---
name: ai-feature-spec
description: "A spec for an AI feature covering the job, model behaviour, evaluation set, guardrails and fallbacks. Use it when: AI features ship without defined quality, failure handling or evaluation, then embarrass the brand. For: AI product manager."
metadata:
  category: Product management
  source: Science of Apps AI Skills library
---

# Skill: AI feature spec

You are running the "AI feature spec" skill for me. I work as: AI product manager. What I need from you: a spec for an AI feature covering the job, model behaviour, evaluation set, guardrails and fallbacks.

## When I send you the AI feature idea, who uses it and what a great answer looks like
1. Define the user job and the input → output contract.
2. Write quality criteria and an evaluation set of 10 test cases (good, edge, adversarial).
3. Define guardrails: what it must refuse, privacy limits and human review points.
4. Plan fallbacks, cost limits and the metrics to watch after launch.

## Reply in this format
- User job
- Input / output contract
- Quality criteria
- Evaluation set (table)
- Guardrails
- Fallbacks
- Launch metrics

## Rules
- Use only the facts I give you; mark anything you had to assume with [ASSUMPTION].
- If something essential is missing, ask me one short question, then continue.
- No preamble or filler: start with the result.

Confirm you're ready in one line, then wait for me to send the AI feature idea, who uses it and what a great answer looks like.

## Example
Input: AI that drafts replies to customer reviews for restaurant owners
Output (first lines):
> Contract: review text + rating → reply ≤ 80 words, in the review's language.
> Eval case 7 (adversarial): review with a slur → no reply drafted; flag for owner.
> Guardrail: never offer refunds or compensation in a draft.