Coding standards, frameworks, refactoring, and code review (15.7K skills)
Find official documentation for a library, framework, or API and match it to the version in use. Get source-backed answers and focused code examples, with any details that could not be verified clearly identified.
Turn a coding request into a concise, ordered plan after reviewing project documentation and relevant files. The result defines scope, lists concrete actions, and includes validation, risks, and unresolved questions without changing files.
Design backend systems with clear boundaries between business rules, databases, and external services. Use Clean Architecture, Hexagonal Architecture, and Domain-Driven Design to organize new applications, refactor existing code, and make core logic easier to test.
Turn feature ideas and behavior changes into agreed designs before implementation. Clarify goals through one question at a time, compare alternative approaches, review the design in sections, and save a design document before moving to implementation planning.
Integrate WebMCP tools, app capabilities that AI agents can call, directly into an existing web application. Inspect its source code, preserve existing validation and permissions, and verify tool discovery, execution, and actual changes in application state.
Turn recorded browser traffic into an OpenAPI 3.1 specification, a standard format for describing APIs. Infer endpoints and data structures from observed requests, and generate client code plus reports showing examples, confidence, and coverage gaps.
Convert Python browser-use scripts into TypeScript workflows using Stagehand v3 on Browserbase. Separate predictable steps from actions that need AI, and provide runnable project setup plus a migration summary identifying features that require human review.
Improve automation for specific website tasks by repeatedly running them, reviewing execution records, and updating navigation instructions. Turn the resulting workflow and recovery steps into a reusable Claude Code skill, with optional runnable script generation.
Create WebMCP tools, browser features that AI agents can call, for a specific website. Starting from a URL and desired task, generate an initialization script and validate tool registration and execution with Stagehand.
Retrieve HTML or JSON from URLs through Browserbase without starting a browser session. Inspect HTTP status codes and response headers, control redirects, and enable proxies for static page retrieval and simple content collection.
Write, review, and refactor SwiftUI apps for iOS and macOS. Covers state management, adaptable layouts, accessibility, animations, and API migration, with Instruments recordings to investigate performance problems and prioritize improvements.
Check Apple documentation for deprecated SwiftUI APIs and their replacements. Updates the SwiftUI Expert Skill reference with version requirements, code examples, and a lookup table, then prepares a pull request using Sosumi MCP.
Create project guidance documents for topics such as API conventions, testing, security, and deployment. The skill examines existing code patterns and relevant templates, then writes focused documents that agents can use as ongoing project memory.
Create and maintain project reference documents from the codebase, covering product purpose, technology choices, and organization patterns. Detect differences between documentation and code while preserving user additions during updates.
Review a technical design against requirements and existing code patterns to assess implementation readiness. Highlight up to three critical concerns, recognize strengths, and provide a reasoned GO or NO-GO decision with actionable next steps.
Compare feature requirements with an existing codebase to identify missing capabilities and integration challenges. Evaluate extending existing code, building new components, or combining both, then save findings and open research questions to inform the design phase.
Create requirements, designs, and task lists for multiple roadmap features in dependency order. Independent features run in parallel when supported, followed by checks that shared data, interfaces, naming, and work boundaries agree across specifications.
Turn a feature description and project guidance into a requirements document with testable acceptance criteria. Review coverage, ambiguity, and scope before saving, using EARS, a structured format for describing system behavior and conditions.
Review a completed implementation task against approved requirements, design, and assigned scope. The skill inspects code changes and verification evidence, checks tests and hidden dependencies, and returns an approval or rejection with specific findings and required fixes.
Generate requirements, technical designs, and implementation tasks for pending roadmap features in Cascade. Features are processed one at a time in dependency order, followed by a review of consistency and responsibility boundaries across specifications.
Create requirements, designs, and implementation tasks for multiple roadmap features in dependency order. Use parallel workers when available and permitted, or process sequentially, then check consistency across specifications.
Create topic-specific project guidance that agents can use as project memory. Examine existing code and available templates to document conventions for areas such as APIs, testing, authentication, or deployment, with concrete examples.
Document a project's purpose, technical choices, and organization patterns as persistent reference files for agents. Compare existing guidance with the codebase, identify mismatches, and propose additions while preserving user-written content.
Review a technical design before implementation by comparing it with requirements and existing code patterns. Receive up to three critical concerns, recognized strengths, and a clear decision on whether to proceed, with reasons and practical next steps.