all publishers

kaggle

@kaggle source repo

23 published skills

  1. ▌
    Kaggle Harbor Benchmark 2 · kaggle
    Build, run, and validate Kaggle benchmarks using Harbor.
    459 repo stars
  2. ▌
    Kaggle CLI 2 · kaggle bundle
    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 authentication, and accelerator quota. Activate this skill when the user asks about kaggle CLI commands, examples, flags, metadata files, download/upload flows, submissions, benchmark tasks, or Kaggle CLI behavior.
    459 repo stars
  3. ▌
    Review Docs 2 · kaggle
    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. The engine is the source of truth.
    459 repo stars
  4. ▌
    Run Ablation 2 · kaggle
    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 is doing real work. Bootstraps a prompt_variants.py if missing, proposes new variants interactively, then runs a paired-seat tournament and reports the leaderboards.
    459 repo stars
  5. ▌
    Create Harness 2 · kaggle
    Create or update an LLM harness that connects a language model to a kaggle-environments game (prompt generation, response parsing, and tests)
    459 repo stars
  6. ▌
    Review Harness 2 · kaggle
    Review an existing LLM harness for correctness and gameplay-impacting bugs (prompt accuracy, parser robustness, replay-archive scanning, cross-harness sweeps)
    459 repo stars
  7. ▌
    Create Visualizer 2 · kaggle
    Create or update a web visualizer for a Kaggle game environment (Vite + TypeScript frontend with replay playback)
    459 repo stars
  8. ▌
    Create Environment 2 · kaggle
    Create or update a Kaggle game environment (Python backend with specification, interpreter, renderer, agents, and tests)
    459 repo stars
  9. ▌
    Onboard Open Spiel Game 2 · kaggle
    Onboard a new OpenSpiel game into kaggle-environments, including optional proxy, visualizer, and transformer
    459 repo stars
  10. ▌
    Create Playable Visualizer 2 · kaggle
    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.
    459 repo stars
  11. ▌
    Kaggle Harbor Benchmark · kaggle
    Build, run, and validate Kaggle benchmarks using Harbor.
    459 repo stars
  12. ▌
    Kaggle CLI · kaggle bundle
    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 authentication, and accelerator quota. Activate this skill when the user asks about kaggle CLI commands, examples, flags, metadata files, download/upload flows, submissions, benchmark tasks, or Kaggle CLI behavior.
    459 repo stars
  13. ▌
    Hackathon Judging · kaggle bundle
    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 adjustments. Use when a host wants to grade a public Kaggle Hackathon with help from LLMs or AI agents.
    459 repo stars
  14. ▌
    Write Kaggle Benchmarks · kaggle bundle
    Write, push, run, publish, and manage Kaggle Benchmark tasks using the kaggle CLI and the kaggle-benchmarks Python SDK. Use when the user wants to create or push a benchmark task (optionally with attached Kaggle datasets), run benchmarks against LLM models, check task/run status, stream or fetch execution logs, download results and source notebooks, publish a task to make it public, or troubleshoot benchmark workflows.
    459 repo stars
  15. ▌
    Kaggle Standardized Agent Exam · kaggle bundle
    Register as an agent on Kaggle, take a standardized exam, and earn a score.
    459 repo stars
  16. ▌
    Review Docs · 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 use proactively after changing an environment's engine (`kaggle_environments/envs/<game>/<game>.py`) when a sibling README.md or AGENTS.md exists — rebalances and mechanic changes routinely leave those docs stale. The engine is always the source of truth — docs get fixed, not the engine.
    459 repo stars
  17. ▌
    Run Ablation · kaggle bundle
    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 is doing real work. Bootstraps a prompt_variants.py if missing, proposes new variants interactively, then runs a paired-seat tournament and reports the leaderboards.
    459 repo stars
  18. ▌
    Create Harness · kaggle
    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, or custom environments. Also use it when the user mentions core_harness.py, GameHarness, ParseResult, or asks how to connect an LLM to a game.
    459 repo stars
  19. ▌
    Review Harness · kaggle
    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 review (prompt accuracy, parser robustness, common anti-patterns), optional replay-archive scanning to quantify real-world impact, and an optional cross-harness sweep for the same anti-patterns.
    459 repo stars
  20. ▌
    Create Visualizer · kaggle bundle
    Create / Update a Visualizer
    459 repo stars
  21. ▌
    Create Environment · kaggle
    Create / Update an Environment
    459 repo stars
  22. ▌
    Onboard Open Spiel Game · kaggle
    Onboard a New OpenSpiel Game
    459 repo stars
  23. ▌
    Create Playable Visualizer · kaggle
    Create a Playable Visualizer
    459 repo stars