clearai-dsh 0.1.0

package/presets/clearai/template/skills/literature-review/SKILL.md

@@ -0,0 +1,72 @@
+---
+name: literature-review
+description: |
+  【文献综述·系统检索】按 PRISMA 思路做多库检索、主题综合与引用核验。适用：研究主题的系统性文献梳理、技术路线证据链。不适用：售前企业快研（用 domain-presearch）；单篇 DOI 查找（用 paper-lookup）。
+license: MIT license
+metadata:
+  version: 1.0-clearai
+  skill-author: K-Dense Inc. (adapted for ClearAI)
+  tier: system
+  origin: template
+  created_at: '2026-06-12T02:47:05.409207+00:00'
+---
+
+# 文献综述 Skill（ClearAI 版）
+
+## 使用边界
+
+- **适用**：需系统性梳理某技术/工艺/行业的学术与工程文献；撰写 `products/reports/literature_review.md`。
+- **不适用**：快速企业预研 → `domain-presearch`；仅查几篇论文 → `paper-lookup`。
+
+## ClearAI 工具与路径映射
+
+- 广度检索 → `web_search`（领域/学术关键词，标注 sources）
+- 关键来源核验 → `web_fetch`（只打开关键原始落地页、摘要页或公开附件，不浏览全部结果）
+- 学术 API 检索 → `bash` + `paper-lookup` 参考（`references/`）
+- 综述正文 → `write` 到 `products/reports/literature_review.md`
+- 检索日志 → `lab/knowledge/lit_search_log.md`
+- 引用库 → `lab/knowledge/references.bib`（配合 `citation-management`）
+- PRISMA 图 → mermaid → `lab/diagrams/`
+- 经验回写 → `clear/memory/literature_review_lessons.md`
+
+## 来源优先级（对齐 domain-presearch）
+
+P0 标准/手册 > P1 学术论文 > P2 专利 > P3 企业公开 > P4 行业报告 > P5 推断
+
+## 工作流
+
+### Phase 1：规划
+
+- 明确研究问题（PICO 变体：Process / Intervention / Comparison / Outcome）
+- 确定综述类型：叙述性 / 系统性 / 范围综述
+- 时间、地域、文献类型边界
+
+### Phase 2：检索
+
+- `web_search` 多组并行关键词（中英文）
+- 对纳入结论承重的候选，用 `web_fetch` 核验题名、作者、摘要、出处与公开附件语境
+- 深度学术需求：`read` `paper-lookup/SKILL.md` 并按 `references/` 调用 API（`bash` curl）
+
+检索策略见 `references/search_strategies.md`（若已复制）。
+
+### Phase 3：筛选与综合
+
+- 纳入/排除标准；记录于 `lab/knowledge/lit_search_log.md`
+- 主题归类：方法、效果、局限、应用案例
+
+### Phase 4：引用核验
+
+加载 `citation-management`：DOI 校验、BibTeX 去重
+
+### Phase 5：撰写与自检
+
+- 输出 `products/reports/literature_review.md`
+- 文末可点击来源列表 `[N]`
+- 可选 PRISMA 流程 mermaid
+
+## 交付清单
+
+- [ ] 研究问题与检索式已记录
+- [ ] 纳入文献表（标题、年份、来源、相关性）
+- [ ] 综合结论与证据空白
+- [ ] 引用与 `references.bib` 一致

package/presets/clearai/template/skills/literature-review/references/citation_styles.md

@@ -0,0 +1,166 @@
+# Citation Styles Reference
+
+This document provides detailed guidelines for formatting citations in various academic styles commonly used in literature reviews.
+
+## APA Style (7th Edition)
+
+### Journal Articles
+
+**Format**: Author, A. A., Author, B. B., & Author, C. C. (Year). Title of article. *Title of Periodical*, *volume*(issue), page range. https://doi.org/xx.xxx/yyyy
+
+**Example**: Smith, J. D., Johnson, M. L., & Williams, K. R. (2023). Machine learning approaches in drug discovery. *Nature Reviews Drug Discovery*, *22*(4), 301-318. https://doi.org/10.1038/nrd.2023.001
+
+### Books
+
+**Format**: Author, A. A. (Year). *Title of work: Capital letter also for subtitle*. Publisher Name. https://doi.org/xxxx
+
+**Example**: Kumar, V., Abbas, A. K., & Aster, J. C. (2021). *Robbins and Cotran pathologic basis of disease* (10th ed.). Elsevier.
