skill-forge

Automate end-to-end creation of Claude Code skills with validation and packaging.

Updated Apr 22, 2026
One-click install
npx skills add https://github.com/Benjamindaoson/Financial_Asset_QA_System_master --skill skill-forge-benjamindaoson
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-forge
Source: https://github.com/Benjamindaoson/Financial_Asset_QA_System_master/tree/main/.agents/skills/skill-forge
Command: npx skills add https://github.com/Benjamindaoson/Financial_Asset_QA_System_master --skill skill-forge-benjamindaoson

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Skill Forge provides a structured, best-practice framework to design, document, and package Claude Skills, reducing churn and ensuring consistent quality across skill units.

Core Features & Use Cases

  • Establish frontmatter-driven SKILL.md templates, progressive loading patterns, and optional resources (scripts, references, assets) that load on demand.
  • Provide a repeatable workflow for planning, implementing, validating, and packaging skills into distributable .skill archives.
  • Use cases include creating new skills from templates, upgrading existing skills, refactoring architectures, and distributing ready-to-use skill bundles.

Quick Start

Initialize a new skill using the included template, fill in all TODOs, validate with quick_validate, and package with package_skill.

Frequently Asked Questions about skill-forge

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

FAQPage Schema
How do I build production-grade Claude skills from scratch?

Production-grade Claude skills are built by automating planning, frontmatter creation, reference building, and validation. This framework enforces architectural guardrails like progressive loading and on-demand resources, ensuring maintainable and scalable skill units across multiple domains.

What is progressive loading in prompt engineering architecture?

Progressive loading in prompt engineering is an architectural pattern that loads optional resources like scripts and references on demand. It enforces scalable skill design by preventing upfront context bloat, keeping Claude skills maintainable and efficient during execution.

How do I package and validate Claude skills for distribution?

Package and validate Claude skills by running automated validation checks against the skill architecture, then bundling the SKILL.md and optional assets into a distributable .skill archive. This ensures the final bundle meets quality standards before deployment.

Do I need pyyaml to use this skill design workflow?

Yes, pyyaml is required as a dependency to use this skill design workflow. It processes the frontmatter-driven SKILL.md templates and validates the structured metadata necessary for the automation scripts to function correctly.

Can I refactor existing Claude skills to use an Iron Law architecture?

Yes, you can refactor existing Claude skills to enforce an Iron Law architecture. The framework supports upgrading current skills by applying structured templates, progressive loading patterns, and validation to align them with production-grade standards.