Agent Skills Hub

stream-validator

Validate WebSocket and HTTP stream health for WaveCap-SDR. Measure latency, throughput, packet loss, and signal quality for audio, spectrum, and IQ streams.

submit-work

Submit completed tasks on OpenAnt via CLI. Handles text reports, file uploads (images, docs, code), and external proof links to ensure verified deliverables.

geopandas

Python library for geospatial vector data analysis. Perform spatial joins, geometric operations, coordinate transformations, and mapping using GeoPandas, shapely, and interactive tools.

plugin-best-practices

Validates Claude Code plugins against architectural standards, checking manifest files, frontmatter, and tool invocation patterns to ensure high-quality, compliant plugin development.

evidence-first-debugging

Enforces a strict evidence-based debugging workflow using structured observation, hypothesis testing, and causality validation to eliminate speculation in technical investigations.

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.

clawsec-nanoclaw

Security advisory monitoring for NanoClaw WhatsApp bots, providing vulnerability scanning, skill safety checks, and integrity protection through MCP tools.

document-writer

A documentation-writing assistant for the Nuxt ecosystem, providing writing style guides, MDC component usage patterns, and content structure guidelines for technical blog posts and docs.

orchestrator

Autonomous multi-agent orchestration framework for Claude Code with memory-driven workflows, parallel-first task execution, Aristotle-based deconstruction, and multi-stage quality gates.

file-todos

A structured file-based system for tracking todos, managing technical debt, and coordinating code review workflows directly within your repository.

looped-builder

Scaffold complex, multi-step coding tasks into actionable implementation plans and execute them autonomously using a Claude-driven bash loop.

test-skill

A testing fixture for validating AI agent skill configurations and detecting rule violations.