Agent Skills Hub

research-pipeline

End-to-end autonomous research agent: from idea generation and literature review to experiment execution, adversarial review loops, and paper writing.

linkedin-lead-gen

Automated LinkedIn lead generation for tech services. Identifies non-tech founders, performs website gap analysis, and generates professional PDF audit reports for high-value B2B outreach.

multi-agent-patterns

Architect multi-agent systems to overcome context limits, using patterns like supervisor, swarm, and hierarchical models to manage complex workflows.

logo-creator

Create professional logos using AI. Generate, refine, crop, remove backgrounds, and export as SVG. Perfect for brands, mascots, icons, and emblems.

english-text-editor

Provides targeted, concise English language editing and stylistic improvements for text without performing full rewrites.

requirements-clarity

Clarify ambiguous requirements through systematic dialogue and scoring to ensure high-quality, actionable PRDs before starting implementation.

iterate

Autonomous improvement loop for codebase optimization. Automatically modifies, measures, and iterates on code based on a specific goal and mechanical metric.

migrate-to-vinext

Automated migration tool for converting Next.js projects to vinext (Vite-based Next.js reimplementation), including compatibility scanning, dependency replacement, and configuration setup.

training-data-curation

Guidelines for curating high-quality datasets for LLM post-training (SFT/DPO/RLHF), covering data formats, quality filtering, and collection strategies.

book-illustrator

Expert guide for children's book illustration covering age-appropriate styles, character design, color theory, and visual storytelling for 0-12 year olds.

llm-integration

A toolkit for building robust LLM integrations: API patterns, streaming, function calling, RAG pipelines, and cost-effective model routing.

context-cascade

A nested plugin architecture for Claude Code that optimizes context by dynamically loading playbooks, skills, and agents to save over 90% in token usage.