home / skills / zpankz / mcp-skillset / telos

telos skill

/telos

This skill analyzes physiological systems through teleological reasoning, revealing design constraints and optimized trade-offs to explain apparent

npx playbooks add skill zpankz/mcp-skillset --skill telos

Review the files below or copy the command above to add this skill to your agents.

Files (4)
SKILL.md
7.0 KB
---
name: telos
description: Teleological physiology analysis framework for understanding biological systems through multi-constraint optimization. Use when analyzing physiological mechanisms, explaining apparent biological "inefficiencies", preparing for medical examinations (CICM/ANZCA Primary), understanding why biological systems are designed the way they are, or when seeking deeper mechanistic understanding beyond descriptive knowledge. Triggers on questions like "why is X designed this way", "what purpose does Y serve", "how is Z optimized", analysis of physiological trade-offs, or exploration of evolutionary/design constraints.
---

# TELOS: Teleological Physiology Framework

## Core Principle

Analyze biological systems assuming superior designer intelligence. Apparent inefficiencies are puzzles requiring deeper investigation—elegant solutions often solve multiple problems with single mechanisms.

**Epistemological stance**: Teleological reasoning is a productive heuristic, not a metaphysical claim. It generates testable predictions about system design and reveals hidden constraints.

## Methodological Framework

### λτ.ο Pattern (Purpose → Terminal → Observation)

```
λτ.ο : Constraints × Design → Optimization
     where τ = teleological purpose
           ο = observed mechanism  
           λ = transformation revealing hidden design logic
```

Every analysis follows: **Purpose → Constraints → Optimization → Mechanism**

### Three-Level Hierarchical Analysis

| Level | Focus | Key Questions |
|-------|-------|---------------|
| **Strategic (τ)** | Purpose/function | What problem does this solve? What defines "optimal" here? |
| **Tactical (λ)** | Constraint mapping | What competing constraints exist? What alternatives were rejected? |
| **Operational (ο)** | Implementation | How is this achieved molecularly/cellularly? What quantitative optimizations? |

## Core Methodology

### 1. Constraint Mapping

Identify all constraints before seeking optimization:

**Physical**: Thermodynamics, kinetics, diffusion limits, mechanical forces
**Chemical**: pH, ionic strength, molecular compatibility, reaction rates
**Energetic**: ATP cost, metabolic efficiency, heat dissipation
**Spatial**: Size limits, packing constraints, anatomical boundaries
**Temporal**: Response times, developmental sequences, diurnal rhythms

See `references/constraint-taxonomy.md` for formal classification.

### 2. Oscillating Hierarchical Analysis

```
Atomic Principles
      ↓ zoom out
First Composites (combinations)
      ↓ zoom in
Reinforce Atomic Connections
      ↓ zoom out
Higher Composites (system integration)
      ↓ ... iterate
```

Each oscillation reveals connections and reinforces semantic depth. Build efficiently on prior layers.

### 3. Multi-Constraint Optimization Detection

When apparent "flaws" appear:
1. List all constraints the system must satisfy
2. Identify which constraints conflict
3. Analyze how the "flaw" resolves the conflict
4. Quantify the optimization across all dimensions
5. Consider alternative designs and why rejected

### 4. Convergence Validation

Optimization claims require:
- **Quantitative support**: Measurable efficiency gains
- **Comparative evidence**: Similar solutions in unrelated systems
- **Predictive power**: Explains otherwise mysterious features
- **Minimal configuration**: No simpler solution satisfies all constraints

## Analysis Template

```markdown
## [System Name] Teleological Analysis

### Strategic: Purpose Definition
- Primary function:
- Constraints defining "optimal":
- Success criteria:

### Tactical: Constraint Mapping
| Constraint Type | Specific Constraints | Trade-offs |
|-----------------|---------------------|------------|
| Physical        |                     |            |
| Chemical        |                     |            |
| Energetic       |                     |            |
| Spatial         |                     |            |
| Temporal        |                     |            |

### Operational: Implementation Analysis
- Molecular mechanisms:
- Quantitative optimizations:
- Integration points:

### Synthesis: Multi-Constraint Resolution
- How single mechanism solves multiple problems:
- Alternative designs considered:
- Why current design is minimal energy configuration:

### Validation
- Convergent evidence:
- Predictive implications:
- Falsifiable claims:
```

## Integration Points

### With quantitative-physiology
Leverage equations to validate optimization claims quantitatively:
- Stewart-Hamilton for cardiac output optimization
- Henderson-Hasselbalch for pH gradient analysis
- Nernst equation for membrane potential efficiency

