natural-transformations
Problem-solving strategies for natural transformations in category theory
Best use case
natural-transformations is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Problem-solving strategies for natural transformations in category theory
Teams using natural-transformations should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/natural-transformations/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How natural-transformations Compares
| Feature / Agent | natural-transformations | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Problem-solving strategies for natural transformations in category theory
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Natural Transformations
## When to Use
Use this skill when working on natural-transformations problems in category theory.
## Decision Tree
1. **Verify Naturality**
- eta: F => G is natural transformation between functors F, G: C -> D
- For each f: A -> B in C, diagram commutes:
G(f) . eta_A = eta_B . F(f)
- Write Lean 4: `theorem nat : η.app B ≫ G.map f = F.map f ≫ η.app A := η.naturality`
2. **Component Analysis**
- eta_A: F(A) -> G(A) for each object A
- Each component is morphism in target category D
- Lean 4: `def η : F ⟶ G where app := fun X => ...`
3. **Natural Isomorphism**
- Each component eta_A is isomorphism
- Functors F and G are naturally isomorphic
- Notation: F ≅ G (NatIso in Mathlib)
4. **Functor Category**
- [C, D] has functors as objects
- Natural transformations as morphisms
- Vertical composition: Lean 4 `CategoryTheory.NatTrans.vcomp`
- Horizontal composition: `CategoryTheory.NatTrans.hcomp`
5. **Yoneda Lemma Application**
- Nat(Hom(A, -), F) ~ F(A) naturally in A
- Lean 4: `CategoryTheory.yonedaEquiv`
- Fully embeds C into [C^op, Set]
- See: `.claude/skills/lean4-nat-trans/SKILL.md` for exact syntax
## Tool Commands
### Lean4_Naturality
```bash
# Lean 4: theorem nat : η.app B ≫ G.map f = F.map f ≫ η.app A := η.naturality
```
### Lean4_Nat_Trans
```bash
# Lean 4: def η : F ⟶ G where app := fun X => component_X
```
### Lean4_Yoneda
```bash
# Lean 4: CategoryTheory.yonedaEquiv -- Yoneda lemma
```
### Lean4_Build
```bash
lake build # Compiler-in-the-loop verification
```
## Cognitive Tools Reference
See `.claude/skills/math-mode/SKILL.md` for full tool documentation.Related Skills
workflow-router
Goal-based workflow orchestration - routes tasks to specialist agents based on user goals
wiring
Wiring Verification
websocket-patterns
Connection management, room patterns, reconnection strategies, message buffering, and binary protocol design.
visual-verdict
Screenshot comparison QA for frontend development. Takes a screenshot of the current implementation, scores it across multiple visual dimensions, and returns a structured PASS/REVISE/FAIL verdict with concrete fixes. Use when implementing UI from a design reference or verifying visual correctness.
verification-loop
Comprehensive verification system covering build, types, lint, tests, security, and diff review before a PR.
vector-db-patterns
Embedding strategies, ANN algorithms, hybrid search, RAG chunking strategies, and reranking for semantic search and retrieval.
variant-analysis
Find similar vulnerabilities across a codebase after discovering one instance. Uses pattern matching, AST search, Semgrep/CodeQL queries, and manual tracing to propagate findings. Adapted from Trail of Bits. Use after finding a bug to check if the same pattern exists elsewhere.
validate-agent
Validation agent that validates plan tech choices against current best practices
tracing-patterns
OpenTelemetry setup, span context propagation, sampling strategies, Jaeger queries
tour
Friendly onboarding tour of Claude Code capabilities for users asking what it can do.
tldr-stats
Show full session token usage, costs, TLDR savings, and hook activity
tldr-router
Map code questions to the optimal tldr command by detecting intent and routing to the right analysis layer.