AI Agent Skills

Browser Harness | Self-healing harness that enables LLMs to complete any task.

Pre-submission AI review stress-test for research papers. A Claude Code skill: review, verdict, revise, verify.

Plan a practical long-form video with test prompts, recording structure, narration beats, screen-recording steps, and production handoff.

RenoDX workflow for creating readable analysis graphs and plots from shader math, CSVs, EXRs, LUTs, hue sweeps, tone curves, gamut comparisons, energy/scalar maps, and t…

Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.

Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.

Review UI code for web interface guidelines, UX quality, accessibility, and interaction design best practices.

Evaluate systematic strategy ideas through signal testing, statistical validation, decay, execution costs, and model-risk review.

Translate Figma designs into production-ready UI code with close visual fidelity and component-level detail.

Create beautiful slides on the web using a coding agent's frontend skills

Open-source LLM-friendly web crawler and scraper for agent workflows.

A Kubernetes controller for Elastic Load Balancers

Cross-CLI skill for Obsidian: turn your vault into a living AI-first second brain across Claude Code, Codex, Gemini, and OpenCode. 43 commands - now with /obsidian-archi…

Turn websites into clean markdown or structured data for retrieval and agents.

Workflow automation for connecting agents to repeated operational tasks.

Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs…