Agent Skills Hub

review-and-qa

Perform comprehensive code reviews and generate QA test plans for Storyblok projects, ensuring quality, security, and adherence to best practices.

tool-design

Expert framework for designing agent-facing tools, optimizing tool descriptions, enforcing contract-based APIs, and implementing architectural reduction for reliable AI agent tool selection.

lofy-career

Automated job search management for the Lofy AI assistant: track applications, tailor resumes, prepare for interviews, manage follow-ups, and analyze career pipelines.

link-strategy

Strategic internal linking, anchor text optimization, and site architecture planning for improved SEO and content topical authority.

hegelion

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

agentdb-state-manager

Persistent state management and workflow analytics using DuckDB for task dependency tracking, historical metrics, and context checkpointing.

tapestry

Unified content extraction and action planning engine. Automatically processes URLs (YouTube, articles, PDFs) into actionable plans.

feishu-weekly-report

Generate professional weekly reports by aggregating Feishu chat history and local daily memory logs into a structured template.

multi-llm-advisor

Fetches expert perspectives from OpenAI Codex and Google Gemini for architecture, code reviews, and debugging, with transparent LLM synthesis.

content-trend-researcher

An advanced research intelligence skill for content creators and marketers that analyzes trends across 10+ platforms to generate data-driven content outlines based on user intent.

memcontext-autopilot

An automated memory middleware for AI agents, implementing a Retrieve-Respond-Save loop to maintain long-term persistent context across conversations.

command-executor

Safely execute, test, and verify commands discovered in documentation with real output capture, performance tracking, and git-aware safety protocols.