Skills on Start AI Tools - Presented by Intent Solutions

Global Skill Schema and a Prediction Markets Vertical

Fri, 05 Dec 2025 10:00:00 -0600

106 files. 11,951 lines. The day split into two halves: standardizing how skills get built, then proving the standard works by building a new vertical from it. Standards that exist without implementations are aspirational. Standards that ship with a working example are real.

Global Standard Skill Schema

The 8 skills from Dec 1 followed a structure. But that structure lived in tribal knowledge and copy-paste. Today it became a formal specification.

v1.2.0: Every Skill to 100% Compliance

Thu, 04 Dec 2025 10:00:00 -0600

24 commits. One release. The entire day was compliance remediation. Not the glamorous kind of engineering. The kind that makes everything else work correctly.

The Starting Point

The skills infrastructure built on Dec 1 had the right structure but loose compliance. Each SKILL.md file scored between 38% and 40% against the compliance checker. Missing required fields, incomplete schemas, permissions that didn’t match actual plugin requirements, usage examples that wouldn’t parse.

Skills Infrastructure from Scratch: 8 SKILL.md Files, an Installer, and a Compliance Framework

Mon, 01 Dec 2025 10:00:00 -0600

53 files. 13,445 lines. One goal: give the Nixtla workspace a skills layer that doesn’t exist yet.

What Needed Building

The Nixtla workspace had plugins. It had documentation. It had release discipline. What it didn’t have was a way for external tools to discover and invoke its capabilities through a standardized interface.

Skills are that interface. A SKILL.md file declares what a skill does, what inputs it needs, what outputs it produces, and what permissions it requires. An installer package reads those declarations and wires them into Claude Code. A demo project proves the whole chain works end-to-end.