+
+### Book Chapters
+
+**Format**: Author, A. A., & Author, B. B. (Year). Title of chapter. In E. E. Editor & F. F. Editor (Eds.), *Title of book* (pp. xx-xx). Publisher.
+
+**Example**: Brown, P. O., & Botstein, D. (2020). Exploring the new world of the genome with DNA microarrays. In M. B. Eisen & P. O. Brown (Eds.), *DNA microarrays: A molecular cloning manual* (pp. 1-45). Cold Spring Harbor Laboratory Press.
+
+### Preprints
+
+**Format**: Author, A. A., & Author, B. B. (Year). Title of preprint. *Repository Name*. https://doi.org/xxxx
+
+**Example**: Zhang, Y., Chen, L., & Wang, H. (2024). Novel therapeutic targets in Alzheimer's disease. *bioRxiv*. https://doi.org/10.1101/2024.01.001
+
+### Conference Papers
+
+**Format**: Author, A. A. (Year, Month day-day). Title of paper. In E. E. Editor (Ed.), *Title of conference proceedings* (pp. xx-xx). Publisher. https://doi.org/xxxx
+
+---
+
+## Nature Style
+
+### Journal Articles
+
+**Format**: Author, A. A., Author, B. B. & Author, C. C. Title of article. *J. Name* **volume**, page range (year).
+
+**Example**: Smith, J. D., Johnson, M. L. & Williams, K. R. Machine learning approaches in drug discovery. *Nat. Rev. Drug Discov.* **22**, 301-318 (2023).
+
+### Books
+
+**Format**: Author, A. A. & Author, B. B. *Book Title* (Publisher, Year).
+
+**Example**: Kumar, V., Abbas, A. K. & Aster, J. C. *Robbins and Cotran Pathologic Basis of Disease* 10th edn (Elsevier, 2021).
+
+### Multiple Authors
+
+- 1-2 authors: List all
+- 3+ authors: List first author followed by "et al."
+
+**Example**: Zhang, Y. et al. Novel therapeutic targets in Alzheimer's disease. *bioRxiv* https://doi.org/10.1101/2024.01.001 (2024).
+
+---
+
+## Chicago Style (Author-Date)
+
+### Journal Articles
+
+**Format**: Author, First Name Middle Initial. Year. "Article Title." *Journal Title* volume, no. issue (Month): page range. https://doi.org/xxxx.
+
+**Example**: Smith, John D., Mary L. Johnson, and Karen R. Williams. 2023. "Machine Learning Approaches in Drug Discovery." *Nature Reviews Drug Discovery* 22, no. 4 (April): 301-318. https://doi.org/10.1038/nrd.2023.001.
+
+### Books
+
+**Format**: Author, First Name Middle Initial. Year. *Book Title: Subtitle*. Edition. Place: Publisher.
+
+**Example**: Kumar, Vinay, Abul K. Abbas, and Jon C. Aster. 2021. *Robbins and Cotran Pathologic Basis of Disease*. 10th ed. Philadelphia: Elsevier.
+
+---
+
+## Vancouver Style (Numbered)
+
+### Journal Articles
+
+**Format**: Author AA, Author BB, Author CC. Title of article. Abbreviated Journal Name. Year;volume(issue):page range.
+
+**Example**: Smith JD, Johnson ML, Williams KR. Machine learning approaches in drug discovery. Nat Rev Drug Discov. 2023;22(4):301-18.
+
+### Books
+
+**Format**: Author AA, Author BB. Title of book. Edition. Place: Publisher; Year.
+
+**Example**: Kumar V, Abbas AK, Aster JC. Robbins and Cotran pathologic basis of disease. 10th ed. Philadelphia: Elsevier; 2021.
