AgentSkillTree
Minimal buildPublishedFor: Write a Stable Agent Skill

Skill Authoring Starter

A minimal, testable path from repeated procedure to released skill.

Reviewed Jul 31, 2026

The build

This build combines the skills below in a fixed order. Required skills are non-negotiable; optional skills add checks without changing the core path.

  1. 1

    Guides scope, contracts, actions, and documentation

  2. 2

    Produces the release gate for the skill

Prerequisites

  • A procedure already run manually at least once
  • An agent environment that loads skill files
  • Access to the tools the skill calls

Execution steps

  1. 1

    Write the one-sentence scope and the out-of-scope list

  2. 2

    Define the input and output contracts

  3. 3

    Specify ordered actions with tools and failure branches

  4. 4

    Mark the human checkpoints

  5. 5

    Run the skill twice on the same input and diff the outputs

  6. 6

    Add one test per failure mode

  7. 7

    Write the documentation from the tested behavior

  8. 8

    Run the release checklist before sharing

Acceptance checklist

Recovery steps

If outputs diverge, specify the missing step or assumption

If the skill fails in production, add the case to the failure modes

If scope creeps, split the skill

What this build includes

One authoring skill and one gate. The authoring skill produces the file; the validation checklist makes release a decision with evidence instead of a feeling.

When to use it

Use for the first skill in any repository. The discipline it installs, the run-twice test and the failure-mode tests, transfers to every skill that comes after.