Back to directory

Prompt Engineering Toolkit

A collection of 50 standalone browser-based tools for analyzing, refining, scoring and building prompts for large language models, each a single HTML file with no build step.

Prompt Engineering Toolkit

Prompt Engineering Toolkit is a collection of 50 standalone web tools for crafting, analyzing and refining prompts for large language models. Each tool is a single HTML file with inline CSS and JavaScript, runs entirely in the browser with no dependencies or build step, and works offline.

The tools are grouped by purpose: prompt analysis and scoring, persona builders for roles such as expert, teacher or recruiter, prompt refiners that expand, simplify or reformat a prompt, a sandbox and version tracker for testing and comparing prompts, purpose-built builders for content such as blog posts or resumes, and generators for zero-shot, few-shot and chain-of-thought prompting.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.