Skill Tracer
Skills › Scientific Agent Skills › citation-management › search_strategies.md

search_strategies.md

73 lines · skills/citation-management/references/search_strategies.md at 5f2bc03

Open on GitHub

Most marks come from matching words in the file, so treat them as pointers.

1# Search Strategies
2
3Google Scholar and PubMed query construction: operators, field tags, MeSH terms,
4date and publication-type filters, and worked query examples.
5

Search Strategies

Google Scholar and PubMed query construction: operators, field tags, MeSH terms, date and publication-type filters, and worked query examples.

Raw lines 1 to 5
6## Search Strategies
7

Search Strategies

Raw lines 6 to 7
8### Google Scholar Best Practices
9
10Use [Google Scholar's documented search controls](https://scholar.google.com/intl/en/scholar/help.html):
11quoted titles/phrases, `author:`, exclusion terms, and the Advanced Search
12publication/title/date fields. Use year controls or script arguments rather
13than `2020..2024`; Scholar does not offer a global `sort:citations` operator.
14Citation counts reflect age, field, and database coverage; they are discovery
15signals, not evidence-quality thresholds.
17```bash
18# Find recent reviews; examples are illustrative searches.
19python scripts/search_google_scholar.py 'CRISPR review' --year-start 2023 --year-end 2024
21# Author and topic
22python scripts/search_google_scholar.py 'author:Church "synthetic biology"'
24# Citation sorting applies only to the retrieved sample.
25python scripts/search_google_scholar.py '"deep learning"' \
26 --year-start 2012 --year-end 2015 --sort-by citations --limit 50
27```
29For global citation-count ordering over API search matches, use the bundled
30OpenAlex client (`--sort-by citations`); document the different database coverage.

Google Scholar Best Practices

Use Google Scholar's documented search controls: quoted titles/phrases, author:, exclusion terms, and the Advanced Search publication/title/date fields. Use year controls or script arguments rather than 2020..2024; Scholar does not offer a global sort:citations operator. Citation counts reflect age, field, and database coverage; they are discovery signals, not evidence-quality thresholds.

# Find recent reviews; examples are illustrative searches.
python scripts/search_google_scholar.py 'CRISPR review' --year-start 2023 --year-end 2024

# Author and topic
python scripts/search_google_scholar.py 'author:Church "synthetic biology"'

# Citation sorting applies only to the retrieved sample.
python scripts/search_google_scholar.py '"deep learning"' \
  --year-start 2012 --year-end 2015 --sort-by citations --limit 50

For global citation-count ordering over API search matches, use the bundled OpenAlex client (--sort-by citations); document the different database coverage.

Raw lines 8 to 31
Runs code python scripts/search_google_scholar.py :19
32### PubMed Best Practices
34**Using MeSH Terms**:
35MeSH (Medical Subject Headings) provides controlled vocabulary for precise searching.
371. **Find MeSH terms** at https://meshb.nlm.nih.gov/search
382. **Use in queries**: `"Diabetes Mellitus, Type 2"[MeSH]`
393. **Combine with keywords** for comprehensive coverage
41**Field Tags**:
42```
43[Title] # Search in title only
44[Title/Abstract] # Search in title or abstract
45[Author] # Search by author name
46[Journal] # Search specific journal
47[Publication Date] # Date range
48[Publication Type] # Article type
49[MeSH] # MeSH term
50```
52**Building Complex Queries**:
53```bash
54# Clinical trials on diabetes treatment published recently
55"Diabetes Mellitus, Type 2"[MeSH] AND "Drug Therapy"[MeSH]
56AND "Clinical Trial"[Publication Type] AND 2020:2024[Publication Date]
58# Reviews on CRISPR in specific journal
59"CRISPR-Cas Systems"[MeSH] AND "Nature"[Journal] AND "Review"[Publication Type]
61# Specific author's recent work
62"Smith AB"[Author] AND cancer[Title/Abstract] AND 2022:2024[Publication Date]
63```
65**E-utilities for Automation**:
66The bundled PubMed script uses ESearch and EFetch. Other E-utilities are documented
67manual alternatives:
68- **ESearch**: Search and retrieve PMIDs
69- **EFetch**: Retrieve full metadata
70- **ESummary**: Get summary information
71- **ELink**: Find related articles
73See `references/pubmed_search.md` for complete API documentation.

PubMed Best Practices

Using MeSH Terms: MeSH (Medical Subject Headings) provides controlled vocabulary for precise searching.

  1. Find MeSH terms at https://meshb.nlm.nih.gov/search
  2. Use in queries: "Diabetes Mellitus, Type 2"[MeSH]
  3. Combine with keywords for comprehensive coverage

Field Tags:

[Title]              # Search in title only
[Title/Abstract]     # Search in title or abstract
[Author]             # Search by author name
[Journal]            # Search specific journal
[Publication Date]   # Date range
[Publication Type]   # Article type
[MeSH]              # MeSH term

Building Complex Queries:

# Clinical trials on diabetes treatment published recently
"Diabetes Mellitus, Type 2"[MeSH] AND "Drug Therapy"[MeSH] 
AND "Clinical Trial"[Publication Type] AND 2020:2024[Publication Date]

# Reviews on CRISPR in specific journal
"CRISPR-Cas Systems"[MeSH] AND "Nature"[Journal] AND "Review"[Publication Type]

# Specific author's recent work
"Smith AB"[Author] AND cancer[Title/Abstract] AND 2022:2024[Publication Date]

E-utilities for Automation: The bundled PubMed script uses ESearch and EFetch. Other E-utilities are documented manual alternatives:

  • ESearch: Search and retrieve PMIDs
  • EFetch: Retrieve full metadata
  • ESummary: Get summary information
  • ELink: Find related articles

See references/pubmed_search.md for complete API documentation.

Raw lines 32 to 73