AI & LLM

test-skill-1 @dmgrok

test-skill-1 skill

deno-sandbox @denoland

Use when building features that execute untrusted user code, AI-generated code, or need isolated code execution...

deno-frontend @denoland

Use when building web UIs with Fresh 2.x framework, using Preact components, or adding Tailwind CSS styling in Deno....

dynamic-agent @memgrafter

Dynamically generate and execute a specialized agent for any task. Use when the user has an arbitrary task that...

coding-agent @memgrafter

AI coding agent that plans, implements, and verifies code changes with human approval gates. Built on FlatAgents.

codebase-ripper @memgrafter

Out-of-band codebase exploration using a cheap/fast model. Keeps your context clean while a cheap model runs 30-80...

codebase-explorer @memgrafter

Explore a codebase to gather context for coding tasks. Preserves context window and offloads work to cheaper models.

html-to-generateblocks @wpgaurav

Convert HTML/CSS layouts to GenerateBlocks V2 format with inline styles

generateblocks-layouts @wpgaurav

Build layouts using GenerateBlocks V2 elements for WordPress

figma-to-generateblocks @wpgaurav

Convert Figma designs to GenerateBlocks V2 format for WordPress

elementor-to-generateblocks @wpgaurav

Convert Elementor layouts to clean GenerateBlocks V2 format, eliminating DIVception

skill-creator @ValorVie

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an...

eval-harness @ValorVie

A formal evaluation framework for Claude Code sessions, implementing eval-driven development (EDD) principles.

continuous-learning @ValorVie

Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.

ai-instruction-standards @ValorVie

|

ai-friendly-architecture @ValorVie

|

ai-collaboration-standards @ValorVie

|

ui-exploration @felix-huber

Guide UI design exploration using tasteboard for references, keystone for primary screen, and variants for...

review-loops @felix-huber

Implements Doodlestein's iterative review methodology. Contains exact prompts for plan review, beads review, code...

phase-transitions @felix-huber

Contains the actual prompts and iteration requirements for each workflow phase. Use these prompts directly - they...

parallel-execution @felix-huber

Orchestrate parallel task execution with dependency analysis and self-healing. Use when running Ralph with multiple...

oracle-integration @felix-huber

Provides Oracle CLI integration for GPT-5.2 Pro review loops. Use when running external model reviews, multi-model...

agent-browser @felix-huber

Browser automation for E2E testing. Use when testing user journeys, verifying UI behavior, or running end-to-end tests.

doc-audit @danielaskdd

Intelligent document audit system for syntax and semantic verification, legal or technical document compliance...