“Prompt engineering”

Design pegRNAs for prime editing using PrimeDesign algorithms.

Build a self-contained, copy-ready research prompt through a bounded prompt-reversal, critique, schema, review, and verification loop.

Background daemon that builds dependency topology, identifies tech debt hotspots, and incrementally refactors legacy code

Runs systematic self-review on AI-generated output before it's accepted.

Use for community/self-hosted n8n workflow development with reuse-first, validation-first GitOps delivery

Optimize Claude Code permissions by finding safe Bash commands from session history and auto-applying them to settings.json.

Build type-safe LLM applications with DSPy.rb — Ruby's programmatic prompt framework with signatures, modules, agents, and optimization.

Reviews a calendar month of local Codex sessions and their follow-up tasks to improve agent interactions.

Fast, lightweight 2D rendering engine for creating interactive graphics, particle effects, and canvas-based applications using WebGL/WebGPU.

Building applications ON Claude - the Anthropic API and Claude Agent SDK.

Master hub for AI, MCP & prompting.

Versatile JavaScript animation engine for DOM, CSS, SVG, and JavaScript objects.

Blender to web export workflows for 3D models and animations.

Generate professional, platform-specific social content and related image prompts aligned to a consistent personal or company brand voice.

Lead qualification engine with conversational intake.

Modular orchestration of agent patterns from Anthropic's engineering guide.

Create, tighten, or review runnable /goal contracts for coding agents.

Run metric-driven iterative optimization loops.

This skill should be used when generating and editing images using the Gemini API (Nano Banana Pro).