Kaggle

Audit a game environment's README.md and AGENTS.md against its engine implementation. Use when the user asks to "review", "audit", "check", or "fact-check" environment docs, when players report doc/engine discrepancies, or before a competition launch. Also…

Audit a game environment's README.md and AGENTS.md against its engine implementation (stale constants, unreachable caps, undocumented preconditions, wrong observation fields). Also use proactively after changing an environment engine that has sibling docs.…

Create or update an LLM harness that lets a language model play a kaggle-environments game. Use this skill whenever the user wants to write a harness, LLM agent, or game-playing prompt for any kaggle-environments game — including OpenSpiel games, word games,…

Review an existing LLM harness for correctness and gameplay-impacting bugs. Use when the user asks to "review", "audit", "check", "look over", or "find bugs in" a harness, or asks whether a harness has issues that could affect win rates. Covers static code…

Run a prompt-ablation study on a kaggle-environments game's LLM harness. Use when the user mentions "ablation", "prompt sensitivity", "test prompt variants", "compare prompts", "ablate the prompt", "prompt rewrite study", or asks whether their prompt wording…

Build a standalone interactive (human vs AI) visualizer for a Kaggle game environment by porting the engine and bundled agents to TypeScript and running them in a web worker. Use after create-visualizer.

Run a prompt-ablation study on a kaggle-environments game's LLM harness. Use when the user mentions "ablation", "prompt sensitivity", "test prompt variants", "compare prompts", "ablate the prompt", "prompt rewrite study", or asks whether their prompt wording…

Review an existing LLM harness for correctness and gameplay-impacting bugs (prompt accuracy, parser robustness, replay-archive scanning, cross-harness sweeps)

Steers Kaggle Hackathon hosts toward defensible LLM-assisted grading workflows collecting writeups and artifacts via the Kaggle MCP server, auditing with hamelsmu/evals-skills, and ranking submissions via pairwise comparisons / ELO with bell-curve…

Replace with description of the skill and when Claude should use it.

Register as an agent on Kaggle, take a standardized exam, and earn a score.

Write benchmark tasks to evaluate LLMs using the kaggle_benchmarks Python library. Covers task decorators, structured outputs, assertions, tools, dataset evaluation (including failure-tolerant retry patterns for large datasets), and multi-turn conversations.

Register as an agent on Kaggle, take a standardized exam, and earn a score.

Use the local Kaggle CLI skill for command guidance, workflows, and troubleshooting across competitions, datasets, kernels/notebooks, models, model variations and versions, inbox file uploads, forums/discussions, benchmarks, configuration, OAuth/API-token…

Build, run, and validate Kaggle benchmarks using Harbor.