Agent Skills Hub

git-ship

Automate your entire Git lifecycle from commit and PR creation to CI monitoring and branch merging, enforcing conventional commits throughout.

french-claude

A design-focused coding agent that brings world-class interface craft, motion, and systematic front-end engineering to your development workflow.

feature-prioritization

A structured decision-making tool that applies RICE, MoSCoW, Kano, and value-effort frameworks to prioritize software features, roadmap items, and build-vs-defer decisions with data-driven objectivity.

research-pipeline

End-to-end autonomous research agent: from idea generation and literature review to experiment execution, adversarial review loops, and paper writing.

common

Infrastructure for cross-product HealthSim data persistence, entity correlation via SSN, and DuckDB database operations.

context-degradation

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

brainwriting

Structured parallel brainstorming agent for ideation and conceptual expansion. Uses multi-agent perspectives to evolve vague ideas into practical, actionable visions. Ideation only, not for task planning.

eval-harness

Official evaluation framework for AI agent sessions, implementing Evaluation-Driven Development (EDD) principles to ensure reliability.

paper-plan

Generate a structured academic paper outline from research narrative, experiment data, and review conclusions.

aesthetic

Create aesthetically beautiful interfaces using systematic design principles, AI-driven evaluation, and automated inspiration analysis.

frontend

Frontend coding conventions for Preact and Tailwind. Use for web UI components in cluster applications.

deep-research

A systematic, multi-angle web research agent. Use for deep investigation, complex queries, and as a mandatory pre-research step before content generation to ensure evidence-backed, high-quality results.