Agent Skills Hub

synapse-a2a

Framework for multi-agent collaboration using the Google A2A protocol. Enables messaging, task delegation, and cross-agent coordination for CLI-based AI tools.

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.

document

Interactive terminal canvas for rendering, editing, and selecting markdown text, emails, and project documentation in Claude Code.

iterating

Stateful, multi-session workflow manager that uses Work Logs to persist context, enable checkpoints, and manage iterative progress across long-running tasks.

customer-research

Multi-source research tool for customer inquiries, bug investigations, and account history synthesis with source attribution and confidence scoring.

context-management

Proactive context window management for AI agents via intelligent token monitoring, snapshot creation, and selective state rehydration to maintain continuity during long sessions.

massgen-config-creator

Guide for creating properly structured YAML configuration files for MassGen. Use this when creating new configs for examples, case studies, testing, or feature demonstrations.

sage-mcp-protocol

Sage MCP protocol implementation for integrating external tool servers and standardized AI model context.

scheduling

Create and manage recurring tasks and one-off reminders using natural time inputs or cron expressions to keep your AI assistant organized.

ideate

Capture and formalize software development ideas into structured design documents within the Hashbrown repository, including research and conceptual sketches.

session-reflection-analysis

Analyze Claude Code session history to identify inefficiencies, optimize token usage, and suggest workflow improvements.

self-improve

Self-maintaining skill for OpenCode agents to update documentation, capture learnings, and extend tool/agent capabilities dynamically.