Resume

Skill tmuskal/arc-agi-benchmarker/plugins/longmemeval-benchmarker/skills/resume

Prove you achieved AGI at home by testing your claude-code setup against arc-agi-3 benchmarks

Install

npx -y skills add tmuskal/arc-agi-benchmarker --skill resume

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.
3 stars3 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.

What its author says it does

Copied from the file, not written here

Detect an incomplete LongMemEval run and continue it from the last checkpoint

SKILL.md

1.2 KB, as published. Nobody here has run it

LongMemEval Resume

Step 1: Resolve venv.

Step 2: Find the most recent incomplete run

$VENV_PYTHON -c "
import json
from pathlib import Path
d = Path('.longmemeval-benchmarks/runs')
incomplete = []
for r in sorted(d.iterdir(), key=lambda p: p.stat().st_mtime, reverse=True):
    meta_path = r / 'run-meta.json'
    if not meta_path.exists(): continue
    meta = json.load(open(meta_path))
    if meta.get('status') != 'completed':
        incomplete.append((r.name, meta.get('status'), meta.get('datasetVariant')))
for name, st, v in incomplete[:5]:
    print(f'{name}  status={st}  variant={v}')
"

Step 3: Pick target run

If args include a <run_id>, use that. Else pick the most recent incomplete run.

Step 4: Continue

Invoke the run-benchmark skill with --run-id <runId>. The checkpoint loader filters out question_ids already present in questions_completed.jsonl, so execution picks up where it left off. The maxEvals cap applies to the REMAINING items in the cap, not the already-done ones.

Step 5: Finalize

Once finished, rewrite run-meta.json with status=completed and invoke the report skill.