Agent Skills Hub

context-degradation

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

proactive-agent

Transform AI agents into proactive partners using WAL Protocol, persistent memory buffers, and autonomous cron scheduling to anticipate needs and improve performance.

go-api

Generate a production-ready Go API service with boilerplate for observability, local development, and clean architecture.

components-build

Build modern, composable, and accessible React UI components following the components.build specification. Use for design systems, component libraries, and reusable UI architectures.

solana

Expert Solana Anchor development: build programs, manage PDAs, implement SPL tokens, handle security audits, and perform fuzz testing with Trident.

skill-from-github

Create high-performance AI skills by reverse-engineering successful GitHub projects and proven open-source methodologies.

Task Patterns

CLI-based Linear integration for AI-assisted task management, issue tracking, and automated development workflows.

skills

A project-specific architectural template for Next.js 15, FastAPI, and Supabase applications, including structured AI integration patterns.

mcp-tools

Skill for managing MCP-based research, documentation lookups, and coordination between external search tools and plugin-backed memory systems.

deployment-rollback

Emergency recovery suite for Vercel-hosted projects. Manage deployment rollbacks, database migration reverts, cache invalidation, and health verification workflows.

nx-workspace-patterns

Configure and optimize Nx monorepo workspaces. Use for project boundaries, build caching, library organization, and implementing affected commands.

evidence-first-debugging

Enforces a strict evidence-based debugging workflow using structured observation, hypothesis testing, and causality validation to eliminate speculation in technical investigations.