Skip to content

brycewang-stanford/Auto-Empirical-Research-Skills / skills/01-lishix520-academic-paper-skills/strategist

academic-paper-strategist

Unverified

Systematic strategic planning framework for philosophy and interdisciplinary academic papers targeting preprint platforms (PhilArchive, arXiv, PhilSci-Archive). Use when users want to: (1) plan a paper on a specific topic, (2) identify research gaps and assess originality, (3) develop optimized paper outlines, (4) prepare for preprint submission, or (5) understand platform requirements and writing standards. Triggered by phrases like 'plan a paper on,' 'help me design a paper about,' 'identify research gaps in,' 'is this idea original,' or when users need structured research planning. The skill guides through three phases: Platform Analysis (identifying target venue and studying sample papers), Theoretical Framework (AI-driven literature search and gap identification), and Outline Optimization (structured design with reviewer-perspective self-assessment). Each phase includes quality evaluation standards and validation checkpoints. Output: optimized detailed outline ready for systematic writing (use with academic-paper-composer skill).

FileKindSize
SKILL.mdskill md22.3 KB
references/quality_standards.mdmarkdown10.2 KB
references/search_strategy.mdmarkdown14.0 KB

references/quality_standards.md

View on GitHub
<!--
  ╔══════════════════════════════════════════════════════════════╗
  ║  本文件为开源 Skill 原始文档,收录仅供学习与研究参考        ║
  ║  CoPaper.AI 收集整理 | https://copaper.ai                  ║
  ╚══════════════════════════════════════════════════════════════╝

  来源仓库: https://github.com/lishix520/academic-paper-skills
  项目名称: academic-paper-skills
  开源协议: MIT License
  收录日期: 2026-04-02

  声明: 本文件版权归原作者所有。此处收录旨在为社会科学实证研究者
  提供 AI Agent Skills 的集中参考。如有侵权,请联系删除。
-->

# Quality Standards for Academic Paper Strategy

This document defines the quality evaluation criteria used throughout the strategic planning phase.

## Phase 1: Platform Analysis Quality Standards

### 1.1 Sample Paper Selection Quality

**Time Distribution**:
- ✓ Recent (last 6 months): 3 papers - captures current trends
- ✓ Current (1-2 years): 3 papers - represents accepted standards
- ✓ Classic (highly cited): 2 papers - establishes benchmarks
- **Minimum**: 8 papers total

**Relevance Scoring** (0-10 scale):
- 9-10: Directly addresses user's topic with same methodology
- 7-8: Related topic or similar approach
- 5-6: Adjacent field or partial overlap
- <5: Insufficient relevance, exclude
- **Target**: Average relevance ≥ 8.0

**Diversity Checks**:
- ✓ At least 5 different authors
- ✓ At least 3 different research perspectives/schools
- ✓ Varied paper lengths (short/medium/long form)
- ✓ Different subfields if applicable

**Quality Indicators**:
- ✓ Has DOI or permanent identifier
- ✓ Complete abstract available
- ✓ Proper citation format
- ✓ Published on target platform

**Sample Evaluation Report Template**:
```markdown
| # | Title | Authors | Date | Relevance | Selection Reason |
|---|-------|---------|------|-----------|------------------|
| 1 | ... | ... | YYYY-MM | 9/10 | Direct methodological match |
| 2 | ... | ... | YYYY-MM | 8/10 | Similar theoretical framework |
...
```

### 1.2 Platform Matching Quality

**Platform Relevance Score** (0-10):
- Subject area alignment
- Methodology fit (philosophical/empirical/computational)
- Format compatibility
- Historical acceptance rate

**Minimum**: 7/10 for recommended platform

---

## Phase 2: Literature Review Quality Standards

### 2.1 Literature Search Comprehensiveness

**Coverage Metrics**:
- **Minimum**: 20 core papers
- **Recommended**: 30-50 papers
- **Time span**: Last 5 years + foundational classics
- **Source diversity**: At least 3 major journals/venues

