Agent Skills Hub

frontend-design-review

Review, audit, and build production-grade frontend interfaces with high design quality, accessibility standards, and design system compliance.

autoresearch

Autonomous multi-team codebase improvement agent with specialized modes: narrow (goal-directed), broad (hypothesis-divergent), and sweep (quality-focused).

screenpipe-cli

Manage screenpipe pipes (AI-driven automations) and integrations via CLI. Create, run, schedule, and debug local agents to automate tasks based on your computer activity.

casadi-ipopt-nlp

Nonlinear optimization toolkit using CasADi and IPOPT. Ideal for building complex NLP models, defining symbolic variables, constraints, and solvers, with specialized support for power systems optimization patterns.

proofread

Automated, non-destructive proofreading for LaTeX and Quarto lecture files, generating quality reports for grammar, typos, and academic style.

session-logs

Search, analyze, and audit GeminiClaw session logs and memory. Use to investigate past interactions, track token usage, debug tool calls, and monitor agent performance.

dynamodb

AWS DynamoDB engineering assistant for schema design, query optimization, single-table patterns, and infrastructure management using Boto3 and AWS CLI.

agno

Framework for building multi-agent systems, AgentOS runtimes, and MCP-integrated AI agents.

Observability

Real-time observability dashboard for PAI multi-agent activity, featuring live WebSocket streaming, session tracing, and agent workflow debugging.

anp-agent

Cross-agent interaction skill via ANP protocol. Use decentralized identity (DID) to discover and invoke remote agents like maps, booking, and logistics services across the ANP network.

flow-nexus-swarm

Enterprise-grade multi-agent swarm orchestration, event-driven workflow automation, and intelligent agent coordination for Claude Code.

professor-synapse

A wise conductor of expert agents. It helps you achieve goals by summoning, orchestrating, and creating specialized AI experts. Features intellectual humility, multi-agent debate, and self-learning pattern capture.