Xz01 Dev Skill — Xz01 Dev 技能

xz01-dev-技能 Trigger Alias / 命中别名 xz01规范 = xz01-dev-技能

当用户提到以下中文触发词时，必须优先加载并遵循本技能：

xz01规范 xz01 规范 xz01开发规范 xz01学习范围 xz01角色分工 Hermes+Claude xz01 OpenClaw xz01 谁是 dev / 谁是 test /root/.OpenClaw 只读 测试输出写到 /www/wwwroot/www.900az.com 验证通过模板打包到 /root/.hermes/workspace/xz01/ 安装或接入 Lanhu MCP / 蓝湖 MCP References references/lanhu-mcp-安装ation.md — recommended Docker Compose + HTTP MCP 设置up for dsphper/lanhu-mcp, including Hermes native MCP and Claude Code connection examples. references/demo-xz01-may-2026-source-更新.md — read-only learning notes from the May 2026 demo_xz01 source 更新, including the user-confirmed rule that front-end PC/移动 搜索 is canceled/weakened and should not be a default QA 失败. references/xz01-template-工厂-architecture.md — architecture notes for upgrading the current mAIn/dev/test/rule loop into a 60-template dual-end xz01 自动化 工厂 with corpus ingestion, DB/路由 learning, planning, rendering, 验证, repAIr loops, rule review, and packaging. Overview

This 技能 is for operating a Hermes + Claude Code 工作流 around the user's existing OpenClaw/xz01 material. The existing OpenClaw tree is a read-only learning corpus, not a place to write configs, 技能s, memory, cron 状态, 会话s, templates, or 生成d 报告s unless the user explicitly 授权s a specific write.

Authoritative read-only boundary:

/root/.OpenClaw/ and every subdirectory = read-only learning material

Default 运行time division:

Hermes current 会话 = mAIn / dis补丁er / final 报告er Claude Code = dev / implementation worker Hermes independent test 角色 = test / 验证 worker Hermes independent rule 角色 = rule / process and standard reviewer

When to Use

Use this 技能 when the user asks about:

“xz01规范” “xz01 规范” “xz01-dev-技能” “Hermes 和 Claude 怎么分工” “谁是 dev，谁是 test” “OpenClaw 的学习范围” “/root/.OpenClaw 只读” “把这个流程做成 技能” “持续优化技能” Hermes + Claude 角色 division for OpenClaw/xz01-style work what each 角色 should learn from /root/.OpenClaw turning OpenClaw process rules into Hermes 技能s coordinating template development, 验证, and rule review without modifying OpenClaw's existing files preserving dev/test/rule separation while using Claude Code for implementation

Do not use this 技能 to modify /root/.OpenClaw files. Treat them as reference-only.

Non-Negotiable Boundary

All 角色s must obey:

Do not write to /root/.OpenClaw/ Do not 补丁 /root/.OpenClaw/ Do not 更新 /root/.OpenClaw/OpenClaw.json Do not modify /root/.OpenClaw/workspace/ Do not modify /root/.OpenClaw/代理s/ Do not modify /root/.OpenClaw/cron/ Do not modify /root/.OpenClaw/memory/ Do not modify /root/.OpenClaw/flows/ Do not modify /root/.OpenClaw/workspace/demo_xz01

Allowed operations on /root/.OpenClaw:

read tar获取ed files inventory directories summarize rules learn conventions compare 报告s agAInst known standards

If writes are required, write only to:

Hermes 技能 storage (~/.hermes/技能s/...) when creating/updating Hermes 技能s a user-授权d non-OpenClaw project directory /www/wwwroot/www.900az.com for all test-side 输出s, 验证 artifacts, screenshots, 报告s, and 网页site verification 输出s unless the user explicitly changes it /root/.hermes/workspace/xz01/ for numbered zip packages of templates that have fully passed verification another explicit path the user names

Packaging rule for verified templates:

Only templates that are thoroughly verified as passed may be packed. Package verified templates as numbered 压缩ed 归档s under /root/.hermes/workspace/xz01/. Do not store final verified template packages under /root/.OpenClaw/.

角色 Map 角色 Default as签名ee Purpose May write /root/.OpenClaw? mAIn Hermes current 会话 接收 请求s, split work, dis补丁, supervise, final 报告 No dev Claude Code implement code/template changes in 授权d workdir No test independent Hermes test 角色/会话 screenshots, AI visual analysis, lint/HTML/CSS/template 验证 No rule independent Hermes rule 角色/会话 process 审计, rule review, 技能/spec suggestions No MAIn 角色 Learning Scope

MAIn learns coordination and boundaries, not implementation.

Read-only sources:

/root/.OpenClaw/workspace/IRON_RULES.md /root/.OpenClaw/workspace/代理S.md /root/.OpenClaw/workspace/MEMORY.md /root/.OpenClaw/workspace/error.md /root/.OpenClaw/workspace/DREAMS.md /root/.OpenClaw/workspace/scripts/flow-控制器.js /root/.OpenClaw/workspace/scripts/检查-flow-stuck.js /root/.OpenClaw/workspace/scripts/violation-追踪er.js /root/.OpenClaw/OpenClaw.json /root/.OpenClaw/cron/jobs.json /root/.OpenClaw/代理s//会话s only when tar获取ed 历史/调试 上下文 is needed /root/.OpenClaw/memory/*.sqlite only when tar获取ed memory inspection is explicitly needed

MAIn must learn:

角色 boundaries flow sequence: mAIn → dev → test → rule → mAIn when to dis补丁 to each 角色 how to avoid dev/test/rule collapse 报告 格式化 expectations historical violations and user correcti