llm-prompt

346 reusable character attributes for AI agent personas — compose, measure, and port system-prompt personas. Build once. Keep personality everywhere.

Rewrite AI-generated text to sound human. 3-pass editing system with 36+ banned words, 10 structural patterns, and a quality checklist. Works with any LLM — Claude, ChatGPT, Gemini, Cursor, Windsurf. Also available as a Claude Code plugin.

LLM prompt kit that converts recipes from photos, URLs, or text into schema.org/Recipe JSON-LD for Mealie import

A Claude skill that teaches while answering, verifies facts live, explains jargon in plain language, and removes AI fluff — for everyone, on every topic.

An autonomous Application Security (AppSec) prompt and skill module for AI coding assistants (Antigravity, Cursor, Copilot). Converts vibe-coded apps into secure production software

Self-Improving Prompt Optimizer built in Elixir

Prompt Engineering Tool: Anti-Ambiguity × Web Pre-Search × ELO Ranking — forge production-grade AI prompts for Claude, GPT, and agent systems

Open-source eye, ear and skin learning prompt for concise point-of-care guidance

Codebase Health Audit Prompt

Разбор фотографий: пришлите ссылку нейросети и пачку кадров, получите разбор, какой оставить и что удалить. Работает с телефона, ничего устанавливать не нужно.

Ultra-fast codebase-to-prompt packer & interactive token optimizer (TUI/CLI) for Claude, ChatGPT & Gemini. Local-first, comment-stripping, secret-scanning.

短视频口播脚本设计方法论：6种可复用模式+情绪曲线+逐段检查清单。不靠焦虑、不靠恐吓、不靠标题党。

一键把任意AI研究论文用纯小白也能看懂的傻瓜式语言讲透——Claude Code Skill & 通用Prompt模板

Evidence-driven AI career stress test skill: task-level AI exposure analysis, 3 AI scenarios, career transition paths, country adapters. Agent Skills spec compliant, bilingual zh/en.

Active Prompt Engineering (APE): a control-layer framework for reducing LLM hallucinations using structured prompting (C+R+V), achieving ~76% reduction without fine-tuning or RAG.

Calibrate LLM responses for high-agency power users, prioritizing rigorous analysis and executive control. Overrides the default, RLHF-driven tendency toward immediate, ungrounded solutions that serve lower-agency 'LLM as magic tool' workflows.

AI-powered reactive dog training coach — force-free, evidence-based, breed-aware. Standalone skill for Claude, ChatGPT, or any LLM.

A guided somatic body-scan meditation + a prompt that turns any LLM into a gentle body-signal interpreter. Built on Nummenmaa et al., 'Bodily maps of emotions' (PNAS 2014).

Audit code health with AI using evidence-based checks, risk metrics, and prioritized findings for clear refactor decisions