Agent Skills Hub

karpathy-guidelines

Behavioral guidelines for LLMs to reduce coding mistakes, follow best practices, and improve output quality by enforcing simplicity, surgical changes, and goal-driven verification.

trulens-evaluation-workflow

A systematic workflow to instrument, evaluate, and monitor LLM applications using TruLens, supporting frameworks like LangChain, LangGraph, and LlamaIndex.

finishing-a-development-branch

Completes development branches by verifying tests, managing merge or PR workflows, and cleaning up worktrees to ensure a consistent repository state.

deep-thinking

A deep reasoning protocol that ensures systematic analysis, multi-hypothesis generation, and rigorous verification for complex architectural, debugging, and high-stakes tasks.

steering-specs-generator

Extract tacit engineering knowledge through guided interviews and generate structured steerings for consistent project standards and conventions.

ralph-tui-create-beads

Converts PRDs into structured task beads for autonomous execution with ralph-tui, including quality gates and dependency management.

sparc-methodology

SPARC methodology for multi-agent development: systematic Specification, Pseudocode, Architecture, Refinement, and Completion workflows via Claude Flow orchestration.

localization-testing

Automated internationalization (i18n) and localization (l10n) testing suite for global software. Validates translations, RTL layouts, locale-specific formats, and unicode support.

code-auditing

A systematic code auditing framework for identifying technical debt, security vulnerabilities, dead code, and code quality issues in software projects.

github-code-review

Deploy specialized AI swarms to perform comprehensive, multi-domain GitHub pull request reviews covering security, performance, architecture, and style.

designer

Expert UI/UX design assistant for React & Next.js. Provides visual critiques, design system architecture, and Tailwind CSS/shadcn/ui implementation guidance for production-grade web applications.

cross-plugin-detective

Standardized detective skill integration for agent roles. Maps agents to code-analysis skills and enforces claudemem usage for memory-indexed code investigation.