write-outcomes

Generates one plain-English founder-outcome line from an artefact's technical content.

Updated May 25, 2026
One-click install
npx skills add https://github.com/DATA-AI-XYZ/Tandem --skill write-outcomes-data-ai-xyz
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: write-outcomes
Source: https://github.com/DATA-AI-XYZ/Tandem/tree/main/skills/write-outcomes
Command: npx skills add https://github.com/DATA-AI-XYZ/Tandem --skill write-outcomes-data-ai-xyz

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Technical artefacts like PRDs, stories, and features describe implementation details that founders cannot act on. This Skill converts that technical content into a single plain-English outcome line stating what the founder can now do, keeping founder-facing surfaces free of internal IDs, command names, and jargon. ## Core Features & Use Cases - Outcome Voice Rules: Enforces a one-sentence, second-person or capability-framed style with hard bans on internal IDs, command names, shell syntax, and jargon. - Strict Output Contract: Produces exactly one plain-text line under ~20 words (max 120 characters), with no markdown, labels, or quotes, persisted verbatim to the artefact's outcome field. - Honest Empty Handling: Returns an empty line when the artefact has no shipped capability, so producers leave the outcome blank rather than fabricating value. - Use Case: After drafting a story about dashboard auto-generation, a producer skill applies this rulebook inline to write: "You can now auto-generate dashboards from your requirements — ship faster without wiring widgets by hand." ## Quick Start Ask the producer skill drafting your PRD, feature, or story to apply the write-outcomes rules and add a one-line founder-facing outcome to the artefact.

Frequently Asked Questions about write-outcomes

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I write a founder-facing outcome line for a technical artefact?

Write one plain-English sentence stating what the founder will have or be able to do, using the template "You can now <capability> — <the value it unlocks>." Keep it under 20 words and strip all internal IDs, command names, and jargon.

What is an outcome line in a PRD or user story?

An outcome line is a what-you-can-now-do summary of an artefact: the value a founder gets after it ships. It surfaces user-visible capability rather than implementation details, and is stored verbatim in the artefact's outcome field.

Can users invoke the write-outcomes skill directly?

No. It is an internal support skill applied inline by producer skills such as draft-prd, split-into-features, and split-into-stories. Dispatching it to a sub-agent is an optional fallback under specific conditions, but humans never invoke it manually.

What happens when an artefact has no shipped capability yet?

The skill returns an empty line, and the producer leaves the outcome field blank. It never fabricates value for stubs, placeholder acceptance criteria, or scaffolding-only scope, since an unearned promise is worse than an honest blank.

What are the length and format limits for outcome lines?

Output must be exactly one plain-text line of roughly 20 words, at most 120 characters, with no markdown, labels, or quotes. The bound is agent-enforced and advisory; it is not linted and will not fail a build.