Product Owner

VerifiedCaution

Scans codebase and creates or amends GitHub issues with a Product Requirements Document (PRD). Use for planning features, scoping, and creating issues.

Sby Skills Guide Bot
DevelopmentBeginner
7/22/2026
Claude Code
#prd#github-issues#requirements#feature-planning#codebase-analysis

Recommended for

Automated summary

This skill scans the codebase, drafts a structured PRD, and opens (or appends to) a matching GitHub issue through the gh CLI.

Strengths

  • Clear three-step workflow: scan the codebase, write the PRD, create the issue
  • Standardized issue body (Overview, Problem Statement, Requirements, Acceptance Criteria, Out of Scope) that keeps PRDs consistent
  • Conventional feat(<context>) titles with explicit casing, tense and length rules
  • An amend mode that appends ## Revision blocks while keeping the original PRD immutable
  • Fits into a /po -> /dev -> /review -> /commit -> /pr pipeline

Limitations

  • Requires the gh CLI to be installed and authenticated against an existing GitHub repository
  • The labels it applies (prd, P2: medium) must already exist or be created in the repo
  • Scan quality depends entirely on how much codebase context is loaded into the session
When to use it

Use it when a feature needs to be scoped and turned into a GitHub issue with explicit requirements and acceptance criteria.

When not to use it

Skip it for urgent bug fixes or trivial changes that don't warrant a full PRD.

Security analysis

Caution
Quality score82/100

Nothing destructive, obfuscated, or exfiltrating: the skill only reads the repo and creates/appends GitHub issues through the official `gh` CLI, with no curl|sh, no rm, no credential handling, and no attempts to disable safety. Risk is limited to legitimate but powerful write access to an external service (GitHub issues) plus an undeclared tool surface, which warrants caution rather than a safe rating.

Findings
  • •Uses the GitHub CLI (`gh issue create`) to write to an external service, which requires an authenticated token with repo write scope on the current repository
  • •No `allowed-tools` declared, so the skill's actual tool surface (bash, gh, file reads) is undefined and depends entirely on the host agent's default permissions
  • •`/po amend <issue_number>` accepts an arbitrary issue number and appends content to it, so a mistyped number could modify an unrelated issue (mitigated by the skill's rule to never overwrite the original body)
  • •The heredoc-built `--body "$(cat <<'EOF' ... EOF)"` interpolates generated PRD content into a shell command; unusual quoting or backticks in generated content could misbehave at the shell level
How this analysis is made

Examples

New feature issue
/po add the ability to pin a blog article to the top of the index page
Explicit priority
/po handle rate limiting from the dev.to API during import --priority P1
Amend existing issue
/po amend 142 drop RSS autodiscovery, keep only the feed generation endpoint

name: po description: Product Owner - scans codebase and creates or amends GitHub issues with PRD. Use when: PRD, feature, issue, create issue, amend issue, what should we build, plan feature, design feature, scope, requirements.

Product Owner

Scan the codebase, write a PRD, and open a GitHub issue.

Usage

  • /po <prompt> - Create a GitHub issue from the given feature description
  • /po <prompt> --priority <P0|P1|P2|P3> - Create issue with explicit priority
  • /po - Ask user what to build, then create the issue
  • /po amend <issue_number> <summary> - Append a revision to an existing issue

If no --priority is given, ask the user which priority to assign.

Workflow

  1. Scan the codebase to understand current state:
    • Read relevant context modules (Blog, Import, Export)
    • Explore relevant source files for what's already implemented
    • Identify gaps, dependencies, and integration points
  2. Write the PRD as the issue body (no local file)
  3. Create GitHub issue with conventional title and PRD body

Issue Title

Conventional format:

feat(<context>): <short description>

Examples:

  • feat(blog): add article pinning
  • feat(export): add rss feed generation
  • fix(import): handle rate limiting from dev.to api

Rules:

  • Lowercase after prefix
  • Present tense imperative ("add", not "added")
  • Under 70 characters
  • Context name matches domain area (blog, import, export, web)

Issue Body (PRD)

## Overview
What we're building and why.

## Problem Statement
What user problem does this solve?

## Current State
What already exists in the codebase relevant to this feature.

## Requirements
- [ ] R-1: Description

## Technical Approach
- Affected modules
- Data flow changes
- Database changes if any

## Acceptance Criteria
Given/When/Then scenarios.

## Out of Scope
What we're explicitly NOT doing.

Creating the Issue

gh issue create \
  --title "feat(<context>): <description>" \
  --body "$(cat <<'EOF'
<PRD content>
EOF
)" \
  --label "prd" \
  --label "P2: medium"

Report the issue URL to the user when done.

Amending an Issue

When called with /po amend <issue_number> <summary>, append a revision to the existing issue. The original PRD is immutable — never edit or overwrite it.

Append a ## Revision <N> block with changes, updated requirements, and removed/deferred items.

Pipeline

/po <prompt> -> GitHub issue -> /dev -> /review -> /commit -> /pr

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/product-owner-mrwakdfj/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/product-owner-mrwakdfj' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/product-owner-mrwakdfj/download' --output '.skill-downloads/product-owner-mrwakdfj/SKILL.md.part' && mv '.skill-downloads/product-owner-mrwakdfj/SKILL.md.part' '.skill-downloads/product-owner-mrwakdfj/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/product-owner-mrwakdfj/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills