Agent Skills Hub

ai-llm-patterns

Anthropic Claude integration patterns: streaming, RAG with pgvector, tool use, model selection (Haiku/Sonnet/Opus), prompt caching, and cost management for AI-powered engineering.

massive-context-mcp

Process massive files and large codebases (10M+ tokens) by recursively chunking, sub-querying, and aggregating results to overcome LLM context limits.

web-artifacts-builder

A toolkit for developing and bundling complex, multi-component React/TypeScript web artifacts using Vite, Tailwind CSS, and shadcn/ui.

metacognition

Enforces structured self-assessment checkpoints to validate approach, mitigate risks, and ensure quality before, during, and after task execution.

zai-cli

Execute z.AI CLI for multimodal analysis, web search, reader, and GitHub repo exploration via CLI and MCP.

structured-outputs-advisor

Expert advisor for implementing Anthropic's structured outputs. Choose between JSON mode and strict tool use for guaranteed schema compliance and validated agentic workflows.

subagent-driven-development

Execute implementation plans using isolated subagents for each task, featuring a rigorous two-stage review process for spec compliance and code quality.

hipocampus-flush

Manually triggers a Hipocampus memory flush to persist current session context to raw logs and initiate the compaction tree process for long-term agent memory maintenance.

qa-tester

Specialized QA testing agent for morphir-dotnet, covering test plans, regression, E2E verification, bug reporting, and package validation.

manage-worktree

Manage git worktrees: create, move branches into, or remove worktrees. Simplifies parallel development, context switching, and cleanup for Apartment-based Rails projects.

data_processor

A multi-paradigm ETL pipeline agent supporting batch and streaming data processing, schema inference, and configurable DAG-based transformations for heterogeneous data sources.

test-driven-development

Enforces disciplined Test-Driven Development (TDD) by requiring a failing test before implementation, ensuring code reliability and preventing premature over-engineering.