Agent Skills Hub

context-bar

A color-coded, real-time context usage progress bar for the Claude Code statusline and manual on-demand checks.

rag-engineer

Architect and optimize production-grade RAG systems. Master embedding models, vector databases, chunking strategies, and retrieval pipelines for high-accuracy LLM applications.

newsletter-events-write

Generate professional markdown newsletters from localized events stored in SQLite. Automates event aggregation, curation, and formatting for community or niche media newsletters.

debug

Debug package implementation guide for LobeHub. Provides standardized logging patterns, namespace conventions, and configuration for browser, Node.js, and Electron environments.

snowflake-semanticview

Create, alter, and validate Snowflake semantic views using the Snowflake CLI.

import-content

Manually import markdown files into the Kurt database, fix ingestion errors, and manage document metadata via local file system synchronization.

claude-api

Expert guidance for Claude Messages API: structured outputs, prompt caching, tool use, and migration from deprecated Claude 3.x models to 4.5. Prevents common API errors.

rspack-sftrace

Trace Rspack Rust function calls using LLVM XRay for performance analysis, troubleshooting, and visualization of execution flow.

evaluation

Build systematic evaluation frameworks for AI agents using multi-dimensional rubrics, LLM-as-a-judge, and regression testing to measure performance, quality, and context engineering effectiveness.

investigate-dependencies

Conduct thorough dependency audits to identify redundant code, unused features, and improper usage patterns. Ensures project modularity by leveraging existing dependencies instead of reinventing functionality.

financial-analyzing

Analyze financial data, calculate key performance metrics like margins and ROI, and generate structured analytical reports.

ragcode-sse

Directly interface with RagCode MCP via SSE protocol without complex configuration files or binary dependencies.