菜单
Run repo health checks, validate benchmark tasks, and audit run integrity.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Archive old completed benchmark runs to save disk space and speed up scans. Triggers on archive runs, clean up runs, disk space, old runs.
Audit benchmark suites against ABC framework (Task/Outcome/Reporting validity). Checks instruction quality, verifier correctness, reproducibility. Triggers on benchmark audit, audit benchmark, abc audit, task validity.
Verify infrastructure readiness before launching benchmark runs — tokens, Docker, disk, credentials. Triggers on check infra, infrastructure check, ready to run, pre-run check.
Compare benchmark results across agent configurations (baseline, SG_full). Show where configs diverge. Triggers on compare configs, config comparison, which config wins, MCP impact.
Token and cost analysis per run, suite, and config. Shows most expensive tasks and config cost comparison. Triggers on cost report, how much did it cost, token usage, spending.
Generate the aggregate CSB evaluation report from completed Harbor runs. Triggers on generate report, eval report, ccb report, benchmark report.
| name | audit |
| description | Run repo health checks, validate benchmark tasks, and audit run integrity. |
Use this skill when the user asks to:
# Full repo health gate
python3 scripts/maintenance/repo_health.py
# Quick health (docs + selection file only)
python3 scripts/maintenance/repo_health.py --quick
# Validate all tasks
python3 scripts/authoring/validate_tasks_preflight.py --all
# Validate specific task
python3 scripts/authoring/validate_tasks_preflight.py --task benchmarks/csb/debug/task-name
# Post-run task validation
python3 scripts/authoring/validate_task_run.py runs/staging/run_dir/task_id
# Audit canonical evaluation contract
python3 scripts/evaluation/audit_canonical_evaluation_contract.py
/run — execute benchmarks that will be audited/report — compile audit findings into reports