Back to directory

SMART POLE Skill: The Ultimate Context Engine

SMART POLE is a systematic prompt-engineering framework that breaks a request into nine distinct categories of context - such as style, the user's expertise level, the goal, available resources and audience - intended to reduce vague or hallucinated answers from a language model.

SMART POLE Skill: The Ultimate Context Engine

The nine categories, spelled out by the acronym SMART POLE, are Style (the persona the model should adopt), Mastery (the user's own level of understanding), Aim (the goal and how success will be judged), Resource (available tools, budget and data), Time (deadlines and duration), People (values, audience and beliefs), Outline (structure and scope), Locale (domain, industry and context) and Example (snippets to emulate). Filling in each category before writing a prompt is meant to force a language model toward a specific, checkable answer instead of a generic one.

The documentation is bilingual, provided in both English and Vietnamese, and presents the framework as a reusable skill definition rather than a piece of running software.

It is released under the Apache-2.0 license.

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.