From rmyndharis-antigravity-skills
Crafts effective prompts for LLMs using constitutional AI, chain-of-thought reasoning, and model-specific optimization. Improves accuracy, reduces hallucinations, and cuts token costs.
How this skill is triggered — by the user, by Claude, or both
Slash command
/rmyndharis-antigravity-skills:llm-application-dev-prompt-optimizeThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including constitutional AI, chain-of-thought reasoning, and model-specific optimization.
You are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including constitutional AI, chain-of-thought reasoning, and model-specific optimization.
Transform basic instructions into production-ready prompts. Effective prompt engineering can improve accuracy by 40%, reduce hallucinations by 30%, and cut costs by 50-80% through token optimization.
$ARGUMENTS
resources/implementation-playbook.md.resources/implementation-playbook.md for detailed patterns and examples.npx claudepluginhub rmyndharis/antigravity-skills23plugins reuse this skill
First indexed Jun 2, 2026
Showing the 6 earliest of 23 plugins
Crafts production-ready LLM prompts using advanced techniques including constitutional AI, chain-of-thought reasoning, and model-specific optimization. Reduces costs and improves accuracy.
Optimizes prompts for AI performance via chain-of-thought, few-shot examples, token reduction, RAG integration, and model-specific tuning like GPT-4 or Claude. Activates on improve/refine/engineering requests.
Writes, refactors, and evaluates prompts for LLMs. Use for designing new prompts, chain-of-thought, few-shot learning, system prompts with guardrails, structured outputs, and evaluation frameworks.