Agent Skills Hub

senior-data-engineer

World-class senior data engineering skill for building scalable data pipelines, ETL/ELT systems, and modern data infrastructure using Python, Spark, dbt, and Kafka.

copy-editing

Systematically improve marketing copy through a 7-pass editing framework to boost clarity, tone, and conversion impact.

swarm-advanced

Orchestrate complex multi-agent swarms with topologies like mesh, hierarchical, and star for research, development, and testing workflows.

fluidsim

Framework for high-performance computational fluid dynamics (CFD) simulations, supporting Navier-Stokes, shallow water, and stratified flows using pseudospectral methods and MPI parallelization.

executing-plans

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

agent-system

Implementation patterns for MERIDIAN autonomous AI agents using Claude API, including BaseAgent lifecycle, structured tool use, token budget enforcement, and cron scheduling.

shift-right-testing

Production-grade testing strategy implementing feature flags, canary releases, synthetic monitoring, and chaos engineering for continuous reliability in live environments.

deepscan-monitor

Manage long-running PapersFlow DeepScan research workflows with asynchronous monitoring, live progress tracking, and automated report generation.

research-review

Get deep, critical, NeurIPS/ICML-style peer reviews of your research, paper drafts, and experimental setups using external LLMs via Codex MCP.

request-optimizer

An intelligent gateway that analyzes, scores, and routes user requests across 27 agents, 27 skills, and 14 MCPs to optimize Claude Code execution.

speckit-workflow

A constitution-driven, spec-first development workflow for Claude Code and Codex, automating feature planning, implementation, and quality assurance through structured agentic loops.

doc-coauthoring

A structured workflow for co-authoring documentation, technical specs, and proposals, guiding users through context gathering, collaborative refinement, and reader verification.