Free Agent Builder resource

Build fewer agents. Capture better methods.

A practical seven-part test and worked starter package for deciding when a repetitive task should become a reusable skill.

No signup. One top-level folder. Includes SKILL.md, a template, and three release tests.

AIA Copilot Agent Builder Skill Starter Kit cover

The operating model: let the agent hold the stable role and let each skill hold one bounded, testable method. Do not turn a vague procedure into a skill until its trigger, inputs, steps, output, quality checks, evidence, and stop rule are explicit.

AIA Skill Fit Test

Before a task becomes a skill, require seven things

1

Recognizable trigger

When should the method activate?

2

Defined inputs

What must be available before work begins?

3

Repeatable steps

What sequence should it follow?

4

Required output

What exactly must it produce?

5

Quality checks

What must it verify before returning the result?

6

Verifiable evidence

How can a person check the answer?

7

Stop rule

When must it ask, refuse, or escalate?

Inside the download

A worked weekly-brief example

The package shows how to turn supplied project information into a concise leadership brief while preserving evidence, supported owners and dates, and explicit escalation behavior.

Download the starter package
weekly-work-brief/ SKILL.md references/test-cases.md templates/brief-template.md
Preview note: Skills availability and behavior can vary by tenant. This worked package has not yet been validated in Scott Hay's tenant. Test it in your target tenant before relying on its output, especially for important work.

Need help turning repetitive work into a controlled AI workflow?

Start with the business task, evidence, boundaries, and stop rule before choosing the implementation.

Book an AI Time Back Audit