メニュー
Run, monitor, and troubleshoot a benchmark execution. Use when executing benchmarks, checking results, debugging failed runs, or comparing agent performance.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Plan and execute code changes using a spec-driven workflow with structured documents. Use when making non-trivial changes (multi-file, multi-step, or behavior-impacting) that need structured planning before implementation. Not for trivial single-file edits.
Create and manage changesets for versioning with @changesets/cli. Use when making changes that need a changelog entry, preparing a release, or managing package versions.
Diagnose and fix failed benchmark runs. Use when a benchmark run fails, scores are unexpected, judges show errors, or traces are incomplete.
Build the pnpm monorepo correctly respecting inter-package dependencies. Use when building, verifying changes, or troubleshooting build failures.
Write and run tests using Node.js built-in test runner (node:test) with .mjs files. Use when creating new tests, debugging test failures, or understanding test infrastructure.
Understand the vanilla JS web-report app structure, patterns, and contribution guidelines. Use when modifying the UI, adding new views, or fixing frontend bugs.
| name | benchmark-run |
| description | Run, monitor, and troubleshoot a benchmark execution. Use when executing benchmarks, checking results, debugging failed runs, or comparing agent performance. |
Execute and troubleshoot benchmark runs.
pnpm build — 0 errors.pnpm test — 0 failures.agentarena doctor — target agents are available.agentarena run --repo <path> --task <task.yaml> --agents <agent1,agent2,...> [options]
| Option | Values | Purpose |
|---|---|---|
--score-mode | practical, balanced, issue-resolution, efficiency-first, rotating-tasks, comprehensive | Scoring weight preset |
--token-budget | number | Token budget limit for efficiency scoring |
--max-concurrency | number | Parallel agent execution |
--output | path | Custom output directory |
--json | flag | Output results as JSON to stdout |
Results land in .agentarena/runs/<run-id>/:
| File | Content |
|---|---|
summary.json | Full benchmark results |
report.html | Interactive web report |
decision-report.md | Decision recommendation |
| Symptom | Likely Cause |
|---|---|
| Agent status "missing" | CLI not installed or not in PATH |
| Judge fails | Wrong command, missing deps, or timeout |
| Score is 0 | Agent run failed or all critical judges failed |
| Token usage is 0 | Agent adapter doesn't report token usage |