Agent Skills Hub

prp-ralph-loop

Autonomous iteration loop for AI software development. Executes tasks, validates code, and manages state until completion. Ideal for implementing complex PRP plans.

saving-codeacts

Preserve successful Python code executions as reusable tools within the gentools package structure, utilizing Pydantic models for structured output and type-safe interfaces.

executing-plans

Execute implementation plans in separate sessions with review checkpoints, ensuring task-by-task verification and robust code quality.

long-running-agent

Framework for building AI agents that persist state across multiple context windows, enabling them to complete complex, multi-day coding tasks without losing progress or context.

multi-llm-advisor

Fetches expert perspectives from OpenAI Codex and Google Gemini for architecture, code reviews, and debugging, with transparent LLM synthesis.

prd

Generate professional Product Requirements Documents (PRD) and structure features for autonomous development cycles.

github-copilot-agent-tips-and-tricks

Guidance and operational tips for identifying, reviewing, and managing pull requests created by the GitHub Copilot coding agent within your repository.

context-degradation

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

backend-rag-implementation

Build RAG systems to ground LLMs in proprietary data. Includes vector database integration, embedding strategies, hybrid search, and advanced retrieval patterns for FastAPI backends.

secure-claude-code

Monitor Runwall security posture, enabled guardrails, and recent audit logs for Claude Code, Codex, and MCP-based development environments.

Skill Create

Automates the creation of Betty Framework skills by scaffolding directory structures, generating YAML manifests, and handling registry registration.

agent-canvas

Orchestrate visual communication by drawing diagrams, flowcharts, and annotations on a TLDraw canvas via CLI. Ideal for architectural planning, PR reviews, and logging agent output.