Skip to content
Product

Working Backwards

Refound AI

Clarify a proposed product through a hypothetical announcement and difficult customer questions.

SKILL.md

---
name: knoveya-working-backwards
description: "Clarify a proposed product through a hypothetical announcement and difficult customer questions. Use for matching product work."
---

# Working Backwards

## Scope

Apply this guidance when the requested task matches the description. Honor the user's chosen outcome, repository rules, and existing authorization.

## Workflow

Clarify a proposed product through a hypothetical announcement and difficult customer questions.

Before acting, inspect the relevant artifact and ask only for information that materially changes the result. Use existing tools and conventions; do not install dependencies, publish, send messages, deploy, or mutate external data unless the user has authorized that operation.

## Acceptance check

Future capability remains labelled hypothetical until implemented.

## Example task

Test whether a proposed benefit is compelling before specifying screens.

## Report

State what changed, the evidence checked, and what remains unverified. Do not claim a successful operation or completed test without observing it.

How to use

Copy the full block, including its frontmatter, into a new folder named knoveya-working-backwards as SKILL.md. Review the instructions before enabling them. For Codex, a user skill normally lives in ~/.codex/skills/knoveya-working-backwards/SKILL.md; check the current documentation for another agent's supported location. Do not overwrite an existing skill.

This is an independent Knoveya skill. No files are installed by this website.

Example

Test whether a proposed benefit is compelling before specifying screens.

Verify

Future capability remains labelled hypothetical until implemented.

Test the skill on a small, authorized example. File validation alone does not prove that an agent will make good decisions.

Limits

The skill supplies instructions, not tool access or expertise guarantees. Inspect generated work and preserve the user's approval boundaries.