qa-test-runner skillB
qa-test-runner is agent-read markdown (skill) from mingdui/ming-qa: 在 spec-task 和测试脚本就绪后，逐条执行、分类失败、修最小根因、收集证据、跑 completion 门禁。 你只负责"跑"——不生成报告、不审查代码、不判 Ready。审查留给 qa-code-reviewer，报告与判定留给 qa-report-generator。 不适用：报告生成、代码审查、用例设计。.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# QA Test Runner — 执行与修复
> **CLI 调用约定**：本工具包的 CLI 是 `quality-assurance-agent/scripts/qa_agent.py`。
> 它**不以 PATH 命令的形式分发**——命令由你（agent）执行，人不必手敲。
> 开工前解析一次 skill 目录，之后所有命令一律写成
> `python "$QA_AGENT_DIR/scripts/qa_agent.py" <cmd>`：
>
> QA_AGENT_DIR="${QA_AGENT_CLI:-$(dirname "$(find ~/.claude/skills ~/.agents/skills ~/.codex/skills .claude/skills .agents/skills .codex/skills -maxdepth 2 -name SKILL.md -path '*quality-assurance-agent/*' 2>/dev/null | head -1)")}"
>
> 运行环境若已告知本 skill 目录（Claude Code 会），直接用，不必跑上面的查找。
> 完整命令语法见 `$QA_AGENT_DIR/references/cli-reference.md`。
## 你的定位
你是从 spec-task 到执行证据的执行引擎。你前面的阶段把用例变成了 task 和脚本，你的任务是把它们**跑出来、跑出问题修最小根因、收集证据、跑完 completion 门禁**。报告生成和最终判定不归你管——那是 `qa-report-generator` 的职责。
你不是代码审查者——那个判断留给 `qa-code-reviewer`。你的 completion-check 是下游 readiness 判定的硬前置条件，没通过下游不能叫 Ready。
## CLI 命令
本阶段所有命令的完整语法、参数说明见**主 skill（quality-assurance-agent）→ CLI 命令参考 → 阶段 4**。这里不重复维护命令语法。
测试脚本执行推荐用 `python "$QA_AGENT_DIR/scripts/qa_agent.py"run-with-env`（自动处理 CRLF/环境变量/日志），详细用法见主 skill CLI 命令参考的「通用工具」章节。
## 前置条件
- `.qa-agent/current/test-cases.json` 已确认
- `.qa-agent/current/test-spec-tasks.json` 存在
- `.qa-agent/current/coverage-balance.json` 通过
…Read the whole file at its exact version.
How to install
mdr add mingdui/ming-qa/qa-test-runner@git:20260918.2d0e957mdr add mingdui/ming-qa/qa-test-runner@sha256:f0dbfc65ff309c55Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_egwpcalqqs6divqo)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260918.2d0e957 latest | 2026-09-18 | 2d0e957 | 12,617 B | B | view · diff |
| git:20260918.568ef46 | 2026-09-18 | 568ef46 | 12,637 B | B | view · diff |
| git:20260918.8d4fb77 | 2026-09-18 | 8d4fb77 | 12,737 B | B | view · diff |
| git:20260917.3052494 | 2026-09-17 | 3052494 | 12,179 B | B | view · diff |
| git:20260916.d5f28f3 | 2026-09-16 | d5f28f3 | 11,231 B | B | view |
Audit of the latest version
- fail: No script tag (matched: <script)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (12617 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
Source
mingdui/ming-qa · 28 stars · license MIT · pushed 2026-09-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_egwpcalqqs6divqo GET https://markdownregistry.com/api/v1/resolve?ref=mingdui/ming-qa/qa-test-runner GET https://markdownregistry.com/api/v1/blob/f0dbfc65ff309c5585e608c8df99ab69082fd9fe35f07e634ddc55dbe6e90a7e
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.