Summary
This is your requirements engineering toolkit for turning fuzzy stakeholder requests into executable specs. It walks you through INVEST user stories, BDD acceptance criteria (Given/When/Then), and scope management with MoSCoW prioritization. The examples are actually good: it shows you the difference between "I want a better dashboard" (bad) and a properly scoped story with testable criteria (good). Bonded to a requirements-definition agent, so it knows how to say no to scope creep and document change requests. If you're tired of building the wrong thing because requirements were vague, this gives you the structure to prevent that. The troubleshooting section even catches you mixing up epics and stories.
Install to Claude Code
npx -y skills add pluginagentmarketplace/custom-plugin-product-manager --skill requirements-specification --agent claude-codeInstalls into .claude/skills of the current project.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Files
SKILL.md
Select a file.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →First SeenJun 3, 2026
