kanso-prompting

Name: kanso-prompting
Availability: InStock
Author: Blake

Standardize prompt engineering with structural rules and behavioral principles for frontier LLMs.

2|Updated Apr 23, 2026

Search Tags:#optimization #llm #claude #reasoning #agentic #prompting

Ready to run

npx skills add https://github.com/blakecyze/kanso --skill kanso-prompting

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: kanso-prompting
Source: https://github.com/blakecyze/kanso/tree/main/skills/kanso-prompting
Command: npx skills add https://github.com/blakecyze/kanso --skill kanso-prompting

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill addresses the common issue of vague or inefficient prompting that leads to poor, verbose, or hallucinated AI output by enforcing a structured, outcome-oriented approach to prompt engineering.

Core Features & Use Cases

Prompt Taxonomy: Provides a standardized framework for structuring complex prompts using tags and clear hierarchies.
Frontier Model Optimization: Implements modern best practices for current models, such as avoiding outdated anti-laziness scaffolds and prioritizing declarative instructions.
Self-Correction: Integrates verification steps into prompts to ensure high-stakes output meets defined criteria before completion.

Quick Start

Ask the assistant to rewrite your current task description using the kanso prompting principles to ensure maximum clarity and efficiency.

Frequently Asked Questions about kanso-prompting

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I structure prompts for frontier LLMs to improve reasoning depth?▼

To improve reasoning depth in frontier LLMs, structure prompts using declarative, outcome-first, and context-aware patterns. This enforces clear hierarchies and tags to minimize ambiguity and maximize model performance.

What is the best way to stop Claude from generating verbose or hallucinated output?▼

The best way to stop verbose or hallucinated output is to apply standardized prompt engineering. This uses structural rules and behavioral principles to enforce an outcome-oriented approach for current models.

How do I add self-correction steps to LLM prompts for high-stakes tasks?▼

Add self-correction to LLM prompts by integrating verification steps into the task description. This ensures the output meets defined criteria and completes required reasoning checks before finishing.

Do I need outdated anti-laziness scaffolds for agentic tasks with current LLMs?▼

You do not need outdated anti-laziness scaffolds for agentic tasks with current LLMs. Modern prompt optimization prioritizes declarative instructions and structural rules to improve instruction following.

Can I use this prompt taxonomy across all agentic tasks?▼

You can use this prompt taxonomy across all agentic tasks. It provides a standardized framework that operates universally to improve instruction following, output quality, and reasoning depth.