Agent Skills Hub

metacognition

Enforces structured self-assessment checkpoints to validate approach, mitigate risks, and ensure quality before, during, and after task execution.

session-reflection-analysis

Analyze Claude Code session history to identify inefficiencies, optimize token usage, and suggest workflow improvements.

skill-authoring-workflow

A standardized workflow for converting raw PM notes, workshops, or rough drafts into polished, validated, and repository-compliant AI skills.

explain-concepts

Explains complex concepts using master teaching frameworks like Feynman, Socratic, and Cognitive Load theory to ensure deep, clear understanding.

ai-collaboration-standards

Prevents AI hallucination and ensures evidence-based, verifiable outputs when analyzing code, reviewing technical documents, or providing recommendations.

agentic-workflows

Build production-grade AI agents using LangGraph, Anthropic/OpenAI/vLLM, and structured outputs. Features streaming, A2A protocol, Pydantic validation, vector memory, and guardrails for resilient, multi-agent workflows.

vibesafe

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

ai-multimodal

Process and generate multimedia with Google Gemini. Analyze audio, images, videos, and PDFs with high-context windows. Supports transcription, visual QA, OCR, and AI-driven image creation.

design-excellence

A design system and anti-pattern guide to make AI-generated UI look human-crafted. Ensures professional aesthetics by managing color, typography, spacing, and animations for the Toh Framework.

code-formatter

Universal CLI tool to convert and synchronize AI agent skills between Claude Code and Gemini CLI extensions.

workflow-execute-plans

Execute implementation plans in small, verifiable batches with pause-for-feedback checkpoints to prevent drift and ensure code quality.

swarm

Orchestrate parallel Claude Code worker swarms with protocol-based behavioral governance for complex features, multi-step refactors, and long-running autonomous coding sessions.