Guide structured development of Claude Code skills with a 9-step workflow.
npx skills add https://github.com/tc9011/my-skills --skill skill-forge-tc9011
Please help me install this Agent Skill. Skill: skill-forge Source: https://github.com/tc9011/my-skills/tree/main/skills/skill-forge Command: npx skills add https://github.com/tc9011/my-skills --skill skill-forge-tc9011
This Skill addresses the common issue of poorly structured and low-quality AI skills by providing a comprehensive framework and best practices for their design, development, and packaging.
scripts/, references/, and assets/ for modularity and token efficiency.Use the skill-forge skill to begin building a new Claude Code skill.
High-intent search queries and answers about installing and using this skill.
Production-grade Claude Code skills are built using a structured 9-step workflow that enforces best practices like Iron Laws and progressive loading. This methodology ensures token efficiency, reliability, and proper skill architecture through prompt engineering and packaging.
AI skill prompt engineering best practices involve applying Iron Laws, workflow checklists, and confirmation gates to define behavior. Effective workflow design also requires documenting anti-patterns and utilizing progressive loading for optimal token efficiency.
To structure scripts and references for modular AI skill development, separate these components into distinct directories to enable progressive loading. This resource management strategy ensures token efficiency and maintains skill reliability during execution.
Claude Code skill development requires managing token efficiency through progressive loading and explicitly documenting anti-patterns. Addressing these constraints ensures that skills trigger correctly, handle user input safely, and provide reliable output without context overflow.
The step-by-step workflow for creating and packaging new AI skills involves a 9-step process covering architecture, workflow design, prompt engineering, and packaging. This structured methodology ensures high-quality, production-ready skill outputs through modularity and reliability.
ResearAIStandardize a reference object for quest evaluation with plan and checklist requirements.
Galaxy-DawnCreate Claude Code skills with frontmatter, structure, and progressive disclosure.
j-showDesign, develop, and package AI agent skills with structured workflows.
dige04Design and refine prompts and agent personas with structured YAML frontmatter.