菜单
Use when creating, editing, validating, or running agent-qa tests, suites, or hooks. Prefer agent-qa MCP tools, enforce canonical agent-qa IDs, and use the bundled schema reference to avoid hallucinated config keys or YAML fields.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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/vostride/agent-qa --skill agent-qa-authoring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。
Use after an agent-qa run has failed and you need to debug, patch, and verify the issue using MCP evidence, logs, artifacts, and local code changes instead of generated fix suggestions.
Use when investigating failed agent-qa runs, inspecting artifacts, classifying failures, or comparing recent runs. Prefer agent-qa MCP run/artifact tools and produce evidence-backed triage.
基于 SOC 职业分类
正在显示 SKILL.md
| name | agent-qa-authoring |
| description | Use when creating, editing, validating, or running agent-qa tests, suites, or hooks. Prefer agent-qa MCP tools, enforce canonical agent-qa IDs, and use the bundled schema reference to avoid hallucinated config keys or YAML fields. |
| metadata | {"short-description":"Author agent-qa tests safely"} |
agent_qa_discover.agent_qa_get_config, especially targets, devices, providers, and services.mcp.references/agent-qa-contracts.json when you need exact schema fields or ID contracts.agent_qa_generate_idagent-qa ids generate <test|suite|hook|run|observation>npx --yes agent-qa ids generate <type>agent_qa_validate_id or agent-qa ids validate <type> <id> --json.agent_qa_validate_test or agent_qa_validate_definition with kind: "test"agent_qa_validate_suite or agent_qa_validate_definition with kind: "suite"agent_qa_validate_definition with kind: "hooks"agent_qa_create_test, agent_qa_update_test, agent_qa_delete_testagent_qa_create_suite, agent_qa_update_suite, agent_qa_delete_suiteagent_qa_create_hook, agent_qa_update_hook, agent_qa_delete_hookworkspace.testMatch or workspace.suiteMatch.t_ + 10 id-agent words.s_ + 10 id-agent words.h_ + 10 id-agent words.r_ + 10 id-agent words.obs_ + 10 id-agent words.agent_qa_enqueue_test_run and agent_qa_enqueue_suite_run over shelling out.