agentsclimarketplace

Source command verify and submit

Skill Erlemar/cayley-puzzles/.agents/skills/source-command-verify-and-submit

Verify an already-built submission CSV then submit to Kaggle.From its SKILL.md

Install
npx -y skills add Erlemar/cayley-puzzles --skill source-command-verify-and-submit

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.2 KB, 549 tokens by cl100k_base, as published. Nobody here has run it

source-command-verify-and-submit

Use this skill when the user asks to run the migrated source command verify-and-submit.

Command Template

/verify-and-submit

Thin submit path: skip the combine/post-process pipeline, just verify a pre-built CSV and submit it to Kaggle. Use this when you already have a finalized submission CSV (e.g., from combine_submissions + post_process ran earlier, or a single-shot solve output that's already PP'd).

Usage

  • /verify-and-submit <csv_path> <description> — verify then submit.
  • /verify-and-submit <csv_path> --force <description> — submit even if verify reports any invalid paths (rarely needed; usually a verify failure = silent 999999 score).

Execution

  1. Confirm the CSV exists. Abort with a clear message if not.

  2. Run verification:

    .venv/Scripts/python.exe -c "
    from pathlib import Path
    import sys
    sys.path.insert(0, 'src')
    from cayley.puzzle import PictureCube
    from cayley.verify import verify_submission
    puzzle = PictureCube.load('data/puzzle_info.json')
    r = verify_submission(puzzle, 'data/test.csv', '<csv_path>')
    print(f'verify: {r.n_valid}/{r.n_total} valid, total_moves={r.total_moves}, all_valid={r.all_valid}')
    sys.exit(0 if r.all_valid else 1)
    "
    
  3. Report the total_moves count and verification status.

  4. If verify failed and --force not set, abort. Otherwise, ask user to confirm submission.

  5. Submit:

    export KAGGLE_API_TOKEN=$KAGGLE_API_TOKEN
    .venv/Scripts/kaggle.exe competitions submit -c cayleypy-ihes-cube -f <csv_path> -m "<description>"
    
  6. Check status:

    .venv/Scripts/kaggle.exe competitions submissions cayleypy-ihes-cube | head -3
    

Gotchas

  • A typo in a generator name returns SubmissionStatus.COMPLETE with score 999999 (silent failure). Verification catches this before submission.
  • The user policy (as of 2026-04-20): do NOT submit community-merged CSVs; only submit our own work. Check the CSV's provenance before running if unsure.
  • This command is for pre-built CSVs only. If you need to combine candidates + post-process first, use /submit instead.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,851. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.