Write, debug, and tune Playwright specs with locator strategy, trace diagnosis, and CI-aware timeouts.
Design & media
Validation And Fix
Try itUse when running existing project validation commands and fixing failures after code changes, including lint, type-check, unit/integration test, build, CI, or local script failures. Do not use when the task is to design or author new component/E2E tests; Chinese triggers include validation, check fa
What it does
1. 从 package.json 或仓库文档中识别可用命令。 2. 优先按以下顺序执行: - lint - type-check - unit/integration tests - build 3. 仔细阅读失败输出。 4. 将错误按文件、错误类型和依赖关系分组,优先处理阻塞后续诊断的根因。 5. 一次只修复一类问题,并显示或记录关键错误上下文。 6. 每次关键修复后重新执行受影响命令,确认错误是否减少。 7. 如果同一错误连续三次修复仍失败,停止扩大改动并报告阻塞。 8. 最后按 总结执行结果、修复内容和剩余风险。
The skill document
验证并修复
Purpose
自动化执行已有验证命令,分析失败原因并安全修复,确保质量门禁达标。
Procedure
- 从 package.json 或仓库文档中识别可用命令。
- 优先按以下顺序执行:
- lint
- type-check
- unit/integration tests
- build
- 仔细阅读失败输出。
- 将错误按文件、错误类型和依赖关系分组,优先处理阻塞后续诊断的根因。
- 一次只修复一类问题,并显示或记录关键错误上下文。
- 每次关键修复后重新执行受影响命令,确认错误是否减少。
- 如果同一错误连续三次修复仍失败,停止扩大改动并报告阻塞。
- 最后按
Expected Output总结执行结果、修复内容和剩余风险。
Failure Triage
- 先修最早出现且会级联的错误,例如缺失类型、导入失败、配置解析失败。
- 区分真实产品 bug、测试环境问题、快照漂移、依赖版本变化和 flaky。
- 对 CI 专属失败记录 Node 版本、包管理器、环境变量、路径大小写和工作目录差异。
- 修复测试时优先修产品代码或测试等待方式,不用删除断言掩盖真实回归。
Constraints
- 不要盲目关闭规则来消除报错
- 除非有明确理由,不要为了通过检查而降低类型安全
- 不要因为附近测试失败就顺手重写无关模块
- 不要一次性修改多个无关根因
- 不要删除失败测试来让验证通过
- 不要只运行失败命令的片段就声称整体验证通过
详细参考
撰写验证修复报告时,加载 references/report-template.md。
Expected Output
- lint / type-check / test / build 等验证命令全部通过
- 失败项已修复或给出明确原因和后续行动
- 修复报告保存为
reports/validation-fix-YYYY-MM-DD-HHmmss.md
Related skills
Run Git operations — commits, branches, merges, rebases, conflict resolution, and recovery — with safety rules enforced.
Generate and edit Draw.io, Mermaid, and Excalidraw diagrams from natural language using a structured JSON spec.
Find why your productivity system keeps failing, then apply the smallest fix — capacity math, bottleneck routing, durable local notes.
Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.
Stores durable facts in a categorized, plain-markdown vault on disk, alongside your agent's built-in memory.
More from bovinphang
Browse all skillsGenerate or edit diagrams, visual assets, and image workflows with reviewable PNG self-checks and bounded self-repair.
Use when creating editable technical diagrams with draw.io / diagrams.net sources, including architecture diagrams, ERD, UML, sequence diagrams, flowcharts, ML model diagrams, official shape lookup, brand symbols, Graphviz auto-layout, codebase structure maps, .drawio validation, or draw.io CLI expo
Use when building, reviewing, or improving frontend UI that needs product-specific design direction, design-system generation, Master/Page overrides, distinctive visual identity, anti-generic interface choices, first-screen hierarchy, UI polish, chart UX, interaction states, responsive behavior, or
Use when creating or reviewing Next.js 14+ App Router projects, file routes, layouts, server/client component boundaries, SSR/SSG/ISR, streaming, metadata, middleware, server actions, or Next-specific data fetching. For generic client React component architecture, apply the project's React conventio
Use when creating, reviewing, or restructuring frontend monorepos with pnpm workspace, Turborepo, Nx, multi-package dependency boundaries, task orchestration, package naming, or package publishing; Chinese triggers include monorepo, workspace, multi-package.
Use when creating or reviewing Nuxt 3 projects, file routes, pages, layouts, SSR/SSG/SPA behavior, Nuxt data fetching, route middleware, plugins, modules, server routes, or Nuxt-specific Vue 3 conventions. For generic Vue component architecture, apply the project's Vue conventions separately; Chines