+
+### Citation in Text
+
+Use superscript numbers in order of appearance: "Recent studies^1,2^ have shown..."
+
+---
+
+## IEEE Style
+
+### Journal Articles
+
+**Format**: [#] A. A. Author, B. B. Author, and C. C. Author, "Title of article," *Abbreviated Journal Name*, vol. x, no. x, pp. xxx-xxx, Month Year.
+
+**Example**: [1] J. D. Smith, M. L. Johnson, and K. R. Williams, "Machine learning approaches in drug discovery," *Nat. Rev. Drug Discov.*, vol. 22, no. 4, pp. 301-318, Apr. 2023.
+
+### Books
+
+**Format**: [#] A. A. Author, *Title of Book*, xth ed. City, State: Publisher, Year.
+
+**Example**: [2] V. Kumar, A. K. Abbas, and J. C. Aster, *Robbins and Cotran Pathologic Basis of Disease*, 10th ed. Philadelphia, PA: Elsevier, 2021.
+
+---
+
+## Common Abbreviations for Journal Names
+
+- Nature: Nat.
+- Science: Science
+- Cell: Cell
+- Nature Reviews Drug Discovery: Nat. Rev. Drug Discov.
+- Journal of the American Chemical Society: J. Am. Chem. Soc.
+- Proceedings of the National Academy of Sciences: Proc. Natl. Acad. Sci. U.S.A.
+- PLOS ONE: PLoS ONE
+- Bioinformatics: Bioinformatics
+- Nucleic Acids Research: Nucleic Acids Res.
+
+---
+
+## DOI Best Practices
+
+1. **Always verify DOIs**: Use the verify_citations.py script to check all DOIs
+2. **Format as URLs**: https://doi.org/10.xxxx/yyyy (preferred over doi:10.xxxx/yyyy)
+3. **No period after DOI**: DOI should be the last element without trailing punctuation
+4. **Resolve redirects**: Check that DOIs resolve to the correct article
+
+---
+
+## In-Text Citation Guidelines
+
+### APA Style
+- (Smith et al., 2023)
+- Smith et al. (2023) demonstrated...
+- Multiple citations: (Brown, 2022; Smith et al., 2023; Zhang, 2024)
+
+### Nature Style
+- Superscript numbers: Recent studies^1,2^ have shown...
+- Or: Recent studies (refs 1,2) have shown...
+
+### Chicago Style
+- (Smith, Johnson, and Williams 2023)
+- Smith, Johnson, and Williams (2023) found...
+
+---
+
+## Reference List Organization
+
+### By Citation Style
+- **APA, Chicago**: Alphabetical by first author's last name
+- **Nature, Vancouver, IEEE**: Numerical order of first appearance in text
+
+### Hanging Indents
+Most styles use hanging indents where the first line is flush left and subsequent lines are indented.
+
+### Consistency
+Maintain consistent formatting throughout:
+- Capitalization (title case vs. sentence case)
+- Journal name abbreviations
+- DOI presentation
+- Author name format

package/presets/clearai/template/skills/literature-review/references/database_strategies.md

@@ -0,0 +1,455 @@
+# Literature Database Search Strategies
+
+This document provides comprehensive guidance for searching multiple literature databases systematically and effectively.
+
+## Available Databases and Skills
+
+### Biomedical & Life Sciences
+
+#### PubMed / PubMed Central
+- **Access**: Use `gget` skill or WebFetch tool
+- **Coverage**: 35M+ citations in biomedical literature
+- **Best for**: Clinical studies, biomedical research, genetics, molecular biology
+- **Search tips**: Use MeSH terms, Boolean operators (AND, OR, NOT), field tags [Title], [Author]
+- **Example**: `"CRISPR"[Title] AND "gene editing"[Title/Abstract] AND 2020:2024[Publication Date]`
+
+#### bioRxiv / medRxiv
+- **Access**: Use `gget` skill or direct API
+- **Coverage**: Preprints in biology and medicine
+- **Best for**: Latest unpublished research, cutting-edge findings
+- **Note**: Not peer-reviewed; verify findings with caution
+- **Search tips**: Search by category (bioinformatics, genomics, etc.)
