OpenClaw Blackbox
OpenClaw Blackbox CLI — inspect failed, stalled, expensive, or weird OpenClaw agent runs from local disk evidence; list sessions and failures; find the sessi...
End-to-end MailPilot smoke test against real Gmail across outbound@lab5.ca and inbound@lab5.ca. One Phase 0 setup → 2 scenarios run sequentially without state reset. Scenario A = outbound workflow + manual operator reply. Scenario B = live KB-grounded inbound auto-reply demo at https://lab5.ca/demo/ (real Drive folder, in-scope grounded reply + out-of-scope polite decline). Outbound workflow stays active across B → verifies concurrent multi-account, multi-workflow operation. Both scenarios mandatory. Use whenever user says "smoke test", "run end-to-end", "verify the system works", or after non-trivial changes to sync, routing, agent execution, KB grounding, or Pub/Sub code -- even without explicit invocation.
This listing is imported from SkillsMP metadata and should be treated as untrusted until upstream source review is completed.
Install skill "smoke-test" with this command: npx skills add kborovik/skillsmp-kborovik-kborovik-smoke-test
This source entry does not include full markdown content beyond metadata.
This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.
Related by shared tags or category signals.
OpenClaw Blackbox CLI — inspect failed, stalled, expensive, or weird OpenClaw agent runs from local disk evidence; list sessions and failures; find the sessi...
通过 page-agent CLI(CDP)驱动浏览器;CLI 当前仅从 GitHub Release 的 .tgz 安装(npm 官方包尚未发布)。
Desktop automation via native OS accessibility trees using the agent-desktop CLI. Use when an AI agent needs to observe, interact with, or automate desktop a...
输入文章 URL **或本地文档(PDF/DOCX/PPTX/XLSX/EPUB/图片/音频/...)**,自动提取正文、可选 AI 改写、并发布到微信公众号;也可只把任意文档转成 Markdown 文本(不发布)。抓取 / 转换 / 改写 / 发布都在服务端 (tools.siping.me) 完成,CLI 不...