Agent Skills Hub

skills-management

Search, discover, install, update, and manage skills for AI coding agents. Centralized interface for ecosystem-wide skill discovery and local organization.

guard

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

Swarm Orchestration

Orchestrate multi-agent swarms using agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Ideal for building distributed AI systems and scaling complex development workflows.

updating-dawncaster-filters

Systematically updates Dawncaster card/talent browser filter dropdowns and mapping arrays when new game expansions are released, ensuring frontend data synchronization with the Blightbane API.

qras

A local RAG semantic memory system using Qdrant and Ollama. Ideal for recalling workspace files, notes, project decisions, and user preferences with high-relevance vector search.

revert

Git-aware logical undo at track, phase, or task level with confirmation gates.

clean-code

Pragmatic AI-assisted coding standards focused on clean code, simplicity, and maintainability. Enforces best practices like SRP, DRY, and KISS to prevent over-engineering.

widget-tester

Expert assistant for testing the Raamattu Nyt embeddable Bible widget, validating API responses, testing reference formats, and debugging audio integration.

linkedin-post-generator

AI-powered LinkedIn post generator for professionals. Create engaging thought leadership, career updates, and industry-specific content using the Sloan agent.

api-connector

Integrate with REST APIs to manage authentication, execute HTTP requests, and process JSON responses seamlessly within your development workflow.

dyad:swarm-pr-review

Collaborative PR review using a swarm of three specialized AI agents (Correctness, Health, UX) that discuss findings and reach consensus before posting a structured summary with inline comments.

strategic-compact

Enhance workflow efficiency by performing manual context compaction at logical task boundaries instead of relying on unpredictable auto-compaction.