Skip to content
lean-proof-walk logo

Lean Proof Walk

lean-proof-walk

GF(3)-balanced random walk through Lean proof states. Use when generating formal proof chains with parallel triad verification. Invokes 3 agents (Generator +1, Coordinator 0, Validator -1) to traverse proof space via prime geodesics.

SKILL.md

Full skill instructions

Lean Proof Walk

Generate formal Lean 4 proof state chains using GF(3)-balanced random walks.

Triad Structure

AgentTritRoleAction
Generator+1CreatePropose next proof state
Coordinator0TransportFormalize transition, derive seed
Validator-1VerifyCheck soundness, GF(3) conservation

Invariant: trit(G) + trit(C) + trit(V) = (+1) + 0 + (-1) = 0

State Chain Format

State N: Γ ⊢ G

where:
  Γ = context (hypotheses: x : τ, h : P)
  ⊢ = turnstile (entailment)
  G = goal (proposition to prove)

Example Chain

State 0: a : ℤ, b : ℤ, h : a + b = 0 ⊢ b = -a

State 1: a : ℤ, b : ℤ, h : a + b = 0 ⊢ a + b - a = 0 - a

State 2: a : ℤ, b : ℤ, h : a + b = 0 ⊢ b = -a

State 3: No Goals

Protocol

1. Initialize

seed := 0x42D (or user-provided)
state := State 0 with full context and goal
triad := spawn 3 parallel agents with trits {-1, 0, +1}

2. Walk Step (repeat until No Goals)

Generator (+1):  propose tactic τ, predict State n+1
Coordinator (0): formalize Γₙ ⊢ Gₙ  →  Γₙ₊₁ ⊢ Gₙ₊₁
Validator (-1):  verify transition sound, Σ trits = 0
Commit:          seed_{n+1} = hash(seed_n ⊕ state_n)

3. Terminate

State m = "No Goals" → QED
Emit: formal statement, informal proof, detailed proof, state chain

Invocation

/​lean-proof-walk "∀ a b : ℤ, a + b = b + a"
/​lean-proof-walk --seed=1069 --theorem="commutativity of addition"

Output Structure

  1. Formal Statement (Lean 4 syntax)
  2. Informal Proof (1-2 sentences)
  3. Detailed Informal Proof (numbered steps)
  4. Chain of States (with interleaved explanations)

Tactics Vocabulary

TacticState Transition
intro xΓ ⊢ ∀x.P → Γ, x:τ ⊢ P
apply hΓ, h:P→Q ⊢ Q → Γ ⊢ P
exact hΓ, h:P ⊢ P → No Goals
rflΓ ⊢ a = a → No Goals
simpΓ ⊢ P → Γ ⊢ P' (simplified)
ringΓ ⊢ polynomial_eq → No Goals
omegaΓ ⊢ linear_arith → No Goals
cases hΓ, h:P∨Q ⊢ R → Γ, h:P ⊢ R and Γ, h:Q ⊢ R
induction nΓ ⊢ P(n) → base case + inductive step

GF(3) Seed Derivation

γ = 0x9E3779B97F4A7C15  # golden ratio constant

def next_seed(seed, state_hash, trit):
    return (seed ^ (state_hash * γ) ^ trit) & ((1 << 64) - 1)

Bundled Triad Skills

lean-proof-walk (0) ⊗ bdd-mathematical-verification (+1) ⊗ chromatic-walk (-1) = 0 ✓

Quick Reference

⟦State n⟧ = (Γₙ, Gₙ)
⟦S → S'⟧ = tactic application
⟦No Goals⟧ = proof complete
⟦Σ trits⟧ ≡ 0 (mod 3) always

More Other skills

Delegate independent tasks to specialized agents working concurrently with isolated context.

295.4K 206.3K
View

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

179.7K 100.1K
View

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

179.7K 89.5K
View

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

179.7K 76.1K
View

Fundamental design principles for writing maintainable, testable Python code.

40.2K 21.9K
View

Modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first strategies.

40.2K 20K
View

Generate Playwright tests from scenarios using interactive browser exploration and validation.

39.7K 18.2K
View

Modern React state management with Redux Toolkit, Zustand, Jotai, and React Query for every state category.

40.2K 14.7K
View

GDPR-compliant data handling with consent management, data subject rights, and privacy controls.

40.2K 14.3K
View

Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.

40.2K 13.5K
View

Detailed multi-file refactor planning with safety checks and rollback guidance.

39.7K 13K
View