Agent Skills Hub

maestro

Intelligent RAG-based gateway that routes coding tasks to specialized Swift/iOS expertise without context window bloat. Uses MCP to retrieve precise patterns from 100+ indexed skills.

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.

plan

Structured 6-phase workflow for planning and implementing features, skills, and architectural changes with automated tool discovery and safety verification.

test-skill

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

gskills-forge

Professional Gemini CLI Skill Architect: specialized in scaffolding new skills, converting Claude Code tools to Gemini, and refactoring/optimizing existing CLI orchestrators.

vibesafe

Manage Vibesafe units to scan, generate, test, and verify AI-written code with cryptographically-secure hash-locked checkpoints.

inno-prepare-resources

Automates research resource preparation by loading instances, searching GitHub for codebases, building dataset descriptions, and downloading arXiv papers.

swift-style

Standardized Swift coding conventions, naming rules, and idiomatic patterns for clean, maintainable, and readable iOS/macOS development.

resolve-pr-comments

Review, fix, and resolve GitHub PR review comments automatically.

ReasoningBank with AgentDB

Implement ReasoningBank adaptive learning with AgentDB's ultra-fast vector backend. Features trajectory tracking, verdict judgment, memory distillation, and pattern recognition for self-learning autonomous agents.

paperbanana

Generate publication-quality statistical plots from CSV or JSON data files using AI-driven automated visualization.

lint-fix

Automated code maintenance loop using Trunk to perform linting, formatting, and iterative error resolution.