Agent Skills by Tal Muskal
Showing 13 vetted skills indexed across 1 GitHub repositories.
tmuskallongmemeval-resume
Resume incomplete LongMemEval benchmark runs from the last checkpoint.
tmuskalsetup
Set up the LongMemEval benchmarking environment with conda and HuggingFace datasets.
tmuskalcross-harness
Automate LongMemEval benchmarking across Codex, Gemini, and OpenCode harnesses.
tmuskalcompare-runs
Compare two LongMemEval runs by scorecards, harness configurations, and per-question-type accuracy.
tmuskalLongMemEval Judge
Evaluate QA answers in the LongMemEval benchmark using Anthropic or OpenAI services.
tmuskalreport
Generate LongMemEval benchmark reports in markdown, JSON, or summary formats.
tmuskalbrowse-tests
Browse and preview LongMemEval dataset items by question ID.
tmuskalrun-benchmark
Automate LongMemEval benchmark execution with hypothesis generation and scoring.
tmuskalarc-agi-benchmarker-setup
Install Python, create a virtual environment, and verify the ARC-AGI package setup.
tmuskalarc-cross-harness
Generate cross-harness benchmarking instructions for ARC-AGI and compare results.
tmuskalarc-agi-benchmarker:report
Generate detailed ARC-AGI benchmark reports with score breakdowns and completion metrics.
tmuskalarc-agi-browse-tests
Browse ARC-AGI environments with game details and historical scores.
tmuskalbenchmark-adder
Automate Claude Code plugin creation for benchmarking setups from a repository URL.