Index of every page on this site: llms.txt
All skills
erkamyaman avatar

/outcome-prompting

@7fcc555
Run it yourself

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 2 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/erkamyaman/dhh-p-bloom-agent-skills/outcome-prompting

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈42 tokens for metadata: the name and description. ≈352 when used: this file. ≈177 more on demand in 1 file.

Description uses 2.1% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈169 characters, or 2.1%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Outcome prompting

Inspired by DHH's Rails World 2026 keynote: https://www.youtube.com/watch?v=vDjW_dRyKXY

From the talk

DHH says agents can now be given problems or outcomes instead of tasks. He warns against being overly prescriptive: a beginner's mindset and higher-level prompts work better. The brief format, acceptance checks and template below are our additions, not from the talk.

Describe the problem and the result you want. Let the agent choose the implementation. Over-specifying steps caps the agent at your own knowledge.

When to use

  • Starting any feature, fix or refactor with an agent.
  • A previous prompt was a long list of steps and the result was mediocre.

Steps

  1. Write the problem in one or two sentences (who is affected, what hurts).
  2. Write the outcome as observable behaviour ("a user can ... and sees ...").
  3. List constraints only where they really exist (platform, API limits, style rules, files not to touch).
  4. Add acceptance checks the agent can run itself (tests, a command, a screenshot comparison).
  5. Leave the implementation open. Do not name functions, files or libraries unless required.

Verification

Run the acceptance checks. If they pass but the behaviour is wrong, the checks were too weak: tighten them and re-run instead of adding more steps to the prompt.

See references/brief-template.md for a fill-in template.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at 7fcc555. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Activeupdated 2 months ago

README badge

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