foryourhealth111-pixel/math-model-selector
bundled/skills/math-model-selector/SKILL.md
Routes problems to appropriate mathematical frameworks using expert heuristics
$ install --global
skillsauthnpx skillsauth add foryourhealth111-pixel/vco-skills-codex math-model-selectorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 13, 2026, 12:23 AM61.4s1 file scanned
SKILL.md
- name:
- math-model-selector
- description:
- Routes problems to appropriate mathematical frameworks using expert heuristics
Math Model Selector
When to Use
Trigger on phrases like:
- "what math should I use"
- "which mathematical framework"
- "how do I model this"
- "what kind of problem is this"
- "formalize this problem"
Use when user has a problem but doesn't know which mathematical domain applies.
Process
Guide user through decision tree using Polya-style questions:
1. Identify the quantity
Ask: "What quantity or phenomenon are you trying to understand?"
- Physics problem -> conservation laws, differential equations
- Economics -> equilibrium, optimization
- Data patterns -> statistics, regression
2. Characterize change
Ask: "What changes, and how does it change?"
- Discrete steps -> difference equations, recurrences
- Continuous rate -> ODEs
- Rate of rate matters -> 2nd order ODEs
- Spatial variation -> PDEs
3. Check for uncertainty
Ask: "Is there randomness or uncertainty involved?"
- Deterministic -> standard analysis
- Epistemic uncertainty -> Bayesian methods
- Random process -> probability theory, stochastic processes
4. Optimization check
Ask: "Are you optimizing something?"
- Convex objective -> linear/quadratic programming
- Non-convex -> gradient descent, evolutionary methods
- Discrete choices -> combinatorics, integer programming
5. Answer precision
Ask: "What level of answer do you need?"
- Rough estimate -> dimensional analysis
- Qualitative behavior -> phase portraits, stability
- Numerical answer -> simulation
- Exact closed form -> analytical methods
Key Questions to Ask
- What changes? (discrete vs continuous)
- What causes the change? (rate dependencies)
- What's random? (uncertainty type)
- What's being optimized? (objective function)
- How precise? (qualitative vs quantitative)
Output Format
Framework Recommendation:
- Primary: [framework name]
- Why: [one-sentence justification]
Starting Point:
- Key equations: [relevant formulas]
- Initial approach: [first step]
Tools to Use:
- [specific script or computation tool]
Related Skills:
- [domain skill to activate next]
Example Interaction
User: I want to model how a rumor spreads through a population
Claude: Let me help you find the right framework.
Q1: What quantity are we tracking?
> Number of people who heard the rumor over time.
Q2: What causes it to change?
> Spread rate depends on who knows and who doesn't.
Q3: Is there randomness?
> Assume deterministic (average behavior) for now.
Q4: Optimizing anything?
> No, just understanding dynamics.
Q5: What precision?
> Qualitative behavior, maybe predict peak rate.
Framework Recommendation:
- Primary: First-order ODE (logistic growth)
- Why: Rate depends on current state nonlinearly
Starting Point:
- dN/dt = r * N * (1 - N/K)
- N = heard count, K = population, r = spread rate
Tools:
- sympy_compute.py solve (equilibrium)
- Phase line for qualitative behavior
Related Skills:
- math/math-intuition-builder (understand the model)
- odes-pdes/first-order-odes (solve it)
Co-activates
After framework selection, suggest:
- math-intuition-builder - to understand the framework
- Relevant domain skill - for actual computation
- math-mode - for symbolic verification
Related Skills
foryourhealth111-pixel/shap
development
VerifiedTrustedCommunity
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.
1,760SKILL.mdUpdated Apr 27, 2026
foryourhealth111-pixel/sentry
development
VerifiedTrustedCommunity
Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.
1,760SKILL.mdUpdated Apr 27, 2026
foryourhealth111-pixel/senior-prompt-engineer
development
VerifiedTrustedCommunity
World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Claude, GPT-4, prompt design patterns, few-shot learning, chain-of-thought, and AI evaluation. Includes RAG optimization, agent design, and LLM system architecture. Use when building AI products, optimizing LLM performance, designing agentic systems, or implementing advanced prompting techniques.
1,760SKILL.mdUpdated Apr 27, 2026
foryourhealth111-pixel/senior-ml-engineer
development
VerifiedTrustedCommunity
World-class ML engineering skill for productionizing ML models, MLOps, and building scalable ML systems. Expertise in PyTorch, TensorFlow, model deployment, feature stores, model monitoring, and ML infrastructure. Includes LLM integration, fine-tuning, RAG systems, and agentic AI. Use when deploying ML models, building ML platforms, implementing MLOps, or integrating LLMs into production systems.
1,760SKILL.mdUpdated Apr 27, 2026