一键导入
self-healing
Automatically detect, isolate, and fix regressions or bugs based on test failures.
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。
菜单
Automatically detect, isolate, and fix regressions or bugs based on test failures.
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。
基于 SOC 职业分类
UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, and flat design. Topics: color systems, accessibility, animation, layout, typography, font pairing, spacing, interaction states, shadow, and gradient. Integrations: shadcn/ui MCP for component search and examples.
Analyze technical debt and evolve the project structure to improve scalability and maintainability.
Identify runtime bottlenecks and optimize critical paths to improve application speed and resource efficiency.
Proactively identify and patch security vulnerabilities and implement defensive coding patterns.
Design and implement backend services, APIs, middleware, authentication, and server-side logic following production best practices.
Perform a comprehensive review of the active directory or uncommitted git changes.
| name | Self-Healing |
| description | Automatically detect, isolate, and fix regressions or bugs based on test failures. |
| allowed-tools | ["run_tests","read_file","edit_file","execute_command","git_status","search_code"] |
This skill transforms the agent into an autonomous repair system. Follow these steps strictly:
run_tests to identify failing cases.execute_command to run the application and capture logs/stack traces.search_code and read_file to trace the execution path from the failure point back to the source of the bug.think tool to hypothesize the cause.edit_file for precise changes.memory_append).