**Keyword Coverage**:
- ✓ All core concepts covered (3-5 concepts)
- ✓ Related terms and synonyms searched
- ✓ Adjacent fields explored
- **Evaluation**: Each concept should yield 5-10 relevant papers

**Search Quality Checklist**:
```markdown
Round 1: Direct Search
- ✓ 10-15 keyword combinations used
- ✓ 30-50 papers collected
- ✓ Top 20 papers retained after relevance filter

Round 2: Expanded Search
- ✓ New keywords extracted from Round 1 papers
- ✓ Adjacent fields searched
- ✓ 10-20 additional papers collected

Round 3: Classic Literature
- ✓ High-citation papers identified (>100 citations)
- ✓ Foundational works included
- ✓ 5-10 seminal papers added
```

### 2.2 Research Gap Identification Quality

**Gap Definition Quality** (each gap must have):
1. **Specificity**: Clearly defined boundaries
2. **Evidence**: 3-5 citations showing gap exists
3. **Feasibility**: Reasonable for user to address
4. **Significance**: Addresses important question

**Gap Types** (identify 3-5 total):
- **Complete gaps**: Entirely unresearched area
- **Partial gaps**: Understudied or preliminary work only
- **Controversy gaps**: Unresolved debates

**Quality Check**:
```markdown
For each gap, verify:
- ✓ No existing paper directly addresses this (evidence-based)
- ✓ Related work acknowledges this as limitation
- ✓ Gap aligns with user's research direction
- ✓ Filling gap would constitute original contribution
```

### 2.3 Originality Assessment Quality

**Similarity Analysis Requirements**:
- **Minimum**: Compare with 15 related papers
- **Recommended**: Compare with 20-30 papers
- **Method**: Identify conceptual/methodological overlaps

**Similarity Categories**:
- High (>80%): Requires repositioning or abandonment
- Medium (50-80%): Emphasize differences, may proceed
- Low (<50%): Good originality, proceed

**Innovation Identification**:
Must identify at least 2 of:
- Methodological innovation (new approach)
- Theoretical innovation (new framework)
- Application innovation (new problem domain)
- Integrative innovation (novel synthesis)

**Impact Prediction Criteria** (1-10 scale):
- Gap importance (5 points): Core vs peripheral problem
- Generalizability (3 points): Applicable beyond narrow case
- Explanatory power (2 points): Resolves existing puzzles

**Quality**: Must provide 300-word justification for impact score

---

## Phase 3: Outline Optimization Quality Standards

### 3.1 Structure Quality

**Chapter Proportion Standards** (for philosophy papers):
- Introduction: 15-20% of total
- Main body: 60-70% of total
- Conclusion: 10-15% of total

**Logical Flow Checklist**:
- ✓ Each chapter builds on previous
- ✓ Clear transitions between sections
- ✓ No orphaned arguments
- ✓ Conclusion addresses introduction promises

**Platform Conformity**:
- Structural similarity to sample papers: ≥70%
- Section naming consistent with platform norms
- Word count aligned with platform standards

### 3.2 Reviewer Evaluation Standards

**7-Dimension Assessment** (5 points each, 35 total):

1. **Argument Clarity** (1-5)
   - 5: Crystal clear thesis + supporting arguments
   - 4: Clear thesis, minor ambiguities
   - 3: Thesis identifiable but needs sharpening
   - 2: Thesis unclear or scattered
   - 1: No clear thesis

2. **Argument Completeness** (1-5)
   - 5: All steps justified, no logical gaps
   - 4: Minor gaps that can be filled
   - 3: Notable gaps requiring attention
   - 2: Major logical jumps
   - 1: Argument structure incomplete

3. **Literature Support** (1-5)
   - 5: 50+ citations, all key works covered
   - 4: 40-50 citations, most key works
   - 3: 30-40 citations, some gaps
   - 2: 20-30 citations, major gaps
   - 1: <20 citations, insufficient

4. **Methodological Clarity** (1-5)
   - 5: Method explicit, well-justified
   - 4: Method clear, minor justification issues
   - 3: Method stated but not defended
   - 2: Method unclear
   - 1: No methodological clarity