+
+### General Scientific Literature
+
+#### arXiv
+- **Access**: Direct API access
+- **Coverage**: Preprints in physics, mathematics, computer science, quantitative biology
+- **Best for**: Computational methods, bioinformatics algorithms, theoretical work
+- **Categories**: q-bio (Quantitative Biology), cs.LG (Machine Learning), stat.ML (Statistics)
+- **Search format**: `cat:q-bio.QM AND title:"single cell"`
+
+#### Semantic Scholar
+- **Access**: Direct API (requires API key)
+- **Coverage**: 200M+ papers across all fields
+- **Best for**: Cross-disciplinary searches, citation graphs, paper recommendations
+- **Features**: Influential citations, paper summaries, related papers
+- **Rate limits**: 100 requests/5 minutes with API key
+
+#### Google Scholar
+- **Access**: Web scraping (use cautiously) or manual search
+- **Coverage**: Comprehensive across all fields
+- **Best for**: Finding highly cited papers, conference proceedings, theses
+- **Limitations**: No official API, rate limiting
+- **Export**: Use "Cite" feature for formatted citations
+
+### Specialized Databases
+
+#### ChEMBL / PubChem
+- **Access**: Use `gget` skill or `bioservices` skill
+- **Coverage**: Chemical compounds, bioactivity data, drug molecules
+- **Best for**: Drug discovery, chemical biology, medicinal chemistry
+- **ChEMBL**: 2M+ compounds, bioactivity data
+- **PubChem**: 110M+ compounds, assay data
+
+#### UniProt
+- **Access**: Use `gget` skill or `bioservices` skill
+- **Coverage**: Protein sequence and functional information
+- **Best for**: Protein research, sequence analysis, functional annotations
+- **Search by**: Protein name, gene name, organism, function
+
+#### KEGG (Kyoto Encyclopedia of Genes and Genomes)
+- **Access**: Use `bioservices` skill
+- **Coverage**: Pathways, diseases, drugs, genes
+- **Best for**: Pathway analysis, systems biology, metabolic research
+
+#### COSMIC (Catalogue of Somatic Mutations in Cancer)
+- **Access**: Use `gget` skill or direct download
+- **Coverage**: Cancer genomics, somatic mutations
+- **Best for**: Cancer research, mutation analysis
+
+#### AlphaFold Database
+- **Access**: Use `gget` skill with `alphafold` command
+- **Coverage**: 200M+ protein structure predictions
+- **Best for**: Structural biology, protein modeling
+
+#### PDB (Protein Data Bank)
+- **Access**: Use `gget` or direct API
+- **Coverage**: Experimental 3D structures of proteins, nucleic acids
+- **Best for**: Structural biology, drug design, molecular modeling
+
+### Citation & Reference Management
+
+#### OpenAlex
+- **Access**: Direct API (free, no key required)
+- **Coverage**: 250M+ works, comprehensive metadata
+- **Best for**: Citation analysis, author disambiguation, institutional research
+- **Features**: Open access, excellent for bibliometrics
+
+#### Dimensions
+- **Access**: Free tier available
+- **Coverage**: Publications, grants, patents, clinical trials
+- **Best for**: Research impact, funding analysis, translational research
+
+---
+
+## Search Strategy Framework
+
+### 1. Define Research Question (PICO Framework)
+
+For clinical/biomedical reviews:
+- **P**opulation: Who is the study about?
+- **I**ntervention: What is being tested?
+- **C**omparison: What is it compared to?
+- **O**utcome: What are the results?
+
+**Example**: "What is the efficacy of CRISPR-Cas9 gene therapy (I) for treating sickle cell disease (P) compared to standard care (C) in improving patient outcomes (O)?"
+
+### 2. Develop Search Terms
+
+#### Primary Concepts
+Identify 2-4 main concepts from your research question.
