Setup & Installation
openclaw skills install @christianhaberl/boggle
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install boggle
What This Skill Does
Solves 4x4 Boggle boards by finding all valid words across English and German dictionaries (359K and 1.35M words respectively). Uses a trie-based DFS algorithm with dictionary-only matching, no AI guessing. Works from a photo of a board or typed letters.
Dictionary-only validation guarantees no hallucinated words, unlike LLM-based solvers that can return words that don't exist in any dictionary.
When to use it
- Finding every valid word on a physical Boggle board from a photo
- Maximizing score by identifying long, high-value words before time runs out
- Playing bilingual Boggle with English and German results side by side
- Settling disputes about whether a word is reachable on a specific grid
- Practicing vocabulary by seeing all valid words on a given layout
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: here's a photo of my Boggle board, what words can I find?
AGENT
- 1Read the 4x4 letter grid from the photo left-to-right, top-to-bottom
- 2Display the interpreted grid and ask the user to confirm it is correct
- 3Run the solver for English: python3 skills/boggle/scripts/solve.py ... --lang en
- 4Run the solver for German: python3 skills/boggle/scripts/solve.py ... --lang de
- 5Present results as two labeled sections grouped by word length and score
OUTPUT
Two labeled word lists (English / German) with all valid words found and their point values