### With hierarchical-reasoning
Map teleological levels to cognitive architecture:
- Strategic ↔ Purpose/function analysis
- Tactical ↔ Constraint identification
- Operational ↔ Mechanistic implementation

### With saq
Generate examination questions testing teleological understanding:
- Frame mechanisms within design context
- Test constraint awareness beyond fact recall

### With constraints skill
Formalize physiological constraints using:
- Deontic modalities (what is permitted/required given physics)
- Juarrero's trichotomy (enabling/governing/constitutive)

## Validation Rubrics

| Criterion | Weak | Moderate | Strong |
|-----------|------|----------|--------|
| Constraint mapping | 1-2 constraints | 3-4 constraints | 5+ constraints with interactions |
| Quantitative support | Qualitative only | Some numbers | Equation-backed |
| Alternative consideration | None | Mentioned | Analyzed why rejected |
| Predictive power | Descriptive | Explains known facts | Predicts unknown features |
| Convergence | Single example | Related systems | Phylogenetically independent |

See `references/validation-rubrics.md` for detailed scoring.

## Common Pitfalls

1. **Panglossian fallacy**: Assuming everything is optimal. Some features are historical accidents or vestigial.
2. **Single-constraint thinking**: Optimizing for one constraint while ignoring trade-offs.
3. **Post-hoc rationalization**: Inventing purposes without constraint evidence.
4. **Ignoring alternatives**: Not considering why other designs were "rejected."

## Quick Reference: Analysis Triggers

Apply teleological analysis when encountering:
- "Inefficient" or "wasteful" biological processes
- Anatomical arrangements that seem suboptimal
- Redundant or apparently unnecessary mechanisms
- Extreme precision in physiological values (e.g., pH 7.4)
- Convergent evolution across unrelated lineages

## Example Analyses

See `references/case-studies.md` for worked examples:
- Intracellular pH gradient (0.6 unit differential)
- Vertebrate retinal architecture ("inverted" design)
- Renal countercurrent multiplication
- Hemoglobin cooperativity

## Clinical Applications

Pathological states as constraint violations:
- Identify which design constraint is broken
- Predict compensatory mechanisms based on design logic
- Explain therapeutic targets via intended function
- Understand why some interventions fail (violate other constraints)

Overview

This skill is a teleological physiology analysis framework for explaining why biological systems are structured the way they are using multi-constraint optimization. It helps turn apparent inefficiencies into hypotheses about concealed design logic and testable optimization trade-offs. Use it to generate exam-style reasoning, mechanistic explanations, and quantitative checks on physiological function.

How this skill works

The skill inspects a target physiological feature by mapping purpose → constraints → optimization → mechanism. It enumerates physical, chemical, energetic, spatial and temporal constraints, tests competing solutions, quantifies trade-offs with relevant equations, and evaluates convergence and predictive power. Outputs include a structured analysis template, falsifiable claims, and suggestions for quantitative validation.

When to use it

  • When asked “why is X designed this way?” or “what purpose does Y serve?”
  • Analyzing apparent inefficiencies or redundant mechanisms
  • Preparing for physiology/medical exams that require mechanistic reasoning
  • Designing hypotheses that reconcile multiple constraints in a system
  • Interpreting pathological states as constraint violations

Best practices

  • Start by listing every relevant constraint before proposing purpose
  • Work across hierarchy levels: strategic (purpose), tactical (constraints), operational (mechanism)
  • Quantify claims where possible using physiology equations and comparative data
  • Consider alternative designs and explain why they were rejected
  • Avoid teleological overreach: distinguish testable heuristics from metaphysical claims

Example use cases

  • Explain why the vertebrate retina is inverted by mapping optical, metabolic and packing constraints
  • Analyze why hemoglobin exhibits cooperativity by weighing oxygen delivery, binding kinetics, and metabolic cost
  • Dissect renal countercurrent multiplication as an energy–gradient optimization under spatial and temporal limits
  • Prepare CICM/ANZCA Primary style answers that justify physiological 'inefficiencies' with constraint reasoning
  • Predict compensatory mechanisms in disease by identifying which design constraint is broken

FAQ

Is teleological reasoning proposing a designer?

No. The framework treats teleology as a heuristic to generate testable hypotheses about design logic, not a metaphysical claim.

How do I avoid inventing purposes post-hoc?

Require constraint mapping, quantitative support, alternative comparison, and predictive implications before accepting a teleological explanation.

What counts as strong validation?

Equation-backed quantitative gains, convergent evidence across unrelated systems, predictive power, and demonstration that no simpler design meets all constraints.