Scientific Prediction Skill
Predict properties, trends, and outcomes across scientific disciplines.
When to Use
- "Predict the solubility of this compound"
- "What's the expected trend for..."
- "Estimate the effect size for this intervention"
- "Forecast the trajectory of..."
- "What properties would this material have?"
- Model-based estimation tasks
When NOT to Use
- Looking up known properties (use literature-search)
- Running actual computations (use code-execution)
- Verifying existing predictions (use scienceclaw-verification)
- Real-time data monitoring or alerts
Prediction Categories
1. Property Prediction
- Chemistry: Molecular properties (logP, solubility, toxicity, pKa, boiling point)
- Materials: Mechanical (strength, hardness), thermal, electrical properties
- Biology: Protein function, binding affinity, gene expression levels
- Physics: Material behavior under conditions (temperature, pressure)
2. Trend Analysis
- Time-series extrapolation with confidence intervals
- Growth/decay curve fitting (exponential, logistic, polynomial)
- Seasonal pattern identification
- Regime change detection
3. Outcome Prediction
- Clinical trial outcome estimation
- Experimental result prediction
- Treatment response probability
- Environmental impact forecasting
4. Model-Based Estimation
- QSAR/QSPR (quantitative structure-activity/property relationships)
- Pharmacokinetic modeling (ADME)
- Population dynamics modeling
- Economic indicator forecasting
Output Format
All predictions must include:
**Prediction**: [Value or range]
**Confidence Interval**: [Lower - Upper] at [confidence level]%
**Method**: [Approach used]
**Key Assumptions**: [List]
**Uncertainty Sources**: [List]
**Validation**: [How to verify this prediction]
**Caveats**: [Known limitations]
Guidelines
- Always quantify uncertainty — never provide point estimates without ranges
- State assumptions explicitly — hidden assumptions undermine predictions
- Distinguish extrapolation from interpolation — flag when predicting outside training data range
- Consider domain constraints — physical laws, biological limits, economic boundaries
- Recommend validation approaches — suggest experiments or data to verify predictions
- Use appropriate models — match model complexity to data availability
- Flag low-confidence predictions — be transparent about reliability
Discipline-Specific Methods
| Domain |
Common Methods |
| Chemistry |
QSAR, DFT calculations, molecular dynamics |
| Biology |
Sequence-based prediction, network analysis |
| Medicine |
Cox regression, Kaplan-Meier, NNT/NNH |
| Physics |
Theoretical models, scaling laws |
| Economics |
Econometric models, agent-based simulation |
| Climate |
GCM projections, statistical downscaling |
| Materials |
Phase diagrams, computational screening |
| Sociology |
Panel data models, social network evolution |
Computational Prediction Tools
When predictions require computation, integrate with these skills:
Molecular Property Prediction
- Use rdkit-chemistry for descriptor-based QSAR models
- Use pubchem-compound to retrieve experimental property values for training data
- Use scikit-learn-ml to build/evaluate prediction models
Materials Property Prediction
- Use materials-project to retrieve DFT-computed properties
- Use pymatgen-materials for structure-property analysis
- Use scipy-analysis for interpolation and regression
Biological Outcome Prediction
- Use biopython-bio for sequence-based feature extraction
- Use transformers-inference for protein language models (ESM, ProtTrans)
- Use scanpy-singlecell for cell-type and trajectory prediction
Geospatial/Climate Prediction
- Use geopandas-spatial for spatial feature engineering
- Use copernicus-climate for historical climate data as training input
- Use statsmodels-stats for time-series forecasting models
Zero-Hallucination Rule
ALL factual claims, citations, database results, and scientific data presented to the user MUST come from actual tool results (API calls, code execution, web search) in this conversation. NEVER fabricate or "fill in" details from training data. If a tool returns no results or partial data, report exactly what happened.
1---2name: scienceclaw-prediction3description: Predict scientific properties, trends, and outcomes. Use when: user asks for property prediction, trend forecasting, or model-based estimation. NOT for: historical data lookup or real-time monitoring.4---5
6# Scientific Prediction Skill
7
8Predict properties, trends, and outcomes across scientific disciplines.
