Agent Skills Hub

always-works-testing

Mandatory execution-based validation for all software implementation tasks. Ensures code works through empirical verification before confirmation.

claude-skills

A comprehensive library of 305+ modular instruction packages, Python CLI tools, and agent workflows designed to extend the capabilities of AI coding assistants like Claude Code, Cursor, Aider, and Gemini CLI.

moollm

A microworld operating system for LLM-based agent living memory, transforming filesystems into navigable rooms and code into habitable worlds.

cyber-ir-playbook

Generate incident response timelines and structured report packs from event logs to facilitate efficient detection-to-recovery tracking.

ring:using-tw-team

Technical writing specialists for functional and API documentation. Dispatch to create compliant guides, conceptual docs, and API references following the ORCHESTRATOR principle.

clean-code

Pragmatic AI-assisted coding standards focused on clean code, simplicity, and maintainability. Enforces best practices like SRP, DRY, and KISS to prevent over-engineering.

legal-risk-assessment

Assess and classify legal risks using a severity-by-likelihood framework. Evaluate contract risk, deal exposure, and issue severity to determine if senior counsel or external review is required.

langchain-chat-models

A unified interface for integrating and managing LLM chat providers like OpenAI, Anthropic, Google, Azure, and Bedrock within LangChain applications.

customer-research

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

hegelion

Dialectical reasoning and adversarial coding agent for MCP-enabled editors, forcing LLMs to resolve internal contradictions for higher quality outputs.

paper-write

Drafts LaTeX research papers section-by-section using paper plans and research narratives with multi-model reviewer validation.

design-review

Designer's eye QA: detects and automates fixes for visual inconsistencies, spacing, hierarchy, and UI polish issues. Iteratively verifies with before/after screenshots.