Loading...
Loading...
Found 1,194 Skills
智能代码重构，提供设计模式建议、代码异味检测和保持行为不变的安全转换策略。
Design and architect software systems. Plans system components, interactions, and deployment patterns for scalability and maintainability.
Build health audit worker (L3). Checks compiler/linter errors, deprecation warnings, type errors, failed tests, build configuration issues. Returns findings with severity (Critical/High/Medium/Low), location, effort, and recommendations.
Recommended Go linters and golangci-lint configuration. Use when setting up linting for a Go project or configuring CI/CD.
Philosophy-aware PR reviews checking alignment with amplihack principles. Use when reviewing PRs to ensure ruthless simplicity, modular design, and zero-BS implementation. Suggests simplifications, identifies over-engineering, verifies brick module structure. Posts detailed, constructive review comments with specific file:line references.
Comprehensive codebase quality audit with parallel agent orchestration, GitHub issue creation, automated PR generation per issue, and PM-prioritized recommendations. Use for code review, refactoring audits, technical debt analysis, module quality assessment, or codebase health checks.
This skill should be used when the user asks to "review my changes", "review this code", "check my work", "what's wrong with my changes", "review before I push", "security review", "do a code review", or mentions reviewing, auditing, or analyzing local code changes before committing or opening a PR.
Improve code quality, reduce technical debt, restructure for maintainability
Architecture and design review for specified files/dirs/repo. Covers tech debt, patterns, quality. Diff-only review use review-diff. Complements review-code (orchestrated).
Analyze code examples in SKILL.md files for correctness using static analysis and TypeScript compilation
Modern Python development with uv (10-100x faster package manager) and ruff (extremely fast linter/formatter). Use when managing Python projects, dependencies, virtual environments, installing packages, linting code, or formatting Python files. Triggers on phrases like "uv install", "ruff check", "python package manager", "format python code", or working with pyproject.toml files.
Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims. Covers three practices - receiving feedback with technical rigor over performative agreement, requesting reviews via code-reviewer subagent, and verification gates requiring evidence before any status claims. Essential for subagent-driven development, pull requests, and preventing false completion claims.