Agent Skills Hub

prompt-improver

Enriches vague prompts by performing codebase research and asking targeted questions to clarify user intent before execution.

data-viz-plots

Create publication-quality plots and visualizations using matplotlib and seaborn. Works locally with any LLM.

agents-md-generator

Generate hierarchical, token-efficient AGENTS.md files for AI coding agents to provide repository-wide context and project-specific guidelines.

deep-thinking

A deep reasoning protocol that ensures systematic analysis, multi-hypothesis generation, and rigorous verification for complex architectural, debugging, and high-stakes tasks.

receiving-code-review

Rigorous, non-performative code review reception for AI agents, prioritizing technical verification and YAGNI over passive agreement.

context-optimization

Optimize agent context windows through KV-caching, observation masking, summarization-based compaction, and context partitioning to reduce costs and latency.

managing-blog-ideas

Manage the full lifecycle of blog posts, from initial concept and outlining to drafting and editorial refinement for Nuxt/Vue developers.

data-storytelling

Transform raw data into compelling, decision-driving narratives using visualization strategies, story frameworks, and persuasive structures for analytics and executive reporting.

structured-outputs-advisor

Expert advisor for implementing Anthropic's structured outputs. Choose between JSON mode and strict tool use for guaranteed schema compliance and validated agentic workflows.

find-skills-combo

Discover and recommend combinations of agent skills to complete complex, multi-faceted tasks using Maximum Quality or Minimum Dependencies strategies.

help

Interactive guide for workspace discovery, providing access to specialist agents, automated workflows, CLI tools, and active lifecycle hooks.

office-sprite

Generate and process 16-bit pixel art office assets for the Claude Office Visualizer using Nano Banana MCP and multi-pass ImageMagick workflows.