i-onlabs/claude-code-skills/pipeline-pm-spec

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Product requirements to user stories pipeline stage (PM → Spec)

Install

npx vskill@latest install i-onlabs/claude-code-skills/pipeline-pm-spec

SKILL.md

PM Specification Pipeline Stage

Pipeline Position: First stage (Requirements → User Stories) Next Stage: pipeline-arch-review

Methodology

Transform high-level requirements into actionable user stories following INVEST principles.

Process
  1. Requirements Gathering
  • Ask clarifying questions about user needs
  • Identify stakeholders and success criteria
  • Document constraints and assumptions
  1. User Story Creation
  • Follow format: "As a [role], I want [feature] so that [benefit]"
  • Apply INVEST criteria:
  • Independent: Can be developed separately
  • Negotiable: Details can be discussed
  • Valuable: Delivers user value
  • Estimable: Can be sized
  • Small: Fits in one iteration
  • Testable: Has clear acceptance criteria
  1. Acceptance Criteria
  • Given/When/Then format
  • Cover happy path and edge cases
  • Measurable and testable
  1. Prioritization
  • Must-have / Should-have / Nice-to-have
  • Dependencies between stories
  • Risk assessment
Output Format
markdown
# Feature: [Feature Name]
## Overview
[Brief description of the feature and its purpose]
## User Stories
### Story 1: [Title]
**As a** [role]
**I want** [capability]
**So that** [benefit]
**Priority:** Must-have | Should-have | Nice-to-have
**Estimate:** S | M | L
**Acceptance Criteria:**
-Given [context]
When [action]
Then [outcome]
-Given [context]
When [action]
Then [outcome]
### Story 2: [Title]
[Repeat format]
## Success Metrics
-[How we'll measure success]
## Constraints
-[Technical or business constraints]
## Dependencies
-[External dependencies or prerequisites]
## Next Step
→ Use `pipeline-arch-review` to design architecture for these stories
Best Practices
  • User-Centric: Focus on user value, not implementation
  • Collaborative: Involve stakeholders in refinement
  • Testable: Every story must have clear pass/fail criteria
  • Incremental: Break large features into smaller stories
  • Documented: Capture decisions and assumptions
Anti-Patterns to Avoid
  • ❌ Technical tasks disguised as user stories
  • ❌ Stories without acceptance criteria
  • ❌ Vague or unmeasurable criteria
  • ❌ Stories too large (>1 sprint)
  • ❌ Missing "why" (benefit statement)
Handoff to Architecture

After completing spec, suggest:

Use pipeline-arch-review to design the technical architecture for these user stories.

This ensures smooth transition to the next pipeline stage.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/i-onlabs/claude-code-skills/pipeline-pm-spec/badge)](https://verified-skill.com/skills/i-onlabs/claude-code-skills/pipeline-pm-spec)

Something wrong with this skill or its page? Tell us.