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-generation
3description: "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."
4metadata: { "openclaw": { "emoji": "💡" } }
5---
6
7# Scientific Generation Skill
8
9Generate hypotheses, experimental designs, and scientific writing across all disciplines.
10
11## When to Use
12
13- "Propose hypotheses for this research question"
14- "Design an experiment to test..."
15- "Draft a methods section for..."
16- "Generate research questions for this topic"
17- "Write an abstract for these findings"
18- Planning new research directions
19
20## When NOT to Use
21
22- Running data analysis (use code-execution + scipy-analysis)
23- Literature searching (use literature-search)
24- Verifying claims (use scienceclaw-verification)
25- Pure information extraction (use scienceclaw-ie)
26
27## Generation Types
28
29### 1. Hypothesis Generation
30Follow the structured workflow:
311. **Observation**: State the observed phenomenon or gap
322. **Literature Context**: Reference existing knowledge and gaps
333. **Hypothesis Statement**: Formulate as testable H0/H1
344. **Variables**: Identify independent, dependent, and control variables
355. **Predictions**: State specific, measurable predictions
366. **Falsifiability**: Explain what would disprove the hypothesis
377. **Novelty Assessment**: Rate novelty (incremental/moderate/transformative)
38
39Format: "If [independent variable] then [predicted effect on dependent variable] because [mechanism/rationale]"
40
41### 2. Experimental Design
42Include all components:
43- **Objective**: Clear research question
44- **Design Type**: RCT, factorial, quasi-experimental, etc.
45- **Sample**: Size calculation (power analysis), selection criteria, randomization
46- **Variables**: IV, DV, controls, confounds
47- **Protocol**: Step-by-step procedure
48- **Analysis Plan**: Statistical tests, significance thresholds
49- **Ethics**: IRB/IACUC considerations
50- **Reproducibility Checklist**: Materials, data sharing, pre-registration
51
52### 3. Scientific Writing
53Support all IMRaD sections:
54- **Introduction**: Background, gap, objective, significance
55- **Methods**: Detailed, reproducible protocol
56- **Results**: Findings with statistical reporting
57- **Discussion**: Interpretation, limitations, implications
58- **Abstract**: Structured summary (Background, Methods, Results, Conclusions)
59
60### 4. Research Question Generation
61From a broad topic, generate:
62- Descriptive questions (What/How/When)
63- Comparative questions (differences between groups)
64- Correlational questions (relationships between variables)
65- Causal questions (cause-effect with mechanisms)
66
67## Quality Criteria
68
69All generated content must:
701. Be grounded in existing scientific knowledge
712. Use discipline-appropriate terminology
723. Be specific and testable (for hypotheses)
734. Include feasibility assessment
745. Consider ethical implications
756. Acknowledge limitations and assumptions
767. Cite relevant foundational work when possible
77
78## Citation Format
79
80When referencing prior work in generated content, use:
81- Inline: (Author et al., Year) or [DOI]
82- Note which citations need verification
83- Distinguish confirmed vs. suggested references
beita6969 