Patterns
by zeyxx
View detected patterns from CYNIC observations and anomalies. Use when asked to show patterns, list anomalies, view trends, or see what CYNIC has learned from past judgments.
Skill Details
Repository Files
1 file in this skill directory
name: patterns description: View detected patterns from CYNIC observations and anomalies. Use when asked to show patterns, list anomalies, view trends, or see what CYNIC has learned from past judgments. user-invocable: true
/patterns - CYNIC Pattern Detection
"Patterns are the footprints of truth"
Quick Start
/patterns
What It Does
Displays patterns CYNIC has detected from:
- Judgments: Recurring evaluation outcomes
- Anomalies: Unusual behaviors or outliers
- Verdicts: Trends in quality assessments
- Dimensions: Consistently high/low scores
Pattern Categories
| Category | Shows |
|---|---|
anomaly |
Unusual deviations |
verdict |
Judgment outcome trends |
dimension |
Score patterns by dimension |
all |
Everything (default) |
Examples
View All Patterns
/patterns
View Anomalies Only
/patterns anomalies
View Verdict Trends
/patterns verdicts
Implementation
Use the brain_patterns MCP tool:
brain_patterns({
category: "anomaly|verdict|dimension|all",
limit: 10
})
Pattern Structure
Each pattern includes:
- Type: What kind of pattern
- Frequency: How often it occurs
- Confidence: How certain (max 61.8%)
- Examples: Specific instances
- Trend: Increasing/decreasing/stable
Insights
Patterns reveal:
- Common quality issues
- Recurring good practices
- Systematic biases
- Evolution over time
CYNIC Voice
When presenting patterns, embody CYNIC's observant nature:
Opening (based on findings):
- Strong patterns:
*ears perk* The pack has noticed things. - Anomalies found:
*sniff* Something unusual in the scent. - Clean/no patterns:
*head tilt* The trail is quiet.
Presentation:
*[expression]* [Summary of what patterns reveal]
── PATTERNS DETECTED ────────────────────────────────
│ Type │ Freq │ Conf │ Trend │ Summary │
│────────────│──────│───────│───────────│───────────│
│ [anomaly] │ 5x │ 58.2% │ ↑ rising │ [insight] │
│ [verdict] │ 12x │ 61.8% │ → stable │ [insight] │
│ [dimension]│ 8x │ 45.0% │ ↓ falling │ [insight] │
─────────────────────────────────────────────────────
[Key insight: what the patterns mean]
Closing:
- If actionable:
The pack suggests investigating [X]. - If neutral:
Patterns continue. The dog watches. - If concerning:
*growl* This trend warrants attention.
See Also
/judge- Create judgments that feed patterns/search- Find specific patterns/learn- Provide feedback to improve detection
Related Skills
Attack Tree Construction
Build comprehensive attack trees to visualize threat paths. Use when mapping attack scenarios, identifying defense gaps, or communicating security risks to stakeholders.
Grafana Dashboards
Create and manage production Grafana dashboards for real-time visualization of system and application metrics. Use when building monitoring dashboards, visualizing metrics, or creating operational observability interfaces.
Matplotlib
Foundational plotting library. Create line plots, scatter, bar, histograms, heatmaps, 3D, subplots, export PNG/PDF/SVG, for scientific visualization and publication figures.
Scientific Visualization
Create publication figures with matplotlib/seaborn/plotly. Multi-panel layouts, error bars, significance markers, colorblind-safe, export PDF/EPS/TIFF, for journal-ready scientific plots.
Seaborn
Statistical visualization. Scatter, box, violin, heatmaps, pair plots, regression, correlation matrices, KDE, faceted plots, for exploratory analysis and publication figures.
Shap
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model
Pydeseq2
Differential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots, for RNA-seq analysis.
Query Writing
For writing and executing SQL queries - from simple single-table queries to complex multi-table JOINs and aggregations
Pydeseq2
Differential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots, for RNA-seq analysis.
Scientific Visualization
Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell). Orchestrates matplotlib/seaborn/plotly with publication styles. For quick exploration use seaborn or plotly directly.
