---

name: aoc description: "Solve Advent of Code puzzles, algorithm challenges, and competitive programming problems. Activate when user provides AoC problem context/input, mentions solving puzzles/challenges, asks about algorithm selection (BFS, DFS, DP, etc.), or needs help with parsing structured input."

Advent of Code Solver

Language-agnostic problem-solving with TDD and correctness-first approach.

Workflow

Copy1. READ      → Study problem + examples (examples are your spec)
2. PARSE     → Extract data structures from input
3. TEST      → Write tests from example input/output
4. IMPLEMENT → Minimal code to pass
5. RUN       → Execute on real input
6. ADAPT     → Refactor for Part 2

Solution Architecture

Copyparse(input) → data structure
part1(data)  → answer
part2(data)  → answer

Parse once. Solve both parts. Test each function independently.

Algorithm Selection

Deep dive: See algorithms.md

Input Patterns

Grids: Use (row, col) with row↓. Sparse dict for infinite/sparse grids. Directions: UP=(-1,0), DOWN=(1,0), LEFT=(0,-1), RIGHT=(0,1)

Deep dive: See parsing.md

Part 2 Patterns

1. Scale up → Optimize algorithm
2. Add dimensions → 2D → 3D/4D
3. Many iterations → Find cycle, skip ahead
4. Reverse question → "Find X" → "Given X, find Y"
5. Add constraints → New rules or edge cases

Debugging

• Print intermediate state at each step
• Compare with example walkthrough
• Add assertions for every assumption
• Test parsing separately from logic
• Binary search on input size to isolate failures

Complexity Targets

Research Tools

Copy# gh search code for algorithm implementations
gh search code "heapq.heappush" --language=python   # Dijkstra/priority queue
gh search code "collections.deque" --language=python # BFS patterns
gh search code "fn dijkstra" --language=rust

References

• algorithms.md - Graph traversal, DP, cycle detection, search
• parsing.md - Input formats, grids, coordinates, hex grids
• reference.md - Data structures, optimization, anti-patterns