$ loading_
用于执行 Kova/OpenClaw 验证、基准测试、发布门禁与性能报告生成
复制安装指令，让 AI 自动完成配置 · 推荐新手
请帮我安装 askskill 上的 "kova-operator" 技能： 1. 下载 https://raw.githubusercontent.com/openclaw/Kova/main/.agents/skills/kova-operator/SKILL.md 2. 保存为 ~/.claude/skills/kova-operator/SKILL.md 3. 装好后重载技能，告诉我可以用了
请对当前 Kova/OpenClaw 版本执行完整发布前验证：运行核心场景、检查基准测试结果、判断是否满足 release gate，并输出结论与风险摘要。
一份发布验证结果，包含通过/失败结论、关键指标、风险项与是否建议发布。
比较最近两次 Kova/OpenClaw 基准测试结果，找出性能回归项，按影响程度排序，并说明可能原因。
一份性能回归报告，列出变慢指标、影响范围、排序结果及原因分析。
汇总本轮 Kova/OpenClaw 场景测试执行情况，统计通过率、失败场景、异常日志，并生成适合团队同步的简报。
一份场景测试摘要，包含通过率、失败明细、异常概览和可分享的简报内容。
Use Kova to test OpenClaw as users actually run it. Kova is not a unit-test runner and not an OCM test suite. OCM is the lab control plane; OpenClaw is the product under test.
Kova should produce evidence a maintainer can act on:
Do not overstate causality. If OpenClaw did not emit enough diagnostic spans, say Kova proved the outside-in timing but internal attribution is missing.
command -v kova || true
test -f bin/kova.mjs && node bin/kova.mjs version
Use kova when installed. Inside a Kova checkout, use:
node bin/kova.mjs <command>
command -v ocm
ocm env list
ocm runtime list
If the ocm-operator skill is available, use it before running Kova scenarios
that build runtimes, clone existing user envs, inspect services/logs, or clean
up envs.
kova setup
kova self-check
For scripts/CI:
kova setup --ci --json
kova self-check --json
If using the repo checkout, replace kova with node bin/kova.mjs.
Kova real execution requires OCM. If OCM is missing, install it before running benchmarks:
command -v ocm || curl -fsSL https://raw.githubusercontent.com/shakkernerd/ocm/main/install.sh | bash
export PATH="$HOME/.local/bin:$PATH"
ocm --version
ocm env list
ocm runtime list
If installing Kova from its installer, OCM can be installed or required there:
curl -fsSL https://raw.githubusercontent.com/shakkernerd/Kova/main/install.sh | bash -s -- --install-ocm --require-ocm
For Codex agents working from this repo, use the repo-local OCM operating skill
at .agents/skills/ocm-operator when direct OCM operations are needed.
local-build:<repo> for release-like validation of local OpenClaw
source.--execute only when a real run is intended.When the user asks to benchmark OpenClaw, first decide which OpenClaw source is under test:
../openclaw, use it only after
confirming the path and commit./tmp, not inside Kova:repo="/tmp/kova-openclaw-$(date +%Y%m%d%H%M%S)"
git clone https://github.com/openclaw/openclaw.git "$repo"
git -C "$repo" checkout main
git -C "$repo" pull --ff-only
Before benchmarking a checkout, record:
git -C "$repo" status --short
git -C "$repo" rev-parse --abbrev-ref HEAD
git -C "$repo" rev-parse --short HEAD
git -C "$repo" log -1 --format='%h %ci %s'
Do not mutate a user working tree unless the user asked for that. For
benchmarking moving targets, prefer disposable clones or worktrees under
/tmp/kova-openclaw-*.
Use release-shaped Kova targets for local source:
…
帮助你在 Discord 中收发消息、管理频道互动并自动化协作流程