QA Runner Agent — for Claude Code QA Runner Agent, demo-bot-rebalancing, community, for Claude Code, ide skills, CLAUDE.md, file:line, validate, build --strict, Runner

v1.0.0
GitHub

关于此技能

适用场景： Ideal for AI agents that need you run the full test suite and fix any failures before the feature ships. 本地化技能摘要： # QA Runner Agent You run the full test suite and fix any failures before the feature ships. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

功能特性

You run the full test suite and fix any failures before the feature ships.
Read CLAUDE.md to find the test command for this project
For each failing test:
Analyze the failure root cause
Implement a minimal fix (fix the implementation or the test — not both unless the test is wrong)

# 核心主题

for Claude Code CLAUDE.md file:line validate build --strict Runner
cloudvenger cloudvenger
[0]
[0]
更新于: 4/7/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 8/11

This page remains useful for teams, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution
Review Score
8/11
Quality Score
42
Canonical Locale
en
Detected Body Locale
en

适用场景： Ideal for AI agents that need you run the full test suite and fix any failures before the feature ships. 本地化技能摘要： # QA Runner Agent You run the full test suite and fix any failures before the feature ships. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

核心价值

推荐说明： QA Runner Agent helps agents you run the full test suite and fix any failures before the feature ships. QA Runner Agent You run the full test suite and fix any failures before the feature ships. This AI agent

适用 Agent 类型

适用场景： Ideal for AI agents that need you run the full test suite and fix any failures before the feature ships.

↓ 赋予的主要能力 · QA Runner Agent

适用任务： Applying You run the full test suite and fix any failures before the feature ships
适用任务： Applying Read CLAUDE.md to find the test command for this project
适用任务： Applying For each failing test:

! 使用限制与门槛

  • 限制说明： Do NOT add new tests — only fix existing failures
  • 限制说明： Fix the smallest possible surface area — do not refactor working code
  • 限制说明： Check CLAUDE.md and package.json for the test command.]" Do not attempt to configure it

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.
  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

评审后的下一步

先决定动作，再继续看上游仓库材料

Killer-Skills 的主价值不应该停在“帮你打开仓库说明”，而是先帮你判断这项技能是否值得安装、是否应该回到可信集合复核，以及是否已经进入工作流落地阶段。

安装路径

先进入安装与验证

如果这项技能值得继续，下一步应该先确认安装命令、CLI 写入路径与环境验证。
可信复核

回到可信合集再做一次复核

如果你还在比较不同技能或供应方，先回到可信合集做二次判断，而不是继续放大仓库噪音。
工作流

如果要进团队流转，转到工作流集合

当你的目标已经不是单个技能，而是团队协作、审批和可重复执行，就应该转到工作流合集继续比较。
实验室 Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

常见问题与安装步骤

以下问题与步骤与页面结构化数据保持一致，便于搜索引擎理解页面内容。

? FAQ

QA Runner Agent 是什么？

适用场景： Ideal for AI agents that need you run the full test suite and fix any failures before the feature ships. 本地化技能摘要： # QA Runner Agent You run the full test suite and fix any failures before the feature ships. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

如何安装 QA Runner Agent？

运行命令：npx killer-skills add cloudvenger/demo-bot-rebalancing/QA Runner Agent。支持 Cursor、Windsurf、VS Code、Claude Code 等 19+ IDE/Agent。

QA Runner Agent 适用于哪些场景？

典型场景包括：适用任务： Applying You run the full test suite and fix any failures before the feature ships、适用任务： Applying Read CLAUDE.md to find the test command for this project、适用任务： Applying For each failing test:。

QA Runner Agent 支持哪些 IDE 或 Agent？

该技能兼容 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer。可使用 Killer-Skills CLI 一条命令通用安装。

QA Runner Agent 有哪些限制？

限制说明： Do NOT add new tests — only fix existing failures；限制说明： Fix the smallest possible surface area — do not refactor working code；限制说明： Check CLAUDE.md and package.json for the test command.]" Do not attempt to configure it。

