → Supervisor verifies authenticity → ensure academic standards 3️⃣ Literature Authenticity Verification Mechanism Two working modes: Mode A: Placeholder Mode (Default) - Use markers like [Literature Placeholder-001] in place of specific references - Output a Literature Requirement List specifying search requirements for each placeholder - User searches and fills in real references Mode B: Real-Time Verification Mode - Call Google Scholar to verify literature authenticity in real time - Generate Literature Verification Report (authenticity/relevance/authority scores) - Ensure every citation is traceable Preventing AI Hallucination: - Prohibits fabricating authors, journals, DOIs - All references must be verified or marked as placeholders - Guarantees academic integrity bottom line 💡 Core Value and Applicable Scenarios ✅ Key Pain Points Addressed 1. Academic sloppiness: AI-generated content often includes fake references, logical gaps 2. Insufficient innovation: Difficulty uncovering true academic innovation points 3. Weak feasibility: Research plans lack systematic argumentation 4. Cross-disciplinary difficulty: Interdisciplinary topics often fall between two stools 🎓 Target Users - University faculty (social sciences, education, humanities) - Researchers (applying for national and provincial grants) - Academic teams (needing systematic review processes) 📋 Typical Workflow 1. Input: Upload announcement + proposal draft 2. Review: System executes 12-step structured analysis 3. Adversarial: Dual-core mechanism iteratively optimizes key sections 4. Verification: Literature authenticity check 5. Output: Complete review report + optimization suggestions + literature list 🔍 Differences from Traditional Review | Dimension | Traditional Human Review | Expert Review System | |-----------|------------------------|----------------------| | Review depth | Depends on personal experience | 12-step structured + 9D QC | | Academic rigor | Hard to fully audit | Literature verification + dual-core adversarial | | Innovation mining | Subjective judgment | 7-dimension systematic analysis | | Feasibility argumentation | Experience-driven | 7-dimension item-by-item argumentation | | Consistency | Varies by individual | Standardized process | | Efficiency | Days to weeks | 1-2 hours for initial review | The core advantage of this system is: it makes the tacit knowledge of a 15-year senior review expert explicit, structured, and replicable, enabling every user to receive top-level expert review services.
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.
Find your next favorite skill
Explore more curated AI skills for research, creation, and everyday work.