Skip to content
Back to search

product-bench

Product management skills that draft, so PMs can decide. From product brief to engineering project.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/taylortyler-1--product-bench/badge.svg)](/listings/taylortyler-1--product-bench)

HTML

<a href="/listings/taylortyler-1--product-bench"><img src="/api/listings/taylortyler-1--product-bench/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 18 lines
  1. # product-bench
  2. **Status:** In Progress
  3. Product management skills that draft, so PMs can decide.
  4. product-bench takes a feature from product brief to a ready-to-build engineering project. Each skill produces a draft, and a person approves it before the next step starts. The AI handles the document work. You keep the decisions.
  5. Works with Claude Code and any agent that supports the [Agent Plugins](https://agent-plugins.org/) standard, including Cursor, VS Code, GitHub Copilot and Codex. Packaged with [fanout](https://github.com/taylortyler-1/fanout).
  6. ## The idea: draft, don't decide
  7. Most AI product tools try to write the final version. product-bench doesn't. Every skill is named draft-* because nothing it produces is final until a person approves it.
  8. - People own the problem. The brief, which says who has the problem and why it matters now, comes from the PM. draft-product-brief asks questions and organizes your answers. It never invents the problem.
  9. - Every step has an approver. Each draft is reviewed before it feeds the next skill.
  10. - Engineers own the build. The workflow stops at the engineering project. Developers write the tickets and decide how the feature gets built.
  11. - Requirements are testable. User stories come with Gherkin scenarios, so reviewers check concrete behavior instead of skimming prose.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.