菜单
Use when the user asks to "test TPC-H", "check compliance", "review architecture", "run quality checks", "check binaries", "test dialect translation", "compare implementations", "run live platform tests", or "plan and execute" a benchmark feature.
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
Shared protocol for review-shaped actions, authorization scope, defect routing, L2 audit handling, and local-only capture.
Use for "commit code", "review code", "fix lint/type error", "improve performance", "compare code", "shrink code", "generate spec from code", "investigate code", "debug an error", "triage a bug", "iterate to green", or "create handoff prompt".
Use when the user asks to "create documentation", "build docs", "review docs", "compare documents", "compress docs", "adversarial review docs", or "commit docs".
Use when the user asks to "sync skills", "set up skill-sync", "check skill status", "validate skills", "preview skill changes", "diagnose skills", "pin a skill", "unpin a skill", "prune skills", or "promote skill changes".
Use when the user asks to "run tests", "create tests", "fix failing test", "add test coverage", "fix slow tests", or "commit test changes".
Consolidate accumulated permission grants across Claude Code, Codex, and Gemini: move trusted commands into project settings, clean garbage entries, verify cross-agent consistency, commit project-level configs.
| name | benchbox-workflow |
| description | Use when the user asks to "test TPC-H", "check compliance", "review architecture", "run quality checks", "check binaries", "test dialect translation", "compare implementations", "run live platform tests", or "plan and execute" a benchmark feature. |
| version | 0.2.0 |
| tools | Bash, Read, Write, Edit, Glob, Grep, Task |
Route benchmark, platform, quality, and architecture work to one action. Before acting, read the file in the Read column for the selected action. Auto- detect the runner, honor non-interactive mode, and produce human plus JSON/file artifacts when supported.
| Action | Read |
|---|---|
test | references/test.md |
quality | references/quality.md |
compliance | references/compliance.md |
dialect | references/dialect.md |
binary | references/binary.md |
compare | references/compare.md |
live | references/live.md |
architecture | references/architecture.md |
plan | references/plan.md |
Aliases remain accepted: benchmark-test, quality-check, qa,
tpc-compliance, dialect-translation, sql, binary-check, binaries,
compare-impl, live-test, platform-test, arch, arch-review,
plan-execute, and implement.
uv run -- for Python; Makefile wrappers are fine.--phases: generate, load, power, throughput,
and maintenance. Default smoke scale is 0.01; scale >=1 is a whole
integer.benchbox.utils.clock.mono_time() / elapsed_seconds() for durations.benchbox/sql_compat/rules/ddl_optimize/.docs/operations/uat-framework.md.Report commands, pass/fail, artifacts, key findings, and next steps. For failures include a root-cause hypothesis and the narrowest next check.