prompt-repetition
Prompt Repetition
Problem Being Solved
LLMs are trained as Causal Language Models, where each token attends only to previous tokens. This leads to:
- Context-Question Problem: The question is unknown when processing context
- Options-First MCQ Problem: Cannot fully understand the question context when viewing answer choices
- Position/Index Problem: Attention weights weaken for specific position information in long lists
Prompt repetition enables the second pass to reference the entire first pass, effectively mimicking some benefits of bidirectional attention.
When to use this skill
- When using lightweight models: claude-haiku, gemini-flash, gpt-4o-mini, etc.
- Options-First MCQ: Multiple choice where answer choices appear before the question
More from jeo-tech-ai/oh-my-unity3d
bmad-gds
AI-driven Game Development Studio using BMAD methodology. Covers the Execute and Assess phases of the BMAD TEA (Think→Execute→Assess) loop — the core Specification-Driven Development (SDD) cycle. Routes game projects through Pre-production, Design, Architecture, Production, and Game Testing phases with 6 specialized agents. Supports Unity, Unreal Engine, Godot, and custom engines.
11code-review
Conduct thorough, constructive code reviews for quality and security. Use when reviewing pull requests, checking code quality, identifying bugs, or auditing security. Handles best practices, SOLID principles, security vulnerabilities, performance analysis, and testing coverage.
10ralphmode
Configure Claude Code, Codex CLI, and Gemini CLI for Ralph-style automation with fewer approval prompts while keeping project boundaries, secret denylists, and sandbox-first safety rules intact.
10unity-mcp
|
10changelog-maintenance
Maintain a clear and informative changelog for software releases. Use when documenting version changes, tracking features, or communicating updates to users. Handles semantic versioning, changelog formats, and release notes.
9ohmg
Ultimate multi-agent framework for Google Antigravity. Orchestrates specialized domain agents (PM, Frontend, Backend, Mobile, QA, Debug) via Serena Memory.
9