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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/openclaw/openclaw --skill channel-message-flows命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | channel-message-flows |
| description | Use when running QA Lab channel message flow evidence. |
Use this from the OpenClaw repo root to run the QA Lab evidence for Telegram draft/final delivery sequencing. The behavior is owned by one transport-native QA flow that can run through QA Channel or Crabline Telegram.
Run the scenario through QA Lab:
OPENCLAW_BUILD_PRIVATE_QA=1 node scripts/run-node.mjs qa suite \
--provider-mode mock-openai \
--scenario channel-message-flows \
--channel-driver qa-channel
Run the same YAML through the real Telegram plugin against Crabline's local provider server:
OPENCLAW_BUILD_PRIVATE_QA=1 node scripts/run-node.mjs qa suite \
--provider-mode mock-openai \
--scenario channel-message-flows \
--channel-driver crabline \
--channel telegram
qa/scenarios/channels/channel-message-flows.yamlextensions/qa-channel/src/inbound.tsextensions/qa-lab/src/qa-transport.tsextensions/qa-lab/src/crabline-transport.tsextensions/telegram/src/draft-stream.tsThe scenario covers channels.streaming as primary evidence and
runtime.delivery as secondary evidence.