5. **Originality Expression** (1-5)
   - 5: Contribution crystal clear + well-contrasted
   - 4: Contribution clear, minor positioning issues
   - 3: Contribution stated but not differentiated
   - 2: Contribution unclear
   - 1: No clear contribution

6. **Organization** (1-5)
   - 5: Perfect flow, optimal proportions
   - 4: Good flow, minor proportion issues
   - 3: Acceptable flow, some reorganization needed
   - 2: Disjointed, needs restructuring
   - 1: Chaotic structure

7. **Platform Fit** (1-5)
   - 5: Perfect match to platform style
   - 4: Good match, minor adjustments needed
   - 3: Acceptable, needs adaptation
   - 2: Poor fit, major revision required
   - 1: Wrong platform

**Passing Threshold**: ≥28/35 (80%)

**Quality Gate**: Must identify at least 3 issues with concrete improvement suggestions

---

## Quality Gates (Checkpoints)

### Gate 1: Platform Analysis Complete
**Requirements**:
- ✓ Sample papers ≥8
- ✓ Time distribution balanced (recent/current/classic)
- ✓ Average relevance ≥8/10
- ✓ Diversity checks passed
- ✓ Writing guidelines extracted

**Action if Failed**: Re-search with adjusted criteria

---

### Gate 2: Literature Review Complete
**Requirements**:
- ✓ Core papers ≥20
- ✓ Keywords coverage complete (all core concepts)
- ✓ Research gaps ≥3, each with evidence
- ✓ Originality score ≥7/10
- ✓ Impact justification provided

**Action if Failed**: Continue search or pivot research direction

---

### Gate 3: Outline Optimized
**Requirements**:
- ✓ Reviewer score ≥28/35 (80%)
- ✓ All high-severity issues resolved
- ✓ Structure proportions balanced
- ✓ Platform conformity ≥70%

**Action if Failed**: Redesign outline addressing identified issues

---

## Evaluation Report Templates

### Sample Paper Evaluation Report
```markdown
# Sample Paper Analysis Report

## Executive Summary
- Papers analyzed: [N]
- Average relevance: [X/10]
- Time distribution: [breakdown]
- Quality: [Pass/Fail]

## Detailed Breakdown
[Table with all papers]

## Writing Style Patterns
[Extracted guidelines]

## Recommendation
[Proceed/Re-search/Adjust criteria]
```

### Literature Gap Analysis Report
```markdown
# Research Gap Identification Report

## Literature Coverage
- Papers reviewed: [N]
- Timespan: [range]
- Core concepts covered: [list]

## Identified Gaps
### Gap 1: [Title]
- Type: [Complete/Partial/Controversy]
- Evidence: [3-5 citations]
- Significance: [High/Medium/Low]
- Feasibility: [Assessment]

[Repeat for each gap]

## Originality Assessment
- Similarity analysis: [High/Medium/Low]
- Innovation types: [list]
- Impact prediction: [X/10]
- Justification: [300 words]

## Recommendation
[Proceed/Pivot/Reposition]
```

### Reviewer Evaluation Report
```markdown
# Outline Reviewer Assessment

## 7-Dimension Scores
1. Argument Clarity: [X/5]
2. Argument Completeness: [X/5]
3. Literature Support: [X/5]
4. Methodological Clarity: [X/5]
5. Originality Expression: [X/5]
6. Organization: [X/5]
7. Platform Fit: [X/5]

**Total: [X/35]** (Threshold: 28/35)

## Identified Issues
[Prioritized list: High/Medium/Low severity]

## Improvement Recommendations
[Concrete suggestions for each issue]

## Predicted Improvement
[Expected score after implementing recommendations]
```

---

## Notes

- These standards are calibrated for **philosophy and interdisciplinary papers** on **preprint platforms**
- Standards may need adjustment for pure empirical sciences or formal logic papers
- When in doubt, err on the side of higher quality standards—better to over-prepare than under-prepare
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 323kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 198kUpdated Claude CodeCodexVerifiedInstall