By cameronfreer
Automate Lean 4 theorem proving: draft skeletons from PDFs/claims/URLs, iteratively fill sorries and repair errors, refactor with mathlib lemmas, optimize for brevity/performance, review proof quality, checkpoint git commits after verification, run diagnostics, and explore/learn interactively.
npx claudepluginhub cameronfreer/lean4-skills --plugin lean4Autonomous end-to-end formalization from informal sources
Autonomous multi-cycle theorem proving with hard stop rules
Save progress with a safe commit checkpoint
Diagnostics, cleanup, and migration help
Draft Lean declaration skeletons from informal claims
Interactive formalization — drafting plus guided proving
Improve Lean proofs for directness, clarity, performance, and brevity
Interactive teaching and mathlib exploration
Guided cycle-by-cycle theorem proving with explicit checkpoints
Leverage mathlib, extract helpers, simplify proof strategies
Read-only code review of Lean proofs
Remove nonconstructive axioms by refactoring proofs to structure (kernels, measurability, etc.). Use after checking axiom hygiene to systematically eliminate custom axioms.
Golf Lean 4 proofs after they compile; improve proofs for directness, clarity, performance, and brevity without changing semantics. Use after successful compilation to achieve 30-40% size reduction.
Compiler-guided iterative proof repair with two-stage repair escalation (fast → strong). Use for error-driven proof fixing with small sampling budgets (K=1).
Strategic resolution of stubborn sorries; may refactor across files within the header fence. Use when fast pass fails or for complex proofs.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Executes bash commands
Hook triggers when Bash tool is used
Uses power tools
Uses Bash, Write, or Edit tools
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Intelligent prompt optimization using skill-based architecture. Enriches vague prompts with research-based clarifying questions before Claude Code executes them
Persistent memory system for Claude Code - seamlessly preserve context across sessions
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.