+
+**Example**:
+- Concept 1: CRISPR, Cas9, gene editing
+- Concept 2: sickle cell disease, SCD, hemoglobin disorders
+- Concept 3: gene therapy, therapeutic editing
+
+#### Synonyms & Related Terms
+List alternative terms, abbreviations, and related concepts.
+
+**Tool**: Use MeSH (Medical Subject Headings) browser for standardized terms
+
+#### Boolean Operators
+- **AND**: Narrows search (must include both terms)
+- **OR**: Broadens search (includes either term)
+- **NOT**: Excludes terms
+
+**Example**: `(CRISPR OR Cas9 OR "gene editing") AND ("sickle cell" OR SCD) AND therapy`
+
+#### Wildcards & Truncation
+- `*` or `%`: Matches any characters
+- `?`: Matches single character
+
+**Example**: `genom*` matches genomic, genomics, genome
+
+### 3. Set Inclusion/Exclusion Criteria
+
+#### Inclusion Criteria
+- **Date range**: e.g., 2015-2024 (last 10 years)
+- **Language**: English (or specify multilingual)
+- **Publication type**: Peer-reviewed articles, reviews, preprints
+- **Study design**: RCTs, cohort studies, meta-analyses
+- **Population**: Human, animal models, in vitro
+
+#### Exclusion Criteria
+- Case reports (n<5)
+- Conference abstracts without full text
+- Non-original research (editorials, commentaries)
+- Duplicate publications
+- Retracted articles
+
+### 4. Database Selection Strategy
+
+#### Multi-Database Approach
+Search at least 3 complementary databases:
+
+1. **Primary database**: PubMed (biomedical) or arXiv (computational)
+2. **Preprint server**: bioRxiv/medRxiv or arXiv
+3. **Comprehensive database**: Semantic Scholar or Google Scholar
+4. **Specialized database**: ChEMBL, UniProt, or field-specific
+
+#### Database-Specific Syntax
+
+| Database | Field Tags | Example |
+|----------|-----------|---------|
+| PubMed | [Title], [Author], [MeSH] | "CRISPR"[Title] AND 2020:2024[DP] |
+| arXiv | ti:, au:, cat: | ti:"machine learning" AND cat:q-bio.QM |
+| Semantic Scholar | title:, author:, year: | title:"deep learning" year:2020-2024 |
+
+---
+
+## Search Execution Workflow
+
+### Phase 1: Pilot Search
+1. Run initial search with broad terms
+2. Review first 50 results for relevance
+3. Note common keywords and MeSH terms
+4. Refine search strategy
+
+### Phase 2: Comprehensive Search
+1. Execute refined searches across all selected databases
+2. Export results in standard format (RIS, BibTeX, JSON)
+3. Document search strings and date for each database
+4. Record number of results per database
+
+### Phase 3: Deduplication
+1. Import all results into a single file
+2. Use `search_databases.py --deduplicate` to remove duplicates
+3. Identify duplicates by DOI (primary) or title (fallback)
+4. Keep the version with most complete metadata
+
+### Phase 4: Screening
+1. **Title screening**: Review titles, exclude obviously irrelevant
+2. **Abstract screening**: Read abstracts, apply inclusion/exclusion criteria
+3. **Full-text screening**: Obtain and review full texts
+4. Document reasons for exclusion at each stage
+
+### Phase 5: Quality Assessment
+1. Assess study quality using appropriate tools:
+   - **RCTs**: Cochrane Risk of Bias tool
+   - **Observational**: Newcastle-Ottawa Scale
+   - **Systematic reviews**: AMSTAR 2
+2. Grade quality of evidence (high, moderate, low, very low)
+3. Consider excluding very low-quality studies
+
+---
+
+## Search Documentation Template
+
+### Required Documentation
+All searches must be documented for reproducibility:
+
+```markdown
+## Search Strategy
+
+### Database: PubMed
+- **Date searched**: 2024-10-25
+- **Date range**: 2015-01-01 to 2024-10-25
+- **Search string**:
+  ```
+  ("CRISPR"[Title] OR "Cas9"[Title] OR "gene editing"[Title/Abstract])
+  AND ("sickle cell disease"[MeSH] OR "SCD"[Title/Abstract])
+  AND ("gene therapy"[MeSH] OR "therapeutic editing"[Title/Abstract])
+  AND 2015:2024[Publication Date]
+  AND English[Language]
+  ```
+- **Results**: 247 articles
+- **After deduplication**: 189 articles
+
+### Database: bioRxiv
+- **Date searched**: 2024-10-25
+- **Date range**: 2015-01-01 to 2024-10-25
+- **Search string**: "CRISPR" AND "sickle cell" (in title/abstract)
+- **Results**: 34 preprints
+- **After deduplication**: 28 preprints
+
+### Total Unique Articles
+- **Combined results**: 217 unique articles
+- **After title screening**: 156 articles
+- **After abstract screening**: 89 articles
+- **After full-text screening**: 52 articles included in review
+```
+
+---
+
+## Advanced Search Techniques
+
+### Prioritizing High-Impact Papers (CRITICAL)
+
+**Always prioritize papers based on citation count, venue quality, and author reputation.** Quality matters more than quantity.