9
10## When to Use
11
12- "Predict the solubility of this compound"
13- "What's the expected trend for..."
14- "Estimate the effect size for this intervention"
15- "Forecast the trajectory of..."
16- "What properties would this material have?"
17- Model-based estimation tasks
18
19## When NOT to Use
20
21- Looking up known properties (use literature-search)
22- Running actual computations (use code-execution)
23- Verifying existing predictions (use scienceclaw-verification)
24- Real-time data monitoring or alerts
25
26## Prediction Categories
27
28### 1. Property Prediction
29- **Chemistry**: Molecular properties (logP, solubility, toxicity, pKa, boiling point)
30- **Materials**: Mechanical (strength, hardness), thermal, electrical properties
31- **Biology**: Protein function, binding affinity, gene expression levels
32- **Physics**: Material behavior under conditions (temperature, pressure)
33
34### 2. Trend Analysis
35- Time-series extrapolation with confidence intervals
36- Growth/decay curve fitting (exponential, logistic, polynomial)
37- Seasonal pattern identification
38- Regime change detection
39
40### 3. Outcome Prediction
41- Clinical trial outcome estimation
42- Experimental result prediction
43- Treatment response probability
44- Environmental impact forecasting
45
46### 4. Model-Based Estimation
47- QSAR/QSPR (quantitative structure-activity/property relationships)
48- Pharmacokinetic modeling (ADME)
49- Population dynamics modeling
50- Economic indicator forecasting
51
52## Output Format
53
54All predictions must include:
55
56```
57**Prediction**: [Value or range]
58**Confidence Interval**: [Lower - Upper] at [confidence level]%
59**Method**: [Approach used]
60**Key Assumptions**: [List]
61**Uncertainty Sources**: [List]
62**Validation**: [How to verify this prediction]
63**Caveats**: [Known limitations]
64```
65
66## Guidelines
67
681. **Always quantify uncertainty** — never provide point estimates without ranges
692. **State assumptions explicitly** — hidden assumptions undermine predictions
703. **Distinguish extrapolation from interpolation** — flag when predicting outside training data range
714. **Consider domain constraints** — physical laws, biological limits, economic boundaries
725. **Recommend validation approaches** — suggest experiments or data to verify predictions
736. **Use appropriate models** — match model complexity to data availability
747. **Flag low-confidence predictions** — be transparent about reliability
75
76## Discipline-Specific Methods
77
78| Domain | Common Methods |
79|--------|---------------|
80| Chemistry | QSAR, DFT calculations, molecular dynamics |
81| Biology | Sequence-based prediction, network analysis |
82| Medicine | Cox regression, Kaplan-Meier, NNT/NNH |
83| Physics | Theoretical models, scaling laws |
84| Economics | Econometric models, agent-based simulation |
85| Climate | GCM projections, statistical downscaling |
86| Materials | Phase diagrams, computational screening |
87| Sociology | Panel data models, social network evolution |
88
89## Computational Prediction Tools
90
91When predictions require computation, integrate with these skills:
92
93### Molecular Property Prediction
94- Use **rdkit-chemistry** for descriptor-based QSAR models
95- Use **pubchem-compound** to retrieve experimental property values for training data
96- Use **scikit-learn-ml** to build/evaluate prediction models
97
98### Materials Property Prediction
99- Use **materials-project** to retrieve DFT-computed properties
100- Use **pymatgen-materials** for structure-property analysis
101- Use **scipy-analysis** for interpolation and regression
102
103### Biological Outcome Prediction
104- Use **biopython-bio** for sequence-based feature extraction
105- Use **transformers-inference** for protein language models (ESM, ProtTrans)
106- Use **scanpy-singlecell** for cell-type and trajectory prediction
107
108### Geospatial/Climate Prediction
109- Use **geopandas-spatial** for spatial feature engineering
110- Use **copernicus-climate** for historical climate data as training input
111- Use **statsmodels-stats** for time-series forecasting models
112
113## Zero-Hallucination Rule
114
115ALL factual claims, citations, database results, and scientific data presented to the user MUST come from actual tool results (API calls, code execution, web search) in this conversation. NEVER fabricate or "fill in" details from training data. If a tool returns no results or partial data, report exactly what happened.
beita6969