Skillfully guide / article 02

Article 02 / 5 sections

Design the skill contract

Turn the skill from a loose instruction into a contract the agent can execute consistently.

Skillfully Editorial

Skillfully team / Article 02 / 5 sections

Section 01

Inputs the agent can trust

A skill should say which inputs are required and which can be inferred from context. This prevents the agent from filling gaps with guesses.

  • List required paths, URLs, IDs, or account context.
  • State what to do if an input is missing.
  • Keep optional context separate from required context.

Section 02

Tools and files to inspect

The best skills point the agent at the fastest truth path before it starts improvising.

  • Name the first files or routes to read.
  • Prefer repo-local helpers over generic shell exploration.
  • Tell the agent when external lookup is useful.

Section 03

Completion evidence

Completion evidence is the difference between claiming the job is done and proving the job is done.

  • Require the command, screenshot, route check, or diff that proves the result.
  • Make the final answer name the evidence.
  • Avoid proof that depends only on the agent's confidence.

Section 04

Stop rules

Stop rules keep the skill from expanding into unrelated work when it hits uncertainty.

  • Name blockers that require a human decision.
  • State what not to change.
  • Tell the agent when to report partial progress.

Section 05

Feedback prompt

The feedback prompt should ask what happened, what rating fits the run, and what instruction would have helped.

  • Ask for one rating.
  • Ask for a short reason.
  • Ask what to change in the skill next.

Next up

Install feedback collection

Wire Skillfully into the skill without making feedback the main task.

Continue