+
+#### Citation Metrics in Database Searches
+
+Use citation counts to identify influential work:
+
+| Paper Age | Citations | Classification |
+|-----------|-----------|----------------|
+| 0-3 years | 20+ | Noteworthy |
+| 0-3 years | 100+ | Highly Influential |
+| 3-7 years | 100+ | Significant |
+| 3-7 years | 500+ | Landmark |
+| 7+ years | 500+ | Seminal |
+| 7+ years | 1000+ | Foundational |
+
+**Database-Specific Citation Features:**
+- **Google Scholar:** Sort by citation count, use "Cited by" feature
+- **Semantic Scholar:** "Highly Influential Citations" metric, citation velocity
+- **OpenAlex:** Citation counts, citation context analysis
+- **PubMed:** Use "Cited by" in PMC, check citation counts via Google Scholar
+
+#### Filtering by Journal Quality
+
+Prioritize papers from higher-tier venues:
+
+**Tier 1 (Always Prefer):**
+- Nature, Science, Cell, NEJM, Lancet, JAMA, PNAS
+- Nature Medicine, Nature Biotechnology, Nature Methods
+- Search tip: `source:Nature` or `journal:Nature` in Google Scholar
+
+**Tier 2 (High Priority):**
+- High-impact specialized journals (Impact Factor >10)
+- Top conferences: NeurIPS, ICML, ICLR, CVPR, ACL
+
+**Tier 3 (Include When Relevant):**
+- Respected field-specific journals (IF 5-10)
+
+**PubMed Journal Filtering:**
+```
+"Nature"[Journal] OR "Science"[Journal] OR "Cell"[Journal]
+```
+
+**Google Scholar Journal Filtering:**
+```
+source:Nature source:Science source:Cell
+```
+
+#### Leveraging "Cited by" Features
+
+**Finding Influential Work:**
+1. Start with a known key paper
+2. Click "Cited by" to find papers that cite it
+3. Sort citing papers by their citation count
+4. Highly-cited citing papers indicate important follow-up work
+
+**Identifying Seminal Papers:**
+1. Search your topic broadly
+2. Note which papers appear repeatedly in reference lists
+3. Papers cited by many of your results are likely seminal
+4. Check citation counts to confirm influence
+
+**Semantic Scholar Features:**
+- "Highly Influential Citations" shows citations that significantly built on the paper
+- "Citation Velocity" shows recent citation growth
+- Paper recommendations based on citation networks
+
+### Citation Chaining
+
+#### Forward Citation Search
+Find papers that cite a key paper:
+- Use Google Scholar "Cited by" feature
+- Use OpenAlex or Semantic Scholar APIs
+- Identifies newer research building on seminal work
+- **Tip:** Sort by citation count to find the most influential follow-up work
+
+#### Backward Citation Search
+Review references in key papers:
+- Extract references from included papers
+- Search for highly cited references (500+ citations for older papers)
+- Identifies foundational research
+- **Tip:** Focus on references that appear in multiple papers' bibliographies
+
+### Snowball Sampling
+1. Start with 3-5 highly relevant papers **from Tier-1 venues**
+2. Extract all their references
+3. Check which references are cited by multiple papers
+4. Review those high-overlap references - these are likely seminal
+5. Repeat for newly identified key papers
+6. **Prioritize papers with high citation counts** at each step
+
+### Author Search
+Follow prolific and reputable authors in the field:
+- Search by author name across databases
+- Check author profiles (ORCID, Google Scholar) for h-index and publication venues
+- Review recent publications and preprints