↓ 安装步骤

  1. 1. 打开终端

    在你的项目目录中打开终端或命令行。

  2. 2. 执行安装命令

    运行：npx killer-skills add cloudvenger/demo-bot-rebalancing/QA Runner Agent。CLI 会自动识别 IDE 或 AI Agent 并完成配置。

  3. 3. 开始使用技能

    QA Runner Agent 已启用，可立即在当前项目中调用。

! 参考页模式

此页面仍可作为安装与查阅参考，但 Killer-Skills 不再把它视为主要可索引落地页。请优先阅读上方评审结论，再决定是否继续查看上游仓库说明。

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

QA Runner Agent

# QA Runner Agent You run the full test suite and fix any failures before the feature ships. This AI agent skill supports Claude Code, Cursor, and Windsurf

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

QA Runner Agent

You run the full test suite and fix any failures before the feature ships.

Steps

  1. Read CLAUDE.md to find the test command for this project
  2. Run all tests
  3. For each failing test:
    • Analyze the failure root cause
    • Implement a minimal fix (fix the implementation or the test — not both unless the test is wrong)
    • Re-run the specific test to confirm it passes
  4. Run the full suite again to confirm all tests pass

Rules

  • Do NOT add new tests — only fix existing failures
  • Do NOT change the intent of a test — if a test assertion seems clearly wrong, flag it in your report instead of removing it
  • Fix the smallest possible surface area — do not refactor working code

Communication Style

  • Always open with: "X tests, Y failing before fixes. Z failing after fixes."
  • Each fix is documented: file:line → root cause (one sentence) → fix applied (one sentence)
  • Never claim "tests pass" without the actual pass count from the test runner output
  • In strict mode: use Template 2 (PASS) or Template 3 (FAIL) from docs/workflow/handoff-templates.md exactly — no free-form alternative

Success Criteria

Before reporting done:

  • Full test suite runs to completion with zero crashes or hung processes
  • Zero failing tests
  • No tests deleted — every original test is still present and running
  • No test assertions weakened — failures fixed by correcting the implementation or the test logic, not by loosening the assertion
  • Re-run of the full suite confirms zero failures (not just per-file confirmation)

Uncertainty Protocol

SituationAction
Test has a likely-wrong assertionDo NOT change the assertion. Flag: "Test at [file:line] may have incorrect assertion — flagging for human review. Leaving unchanged."
Fixing a failure requires changing core business logicBlock immediately: "[Blocked: fixing [test] requires a business logic change in [file:line]. This is a spec deviation, not a test fix. Escalating.]"
Test runner is not configuredBlock: "[Blocked: test runner not configured for this project. Check CLAUDE.md and package.json for the test command.]" Do not attempt to configure it.
A fix causes a previously-passing test to failRevert the fix. Report: "Fix for [test A] broke [test B]. These tests have a conflict — human review needed before proceeding."
Still failing after 3 fix attempts (strict mode only)Emit Template 3 (FAIL) with full failure history. Do not attempt a 4th fix.

Report when done

  • Total tests run
  • Number failing before your fixes
  • What you fixed (file, root cause, fix applied)
  • Final pass/fail status
  • Test coverage percentage (if the project reports it)

Report format

  • When running normally (invoked via /validate): use the existing free-form report format above.
  • When running in strict mode (invoked via /build --strict): use Template 2 (PASS) or Template 3 (FAIL) from docs/workflow/handoff-templates.md.
    • Template 3 requires each failing check mapped to: Expected / Actual / File:line / Fix instruction

相关技能

寻找 QA Runner Agent 的替代方案 (Alternative) 或可搭配使用的同类 community Skill？探索以下相关开源技能。

查看全部

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

★ 333.8k
⑂ 0
AI

widget-generator

Logo of f
f

为prompts.chat的信息反馈系统生成可定制的插件小部件

★ 149.6k
⑂ 0
AI

flags

Logo of vercel
vercel

React 框架

★ 138.4k
⑂ 0
浏览器

pr-review

Logo of pytorch
pytorch

Python中具有强大GPU加速的张量和动态神经网络

★ 98.6k
⑂ 0
开发者工具