Back to directory

PromptKit

A composable, version-controlled prompt library that snaps together personas, reasoning protocols, output formats and templates into engineered prompts for tasks such as bug investigation and code review.

PromptKit

PromptKit treats prompts as engineered artifacts rather than copy-pasted, untested text, offering 157 components -- 15 personas, 48 protocols, 21 formats, 5 taxonomies and 64 templates across four pipelines -- for software, hardware, mechanical, RF, firmware and protocol engineering tasks.

Three interactive workflows form a domain-agnostic lifecycle and each runs directly inside an LLM session with built-in challenge and verification steps: a spec-extraction workflow scans a repository and extracts structured requirements, design and validation specifications from existing code; an engineering workflow propagates a requirements change through specs and implementation with adversarial alignment audits at each stage; and a maintenance workflow periodically detects where code and specs have drifted apart and corrects both. It requires Node.js 18 or newer and Git, and is installed with npx.

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.