Resume

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

Detect an incomplete LongMemEval run and continue it from the last checkpointFrom its SKILL.md

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.

SKILL.md

1.2 KB, 310 tokens by cl100k_base, 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.

What ships with it

Read from the repository

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

Gives 0 of the 12 instructions most hr recruiting skills give in 310 tokens

Counted across 356 of the 357 authors here whose files we hold, read 2026-08-07

Quantify achievements with specific metricsin 14 of 356, across 6 files
Keep the resume under two pagesin 14 of 356, across 6 files
Request the full job description if not providedin 12 of 356, across 4 files
Extract keywords and prioritize job requirementsin 12 of 356, across 4 files
Stop and ask for clarification if required inputs are missingin 12 of 356, across 5 files
Map candidate experience to job requirementsin 11 of 356, across 3 files
Ask if the user wants adjustmentsin 11 of 356, across 3 files
Provide strengths and gap analysis after the resumein 10 of 356, across 2 files
Request candidate background details if not providedin 10 of 356, across 2 files
Format experience bullets as action verb plus resultin 10 of 356, across 2 files
Ask for missing inputs before startingin 10 of 356, across 9 files
Use exact job description terminologyin 9 of 356, across 1 file

Said here and by no other author read

resolve the virtual environment
find incomplete runs
use provided run id if given
pick most recent incomplete run otherwise
rewrite run-meta.json with status completed
invoke report skill

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.