Loading...
Loading...
Found 29 Skills
Review code for architecture: module and layer boundaries, dependency direction, single responsibility, cyclic dependencies, interface stability, and coupling. Cognitive-only atomic skill; output is a findings list.
Generate an LLM-optimized project profile for any git repository. Outputs docs/{project-name}.md covering architecture, core abstractions, usage guide, design decisions, and recommendations. Trigger: "/project-profiler", "profile this project", "為專案建側寫"
Analyzes code based on John Ousterhout's "A Philosophy of Software Design". Identifies unnecessary complexity, shallow modules, information leaks, and design problems. Use when reviewing architecture, PRs, refactoring, or asking about code quality.
Evaluates and prevents unnecessary abstractions by analyzing interfaces, layers, and patterns against concrete requirements. Use when evaluating new abstractions, reviewing architecture proposals, detecting over-engineering, or simplifying existing code. Triggers on "is this abstraction necessary", "too many layers", "simplify architecture", "reduce complexity", "over-engineered", "do we need this interface", or when reviewing design patterns.
Provides structural context for downstream review and refactoring workflows. Use when before architecture reviews to understand file organization, exploring unfamiliar codebases to map structure, estimating scope for refactoring or migration. Do not use when general code exploration - use the Explore agent. DO NOT use when: searching for specific patterns - use Grep directly.
Architect/CR agent role. Receives git diff, task spec, ADRs, design doc, and project conventions. Reviews code and returns APPROVED or CHANGES_REQUIRED. Do NOT invoke directly — dispatched by team-execute.
Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations.
Analyze the source code of GitHub open-source repositories and generate structured analysis reports. Supports generating reports such as project architecture overview, code quality analysis, core module description, etc., and optional synchronization to Notion.
Use when designing module boundaries, planning refactors, or reviewing architecture in Python codebases. Also use when facing tangled dependencies, god classes, deep inheritance hierarchies, unclear ownership, or risky structural changes.
Auto-generates code flow diagrams from Python module analysis. Detects when architecture diagrams become stale (code changed, diagram didn't). Use when: creating new modules, reviewing PRs for architecture impact, or checking diagram freshness. Generates mermaid diagrams showing imports, dependencies, and module relationships.
Full-codebase audit using 1M context window. Security, architecture, and dependency analysis in a single pass. Use when you need whole-project analysis.
Use when reviewing AWS architecture, designing cloud systems, addressing operational issues, security concerns, reliability problems, performance bottlenecks, cost overruns, or sustainability goals