Scientific Classification Skill
Classify and categorize scientific content across all disciplines.
When to Use
- "Classify this paper by discipline"
- "What research methodology does this use?"
- "Categorize these results by topic"
- "Assess the quality tier of this journal/paper"
- Sorting literature by approach or field
- Identifying study design type (RCT, cohort, case-control, etc.)
When NOT to Use
- Simple keyword extraction (use scienceclaw-ie)
- Full paper summarization (use scienceclaw-summarization)
- Fact verification (use scienceclaw-verification)
Classification Dimensions
1. Discipline Classification
Classify into one of 17+ primary disciplines and subdisciplines:
- Natural Sciences: Physics, Chemistry, Biology, Medicine, Materials Science, Astronomy, Earth Science, Environmental Science, Agricultural Science
- Formal Sciences: Mathematics, Computer Science
- Social Sciences: Economics, Sociology, Psychology, Political Science, Linguistics
- Humanities: Philosophy, History, Law
2. Methodology Classification
- Empirical: experimental, observational, survey, case study
- Theoretical: mathematical modeling, simulation, analytical
- Computational: data-driven, machine learning, numerical methods
- Review: systematic review, meta-analysis, scoping review, narrative review
- Mixed Methods: combining qualitative and quantitative
3. Study Design Classification
- Randomized controlled trial (RCT)
- Cohort study (prospective/retrospective)
- Case-control study
- Cross-sectional study
- Longitudinal study
- Qualitative study (ethnography, phenomenology, grounded theory)
4. Quality Assessment
- Tier 1: High-quality evidence (large RCTs, systematic reviews with meta-analysis)
- Tier 2: Moderate evidence (cohort studies, well-designed experiments)
- Tier 3: Low evidence (case reports, expert opinion, preliminary studies)
- Tier 4: Pre-print or non-peer-reviewed
Output Format
Always structure classification output as:
**Discipline**: [Primary] > [Subdiscipline]
**Methodology**: [Type]
**Study Design**: [Design type]
**Quality Tier**: [1-4] — [Justification]
**Key Topics**: [topic1, topic2, ...]
**Confidence**: [High/Medium/Low]
Guidelines
- Always provide confidence level for classifications
- Note when content spans multiple disciplines (interdisciplinary)
- Distinguish between primary and secondary methodologies
- Consider journal impact factor and peer-review status for quality assessment
- Flag potential misclassifications or ambiguous cases
- Use standardized vocabulary (MeSH terms for biomedical, ACM CCS for CS, etc.)
1---2name: scienceclaw-classification3description: Classify scientific content by discipline, methodology, topic, and quality. Use when: user asks to categorize papers, methods, or research outputs. NOT for: simple keyword tagging or non-scientific content.4---5
6# Scientific Classification Skill
7
8Classify and categorize scientific content across all disciplines.
9
10## When to Use
11
12- "Classify this paper by discipline"
13- "What research methodology does this use?"
14- "Categorize these results by topic"
15- "Assess the quality tier of this journal/paper"
16- Sorting literature by approach or field
17- Identifying study design type (RCT, cohort, case-control, etc.)
18
19## When NOT to Use
20
21- Simple keyword extraction (use scienceclaw-ie)
22- Full paper summarization (use scienceclaw-summarization)
23- Fact verification (use scienceclaw-verification)
24
25## Classification Dimensions
26
27### 1. Discipline Classification
28Classify into one of 17+ primary disciplines and subdisciplines:
29- **Natural Sciences**: Physics, Chemistry, Biology, Medicine, Materials Science, Astronomy, Earth Science, Environmental Science, Agricultural Science
30- **Formal Sciences**: Mathematics, Computer Science
31- **Social Sciences**: Economics, Sociology, Psychology, Political Science, Linguistics
32- **Humanities**: Philosophy, History, Law
33
34### 2. Methodology Classification
35- **Empirical**: experimental, observational, survey, case study
36- **Theoretical**: mathematical modeling, simulation, analytical
37- **Computational**: data-driven, machine learning, numerical methods
38- **Review**: systematic review, meta-analysis, scoping review, narrative review
39- **Mixed Methods**: combining qualitative and quantitative
40
41### 3. Study Design Classification
42- Randomized controlled trial (RCT)
43- Cohort study (prospective/retrospective)
44- Case-control study
45- Cross-sectional study
46- Longitudinal study
47- Qualitative study (ethnography, phenomenology, grounded theory)
48
49### 4. Quality Assessment
50- **Tier 1**: High-quality evidence (large RCTs, systematic reviews with meta-analysis)
51- **Tier 2**: Moderate evidence (cohort studies, well-designed experiments)
52- **Tier 3**: Low evidence (case reports, expert opinion, preliminary studies)
53- **Tier 4**: Pre-print or non-peer-reviewed
54
55## Output Format
56
57Always structure classification output as:
58
59```
60**Discipline**: [Primary] > [Subdiscipline]
61**Methodology**: [Type]
62**Study Design**: [Design type]
63**Quality Tier**: [1-4] — [Justification]
64**Key Topics**: [topic1, topic2, ...]
65**Confidence**: [High/Medium/Low]
66```
67
68## Guidelines
69
701. Always provide confidence level for classifications
712. Note when content spans multiple disciplines (interdisciplinary)
723. Distinguish between primary and secondary methodologies
734. Consider journal impact factor and peer-review status for quality assessment
745. Flag potential misclassifications or ambiguous cases
756. Use standardized vocabulary (MeSH terms for biomedical, ACM CCS for CS, etc.)
beita6969