Back to directory

Perfect Prompts

A filesystem-first library of prompts, rules, personas and other reusable AI-agent assets that lives as plain files in git, with an optional desktop app for indexed search and one-click use.

Perfect Prompts

Perfect Prompts organizes prompts, persistent agent instructions, procedural skill packages, scoped rules, architecture and research standards, and role personas as plain files in a repository, browsable directly in a file manager, editor or GitHub without any application required. Within its prompt collection, portable prompts are kept in directly inspectable form, runtime bindings embed the same prompts in Python, TypeScript, Rust and Go source for use from application code, and templates hold reusable prompt-template families.

An optional desktop application, also called Perfect Prompts, adds indexed search in plain English, batch queries across the library, previews, and one-click actions to use or remove an artifact, but the files remain the source of truth rather than a proprietary database. Active development has moved to a separate organization.

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.