ncklrs

product-specs-writer

1
0
# Install this skill:
npx skills add ncklrs/startup-os-skills --skill "product-specs-writer"

Install specific skill from multi-skill repository

# Description

Expert product specification and documentation writer. Use when creating PRDs, user stories, acceptance criteria, technical specifications, API documentation, edge case analysis, design handoff docs, feature flag plans, or success metrics. Covers the full spectrum from high-level requirements to implementation-ready specifications.

# SKILL.md


name: product-specs-writer
description: Expert product specification and documentation writer. Use when creating PRDs, user stories, acceptance criteria, technical specifications, API documentation, edge case analysis, design handoff docs, feature flag plans, or success metrics. Covers the full spectrum from high-level requirements to implementation-ready specifications.


Product Specs Writer

Comprehensive product documentation expertise β€” from strategic PRDs to implementation-ready specifications that engineering teams can actually build from.

Philosophy

Great product specs bridge the gap between vision and execution. They're not bureaucratic documents; they're communication tools that align teams and prevent expensive misunderstandings.

The best product specifications:
1. Start with the why β€” Context before requirements
2. Are testable β€” Every requirement has clear acceptance criteria
3. Anticipate questions β€” Edge cases, errors, and constraints documented upfront
4. Evolve with the product β€” Living documents, not static artifacts
5. Respect the reader β€” Engineers, designers, and stakeholders can all understand them

How This Skill Works

When invoked, apply the guidelines in rules/ organized by:

  • prd-* β€” Product Requirements Documents, vision, scope
  • stories-* β€” User stories, personas, jobs-to-be-done
  • criteria-* β€” Acceptance criteria, definition of done
  • technical-* β€” Technical specifications, architecture decisions
  • api-* β€” API specifications, contracts, versioning
  • edge-* β€” Edge cases, error handling, failure modes
  • design-* β€” Design handoff, component specs, interactions
  • rollout-* β€” Feature flags, rollout plans, experiments
  • metrics-* β€” Success metrics, KPIs, measurement plans
  • maintenance-* β€” Documentation lifecycle, versioning, deprecation

Core Frameworks

Specification Hierarchy

β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚              VISION                     β”‚  ← Why are we building this?
β”‚         (Problem & Opportunity)         β”‚
β”œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€
β”‚               PRD                       β”‚  ← What are we building?
β”‚      (Requirements & Constraints)       β”‚
β”œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€
β”‚          USER STORIES                   β”‚  ← Who benefits and how?
β”‚       (Personas & Journeys)             β”‚
β”œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€
β”‚      ACCEPTANCE CRITERIA                β”‚  ← How do we know it's done?
β”‚      (Testable Conditions)              β”‚
β”œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€
β”‚      TECHNICAL SPECS                    β”‚  ← How do we build it?
β”‚   (Architecture & Implementation)       β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

Document Types by Audience

Document Primary Audience Purpose Update Frequency
PRD Leadership, PM, Design Align on what and why Per milestone
User Stories Engineering, QA Define scope and value Per sprint
Acceptance Criteria QA, Engineering Define done Per story
Technical Spec Engineering Define how Per feature
API Spec Frontend, External devs Define contracts Per version
Design Handoff Engineering Define UI/UX Per component
Rollout Plan Engineering, Ops Define deployment Per release
Success Metrics Leadership, Data Define success Per quarter

The INVEST Criteria (User Stories)

Criteria Question Example
Independent Can it be built alone? No dependencies on unfinished stories
Negotiable Is scope flexible? Details can be refined with engineering
Valuable Does user benefit? Clear value proposition stated
Estimable Can we size it? Enough detail to estimate effort
Small Fits in a sprint? Can be completed in 1-5 days
Testable Can we verify it? Has clear acceptance criteria

Specification Completeness Checklist

PRD Completeness:
β”œβ”€β”€ Problem Statement         β–‘ Clearly defined user pain
β”œβ”€β”€ Success Metrics          β–‘ Measurable outcomes defined
β”œβ”€β”€ User Stories             β–‘ All personas covered
β”œβ”€β”€ Scope                    β–‘ In-scope and out-of-scope clear
β”œβ”€β”€ Constraints              β–‘ Technical and business limits stated
β”œβ”€β”€ Dependencies             β–‘ External dependencies identified
β”œβ”€β”€ Risks                    β–‘ Known risks and mitigations
β”œβ”€β”€ Timeline                 β–‘ Milestones and deadlines set
└── Open Questions           β–‘ Unknowns explicitly listed

Technical Spec Completeness:
β”œβ”€β”€ Architecture             β–‘ System design documented
β”œβ”€β”€ Data Model               β–‘ Schema and relationships defined
β”œβ”€β”€ API Contracts            β–‘ Endpoints and payloads specified
β”œβ”€β”€ Edge Cases               β–‘ Failure modes documented
β”œβ”€β”€ Security                 β–‘ Auth, encryption, compliance covered
β”œβ”€β”€ Performance              β–‘ SLAs and benchmarks defined
β”œβ”€β”€ Monitoring               β–‘ Observability strategy clear
└── Rollback Plan            β–‘ Recovery procedures documented

Error Handling Taxonomy

Error Type Example Documentation Required
Validation Invalid email format Error message, field highlighting
Authorization User lacks permission Error state, escalation path
Resource Item not found Empty state, recovery action
System Database timeout Retry strategy, user feedback
Business Logic Insufficient balance Error explanation, next steps
External Third-party API down Fallback behavior, degraded mode

Specification Templates

Minimal PRD Structure

# Feature: [Name]

## Problem
What user problem are we solving?

## Solution
High-level approach (1-2 paragraphs)

## Success Metrics
- Primary: [Metric] from X to Y
- Secondary: [Metric] from X to Y

## User Stories
- As a [user], I want [goal] so that [benefit]

## Scope
**In scope:** [List]
**Out of scope:** [List]

## Open Questions
- [ ] Question 1
- [ ] Question 2

User Story Template

**As a** [persona/user type]
**I want** [capability/action]
**So that** [benefit/value]

**Acceptance Criteria:**
- Given [context], when [action], then [result]
- Given [context], when [action], then [result]

**Edge Cases:**
- What if [edge case]? Then [behavior]

**Out of Scope:**
- [Explicit exclusion]

Anti-Patterns

  • Spec by committee β€” Over-collaboration produces vague documents
  • Premature optimization β€” Specifying implementation details too early
  • Missing the why β€” Requirements without context for decisions
  • Kitchen sink scope β€” Trying to solve everything in one release
  • One-way documentation β€” Specs that don't get updated as learnings emerge
  • Assumption blindness β€” Not documenting implicit assumptions
  • Designer/Engineer telephone β€” No direct communication, only docs
  • Success theater β€” Metrics chosen because they're easy, not meaningful
  • Spec as contract β€” Treating specs as unchangeable legal documents
  • Documentation debt β€” Outdated specs worse than no specs

# Supported AI Coding Agents

This skill is compatible with the SKILL.md standard and works with all major AI coding agents:

Learn more about the SKILL.md standard and how to use these skills with your preferred AI coding agent.