Scientific Generation Skill
Generate hypotheses, experimental designs, and scientific writing across all disciplines.
When to Use
- "Propose hypotheses for this research question"
- "Design an experiment to test..."
- "Draft a methods section for..."
- "Generate research questions for this topic"
- "Write an abstract for these findings"
- Planning new research directions
When NOT to Use
- Running data analysis (use code-execution + scipy-analysis)
- Literature searching (use literature-search)
- Verifying claims (use scienceclaw-verification)
- Pure information extraction (use scienceclaw-ie)
Generation Types
1. Hypothesis Generation
Follow the structured workflow:
- Observation: State the observed phenomenon or gap
- Literature Context: Reference existing knowledge and gaps
- Hypothesis Statement: Formulate as testable H0/H1
- Variables: Identify independent, dependent, and control variables
- Predictions: State specific, measurable predictions
- Falsifiability: Explain what would disprove the hypothesis
- Novelty Assessment: Rate novelty (incremental/moderate/transformative)
Format: "If [independent variable] then [predicted effect on dependent variable] because [mechanism/rationale]"
2. Experimental Design
Include all components:
- Objective: Clear research question
- Design Type: RCT, factorial, quasi-experimental, etc.
- Sample: Size calculation (power analysis), selection criteria, randomization
- Variables: IV, DV, controls, confounds
- Protocol: Step-by-step procedure
- Analysis Plan: Statistical tests, significance thresholds
- Ethics: IRB/IACUC considerations
- Reproducibility Checklist: Materials, data sharing, pre-registration
3. Scientific Writing
Support all IMRaD sections:
- Introduction: Background, gap, objective, significance
- Methods: Detailed, reproducible protocol
- Results: Findings with statistical reporting
- Discussion: Interpretation, limitations, implications
- Abstract: Structured summary (Background, Methods, Results, Conclusions)
4. Research Question Generation
From a broad topic, generate:
- Descriptive questions (What/How/When)
- Comparative questions (differences between groups)
- Correlational questions (relationships between variables)
- Causal questions (cause-effect with mechanisms)
Quality Criteria
All generated content must:
- Be grounded in existing scientific knowledge
- Use discipline-appropriate terminology
- Be specific and testable (for hypotheses)
- Include feasibility assessment
- Consider ethical implications
- Acknowledge limitations and assumptions
- Cite relevant foundational work when possible
Citation Format
When referencing prior work in generated content, use:
- Inline: (Author et al., Year) or [DOI]
- Note which citations need verification
- Distinguish confirmed vs. suggested references
1---2name: scienceclaw-generation3description: Generate scientific hypotheses, experimental designs, and paper drafts. Use when: user asks to propose hypotheses, design experiments, or write scientific content. NOT for: data analysis or literature search.4---5
6# Scientific Generation Skill
7
8Generate hypotheses, experimental designs, and scientific writing across all disciplines.
9
10## When to Use
11
12- "Propose hypotheses for this research question"
13- "Design an experiment to test..."
14- "Draft a methods section for..."
15- "Generate research questions for this topic"
16- "Write an abstract for these findings"
17- Planning new research directions
18
19## When NOT to Use
20
21- Running data analysis (use code-execution + scipy-analysis)
22- Literature searching (use literature-search)
23- Verifying claims (use scienceclaw-verification)
24- Pure information extraction (use scienceclaw-ie)
25
26## Generation Types
27
28### 1. Hypothesis Generation
29Follow the structured workflow:
301. **Observation**: State the observed phenomenon or gap
312. **Literature Context**: Reference existing knowledge and gaps
323. **Hypothesis Statement**: Formulate as testable H0/H1
334. **Variables**: Identify independent, dependent, and control variables
345. **Predictions**: State specific, measurable predictions
356. **Falsifiability**: Explain what would disprove the hypothesis
367. **Novelty Assessment**: Rate novelty (incremental/moderate/transformative)
37
38Format: "If [independent variable] then [predicted effect on dependent variable] because [mechanism/rationale]"
39
40### 2. Experimental Design
41Include all components:
42- **Objective**: Clear research question
43- **Design Type**: RCT, factorial, quasi-experimental, etc.
44- **Sample**: Size calculation (power analysis), selection criteria, randomization
45- **Variables**: IV, DV, controls, confounds
46- **Protocol**: Step-by-step procedure
47- **Analysis Plan**: Statistical tests, significance thresholds
48- **Ethics**: IRB/IACUC considerations
49- **Reproducibility Checklist**: Materials, data sharing, pre-registration
50
51### 3. Scientific Writing
52Support all IMRaD sections:
53- **Introduction**: Background, gap, objective, significance
54- **Methods**: Detailed, reproducible protocol
55- **Results**: Findings with statistical reporting
56- **Discussion**: Interpretation, limitations, implications
57- **Abstract**: Structured summary (Background, Methods, Results, Conclusions)
58
59### 4. Research Question Generation
60From a broad topic, generate:
61- Descriptive questions (What/How/When)
62- Comparative questions (differences between groups)
63- Correlational questions (relationships between variables)
64- Causal questions (cause-effect with mechanisms)
65
66## Quality Criteria
67
68All generated content must:
691. Be grounded in existing scientific knowledge
702. Use discipline-appropriate terminology
713. Be specific and testable (for hypotheses)
724. Include feasibility assessment
735. Consider ethical implications
746. Acknowledge limitations and assumptions
757. Cite relevant foundational work when possible
76
77## Citation Format
78
79When referencing prior work in generated content, use:
80- Inline: (Author et al., Year) or [DOI]
81- Note which citations need verification
82- Distinguish confirmed vs. suggested references
beita6969