Discover Tools skills, compare source repositories and read the instructions for each workflow.
Use when creating prompts for Claude or other LLMs, need help structuring prompts effectively, want to improve prompt quality, or need templates for simple or complex prompting tasks. Provides Anthropic's offic...
Professional engineering skill combining senior engineer thinking patterns, adaptive task assessment, and Google-grade standards. Invoke with /pro before any coding task to ensure production-quality work with p...
Analyze multiple assets and define a unified visual style guide. Use when images don't match, assets come from different sources, or need to regenerate consistent variants. Outputs style guides with line weight...
Use when working on web development tasks involving NextJS, React, TypeScript, Tailwind CSS, testing, deployment, APIs, databases, authentication, cloud infrastructure, or any modern web development stack. Prov...
Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and ve...
Create cohesive UI color systems from vibes and reference images. Use when starting a new page/component, unifying assets that feel off, or need consistent color tokens. Outputs core palette (primary, accent, b...
Create production-ready, gorgeous frontend interfaces with expert design guidance, modern component patterns, animations, and extensive templates. Combines design principles, component libraries (React/shadcn/u...
Critique UI layouts and provide specific, actionable fixes. Use when something feels off but you can't articulate why, before finalizing designs, or after adding new components. Outputs diagnosis of visual hier...
Transform rough image generation prompts into consistent, effective art direction. Use when getting inconsistent results from AI image generators, need variations matching existing style, or translating vague i...
Audits and updates UI components across an app to ensure consistent theming using CSS custom properties and design system colors. Use when updating UI theme, ensuring color consistency, or applying a design sys...
Transform design inspiration into implemented code through deep analysis, interactive vision discovery, planning, and checkpoint-based execution. Use when you have a screenshot/reference and want to build somet...
Design layered backgrounds that make PNG assets blend naturally. Use when hero assets float awkwardly on gradients, multiple images don't blend, or need seamless foreground/background integration. Outputs layer...
Create new Claude Skills with proper structure, frontmatter, and best practices. Use when the user wants to create a skill, build a skill, make a new skill, or scaffold skill files.
Add or modify CRUD entities following the layered architecture pattern. Use when adding new database models, creating API endpoints, or implementing data access layers.
Guidelines and best practices for building Convex projects, including database schema design, queries, mutations, and real-world examples
Create, update, and maintain shadcn/ui components in the `apps/web` Next.js project. Use when asked to add UI components, sync styles/theme, adjust Tailwind, or apply shadcn/ui best practices in this codebase.
Steenberg-style architecture review for maintainability and replaceability. Use when (1) planning major refactors, (2) designing new modules or systems, (3) reviewing existing architecture, (4) before significa...
Respond to code review feedback with technical rigor. Use when (1) receiving review comments from any model (Codex, Gemini, Claude), (2) synthesizer outputs issues to fix, (3) refactor agent needs to address fi...
Review and update Python documentation to match project standards. Use when (1) writing new code that needs documentation, (2) reviewing existing code for documentation gaps, (3) updating docstrings after code...
Four-phase structured debugging methodology. Use when (1) tests fail unexpectedly, (2) functions produce wrong values, (3) systems show anomalous results, (4) unexpected errors appear, (5) performance regresses...
Enforce evidence-based completion claims with actual command output. Use before (1) claiming tests pass, (2) claiming a bug is fixed, (3) claiming a task completed successfully, (4) claiming performance improve...
Use when reviewing implementation plans for quantitative trading systems before execution - catches data leakage, look-ahead bias, scalability risks, and production pitfalls
Dispatch multiple agents in parallel for independent problems. Use when (1) 3+ test files failing with different root causes, (2) multiple modules broken independently, (3) multiple components need separate fix...
Enforce test-first development with Red-Green-Refactor cycle. Use when (1) implementing new features in production code, (2) fixing bugs (write test that reproduces bug first), (3) refactoring code (ensure test...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.