All skills
erkamyaman avatar

/outcome-prompting

@57c6daa

Use when giving an AI coding agent a job. Turns a task into a problem-and-outcome brief with acceptance checks, instead of step-by-step instructions.

  • 2 files
  • 2.3 KB
  • Updated 11 hours ago
  • GitHub

Use this Skill: https://skilld.dev/gh/erkamyaman/dhh-p-bloom-agent-skills/outcome-prompting

This session only. Nothing lands on disk.

referencesbrief-template.md

≈177 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Brief template

## Problem
<who is affected and what goes wrong or is missing>

## Outcome
<what is true when this is done, in observable terms>

## Constraints
- <only real ones>

## Acceptance checks
- <command or test that must pass>
- <behaviour to confirm manually or by screenshot>

## Out of scope
- <things the agent should not touch>

Before and after

Step-by-step (avoid): "Create a service, inject it in the component, add a method that calls the endpoint, then add a loading flag..."

Outcome-level (prefer): "Users on the orders page see a loading state while data loads and a retry button if the request fails. Existing tests pass and a new test covers the failure case."

Source: SKILL.md on GitHub

No third-party reports yet.

Signed by skilld at 57c6daa. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 5 hours ago.

Activeupdated 11 hours ago

README badge

README badge for erkamyaman/dhh-p-bloom-agent-skills/outcome-prompting