+- **Prefer authors with multiple Tier-1 publications** and high h-index (>40)
+- Look for senior authors who are recognized field leaders
+
+### Related Article Features
+Many databases suggest related articles:
+- PubMed "Similar articles"
+- Semantic Scholar "Recommended papers"
+- Use to discover papers missed by keyword search
+- **Filter recommendations by citation count and venue quality**
+
+---
+
+## Quality Control Checklist
+
+### Before Searching
+- [ ] Research question clearly defined
+- [ ] PICO criteria established (if applicable)
+- [ ] Search terms and synonyms listed
+- [ ] Inclusion/exclusion criteria documented
+- [ ] Target databases selected (minimum 3)
+- [ ] Date range determined
+
+### During Searching
+- [ ] Search string tested and refined
+- [ ] Results exported with complete metadata
+- [ ] Search parameters documented
+- [ ] Number of results recorded per database
+- [ ] Search date recorded
+
+### After Searching
+- [ ] Duplicates removed
+- [ ] Screening protocol followed
+- [ ] Reasons for exclusion documented
+- [ ] Quality assessment completed
+- [ ] All citations verified with verify_citations.py
+- [ ] Search methodology documented in review
+
+---
+
+## Common Pitfalls to Avoid
+
+1. **Too narrow search**: Missing relevant papers
+   - Solution: Include synonyms, related terms, broader concepts
+
+2. **Too broad search**: Thousands of irrelevant results
+   - Solution: Add specific concepts with AND, use field tags
+
+3. **Single database**: Incomplete coverage
+   - Solution: Search minimum 3 complementary databases
+
+4. **Ignoring preprints**: Missing latest findings
+   - Solution: Include bioRxiv, medRxiv, or arXiv
+
+5. **No documentation**: Irreproducible search
+   - Solution: Document every search string, date, and result count
+
+6. **Manual deduplication**: Time-consuming and error-prone
+   - Solution: Use search_databases.py script
+
+7. **Unverified citations**: Broken DOIs, incorrect metadata
+   - Solution: Run verify_citations.py on final reference list
+
+8. **Publication bias**: Only including published positive results
+   - Solution: Search trial registries, contact authors for unpublished data
+
+---
+
+## Example Multi-Database Search Workflow
+
+```python
+# Example workflow using available skills
+
+# 1. Search PubMed via gget
+search_term = "CRISPR AND sickle cell disease"
+# Use gget search pubmed search_term
+
+# 2. Search bioRxiv
+# Use gget search biorxiv search_term
+
+# 3. Search arXiv for computational papers
+# Search arXiv with: cat:q-bio AND "CRISPR" AND "sickle cell"
+
+# 4. Search Semantic Scholar via API
+# Use semantic scholar API with search query
+
+# 5. Aggregate and deduplicate results
+# python search_databases.py combined_results.json --deduplicate --format markdown --output review_papers.md
+
+# 6. Verify all citations
+# python verify_citations.py review_papers.md
+
+# 7. Generate final PDF
+# python generate_pdf.py review_papers.md --citation-style nature
+```
+
+---
+
+## Resources
+
+### MeSH Browser
+https://meshb.nlm.nih.gov/search
+
+### Boolean Search Tutorial
+https://www.ncbi.nlm.nih.gov/books/NBK3827/
+
+### Citation Style Guides
+See references/citation_styles.md in this skill
+
+### PRISMA Guidelines
+Preferred Reporting Items for Systematic Reviews and Meta-Analyses:
+http://www.prisma-statement.org/