Agent Skills Hub

guard

Epistemic safety analysis for JSON data in prompts to prevent LLM hallucinations and reasoning errors when handling incomplete or large-scale datasets.

design-md

Analyze Stitch projects and synthesize a semantic design system into DESIGN.md files to serve as a source of truth for AI-driven UI generation.

pci-compliance

Implement PCI DSS compliance for secure payment processing, cardholder data protection, and audit preparation using standardized security patterns.

sosumi

Retrieves Apple platform documentation, Human Interface Guidelines, and WWDC transcripts as Markdown using the Sosumi service.

react-patterns

Implement React 19 patterns: React Compiler, Server Actions, Forms, and new hooks like 'use'. Guide decisions between Actions vs TanStack Query for mutations.

git

Safe, protocol-driven Git operations for committing, pushing, and PR management using the GitHub CLI (gh).

api-integration

Automate frontend API integration using Apidog and MCP servers. Generate TypeScript types, TanStack Query hooks, and axios-based clients from OpenAPI specifications for consistent, type-safe API consumption.

codex

Delegates coding tasks to the OpenAI Codex CLI for features, refactoring, PR reviews, and automated issue fixing within Git repositories.

context-degradation

Diagnose, isolate, and mitigate LLM context failures like lost-in-middle, poisoning, distraction, and context clash to improve agent reliability.

route-handlers

A specialized skill for building and managing Next.js App Router API routes, handling HTTP methods, request bodies, streaming, and response configuration.

reload

Clean up your current Claude Code session and automatically resume in a fresh, optimized terminal window.

obsidian-bases

Create and edit Obsidian Bases (.base files) with database-like views, complex filters, custom formulas, and data summaries.