安全
运行本地与 CI Harness 检查并解释治理结果
当用户要求检查、体检、回归、验收、解释或诊断会勇禾口王内容工作流 Harness，或维护、移植、打包、开源这个 Harness 检查器 Skill 时使用。统一调用仓库现有的 verify.sh、harness-check、Runtime Governance、Hook、Task Contract、Safety Gate、Episode、可观测性和失败台账检查，并分别报告本地、暂存区、CI 自动化结果与真实宿主烟测边界。
把 Harness 检查变成可重复、可审计的交付动作。检查逻辑以仓库 .harness/ 为唯一真源；本 Skill 负责选择入口、完整执行、解释结果和暴露未覆盖边界，不复制或改写检查规则。
先定位仓库根目录：必须能找到 .harness/scripts/verify.sh。所有命令从仓库根目录运行。
| 用户目的 | 入口 |
|---|---|
| 检查当前本地工作区 | bash .harness/scripts/verify.sh --working-tree |
| 检查准备提交的治理改动 | bash .harness/scripts/verify.sh --staged |
| 模拟 CI、去除本机 Skill/Memory 依赖 | bash .harness/scripts/verify.sh --ci |
| 只诊断结构、链接和治理契约 | bash .harness/scripts/harness-check.sh --local 或 --ci |
不要默认只跑 harness-check.sh 就宣称 Harness 完成；完整验收应优先使用 verify.sh。
| head、|| true 或吞掉 stderr 的方式判断成功。722、CI 165 项；纳入本 Skill 的组件和路由断言后当前为本地 728、CI 171 项。这些都不是永久硬编码的总分；数量变化时如实记录，不自行补算或夸大。⚠️ 是警告，不等于 ✅；只要任一应通过检查返回非零，就判定自动检查失败。AGENTS.md 的范围说明和确认规则。--no-verify 绕过 Hook，不为让检查通过而修改计数、删除反例、关闭治理项或把宿主烟测写成自动化证据。至少输出以下五部分：
working-tree、staged 或 ci，以及检查到的仓库/提交。语义 Hook 配置校验和 fixture 正反例只能证明配置可解析、规则可归一化、失败路径能被拦截，不能证明真实宿主一定触发。以下情况必须单独标记为“宿主烟测待补”：
verify.sh 失败：按输出先运行对应的单项测试，例如 bash .harness/tests/test-hook-config.sh。bash .harness/scripts/sync-agent-adapters.sh --check；未经用户明确要求，不自动使用 --fix。.harness/contracts/、AGENTS.md、.agents/skills/ 和 Memory 真源，不直接改测试让它变绿。hekouwang-precheck，并把自动检查和人工视觉检查分开报告。详细命令、检查层级和历史基线/当前数量口径见 references/check-matrix.md。面向维护者的开源说明和流程图见 README.md。
Audit Huawei Cloud skills for quality, security, and compliance using a two-check pipeline: skillspector (AI security) and gitleaks (credential leak). Generates structured reports with issue details and fix strategies. Triggers include: "审计技能","技能审计","检查技能质量","扫描技能问题","技能安全审计", "audit skill","check skill quality","scan skills for issues","skill audit", "华为云技能审计","技能合规检查","skill gate","质量门禁","技能检查", "audit huawei cloud skill","verify skill compliance","技能质量检查","跑审计","安全扫描".
引导用户从 0 构建一个基于 Harness 工程的 Skill。适用于具有一定复杂度的任务场景(多阶段、多分支、需要质检、需要状态持久化)。不适用于简单的单步任务或纯 prompt 优化。触发词:'创建 Skill'、'新建 Skill'、'做一个 Skill'、'构建 Skill'、'skill generator'、'harness skill'。
Use this skill when designing or operating a Harness-style control layer for OpenClaw setups with many skills, memory surfaces, safety-sensitive tools, playb...
End-to-end functional testing framework for Huawei Cloud skills — three-tier pipeline covering single-skill unit testing, multi-skill orchestration, and end-to-end full flow testing. Each phase produces structured JSON output with chain verification. Supports skill installation validation, functional analysis, CLI→SDK→API feasibility research, test case generation, real-environment execution with resource lifecycle, resource cleanup, multi-skill scenario orchestration, trigger-conflict detection, and consolidated reporting. Triggers include: 测试技能, 执行技能测试, 跑测试流程, 技能回归测试, skill test, run skill tests, test huawei cloud skill, verify skill, 测试华为云skill, 全流程测试, 编排测试, 技能完整性检查, skill-tester, 跑测试, 回归测试, 组合测试, 多skill编排, verification, e2e.
Audit a target SKILL.md against the Agent Skills specification and generate a Chinese HTML report. Use when the user asks to check, audit, review, or optimiz...
Agent Harness 构建规范——当 AI 通过编程构建 harness agent（coding agent / 自动化 agent / 长时运行 agent）时，读取本 skill 作为参考标准，确保产出符合 harness 工程架构：Loop / Provider / Tools / Permissions / Session / Compaction / Prompts & Skills / Extensions 七层 + Delivery。覆盖设计决策、可运行 Python 代码模板、长时运行模式。触发词：coding agent、agent loop、tool calling、context management、session persistence、agent harness、构建 agent。Use this skill when the user asks to build a coding agent / automation agent / long-running agent / agent harness.