菜单
Profile offline OpenClaw skill run samples to detect latency, CPU, and memory bottlenecks and compare sessions.
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。
Generate safer OpenClaw configuration baselines and audit existing config files for exposure, missing controls, and secret hygiene issues.
clean fixture
malicious fixture
Scan OpenClaw skill directories for high-signal security risks such as download-and-execute chains, obfuscated execution, and suspicious callbacks.
Calculate OpenClaw usage cost from offline event logs, apply budget thresholds, and export operator-facing reports.
avoid fixture
基于 SOC 职业分类
| name | skill-profiler |
| description | Profile offline OpenClaw skill run samples to detect latency, CPU, and memory bottlenecks and compare sessions. |
| homepage | https://github.com/mike007jd/openclaw-skills/tree/main/skill-profiler |
| metadata | {"openclaw":{"emoji":"📈","requires":{"bins":["node"]}}} |
Analyze offline sample sets and surface the slowest or heaviest skills before they become production regressions.
latencyMs, cpuMs, and memoryMb.node {baseDir}/bin/skill-profiler.js run --input ./samples.json
node {baseDir}/bin/skill-profiler.js report --input ./samples.json --out ./report.html
node {baseDir}/bin/skill-profiler.js compare --left ./v1.json --right ./v2.json
[
{
"sessionId": "s1",
"skill": "clawshield",
"latencyMs": 1320,
"cpuMs": 910,
"memoryMb": 240
}
]