Agent Skills Hub

codex

Delegates coding tasks to the OpenAI Codex CLI for features, refactoring, PR reviews, and automated issue fixing within Git repositories.

go

Autonomous recursive execution engine for indiiOS that manages task completion, state verification, and error handling.

recursive-decomposition

Handles large-scale tasks by automatically breaking them down into manageable, recursive sub-tasks to overcome context window limits and improve reasoning accuracy on large codebases and document sets.

pr-review-fix-loop

Orchestrate an automated PR review-fix loop. Dispatches subagents to analyze code, CI status, and comments, then applies iterative fixes until the PR reaches a passing state.

claude

Anthropic Claude AI models for high-performance coding, large-context analysis, and GUI interaction.

posit-news

Fetch and aggregate the latest Posit news, blog posts, podcast episodes, video content, and event announcements using automated sub-agents.

nuwa-skill

A perspective engineering engine that researches, extracts mental models, and generates runnable persona skills based on deep expression DNA analysis.

using-skills

Mandatory workflow skill for managing conversation state, enforcing skill discovery, and ensuring task adherence through TodoWrite checklists.

cross-plugin-detective

Standardized detective skill integration for agent roles. Maps agents to code-analysis skills and enforces claudemem usage for memory-indexed code investigation.

moltbot-arena

AI agent skill for Moltbot Arena, a real-time strategy programming game. Manage units, automate resource harvesting, coordinate structures, and execute tactical decisions via REST API.

ring:writing-skills

A framework for applying Test-Driven Development to process documentation, ensuring agent reliability by using pressure scenarios to identify and patch rationalization loopholes.

vibe-orchestrator

Master workflow controller for Lovable-style, AI-driven development. Instantly generates premium, multi-page, animated applications by routing to specialized sub-agents. No prompts needed—just build.