saas-dev:spec-parser

Convert SaaS product spec text into validated PageSpec[] with provenance layers.

1|Updated Mar 11, 2026
One-click install
npx skills add https://github.com/antonyfmunoz/OS --skill saas-dev-spec-parser
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: saas-dev:spec-parser
Source: https://github.com/antonyfmunoz/OS/tree/main/skills/saas-dev-skill/.claude/skills/saas-dev/skills/spec-parser
Command: npx skills add https://github.com/antonyfmunoz/OS --skill saas-dev-spec-parser

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It eliminates the confusion and rework of turning messy SaaS product notes into a structured, implementation-ready page specification, ensuring everything is validated and clearly marked as explicitly provided or AI-inferred.

Core Features & Use Cases

  • Paste-and-parse or guided collaboration: Converts raw spec text or runs a domain-first questioning flow to generate a PageSpec[].
  • Composable output layers with provenance: Produces core, UI, data, and analytics layers while tagging every item with source provenance (explicit vs inferred) for review.
  • Production-grade post-processing: Performs chunking and reconstruction for large inputs, deduplicates shared components, derives backend spec from UI pages, and runs gap analysis to stop/flag missing critical flows.
  • Surgical editing with confirmations: Supports apply-and-flag edits so only the affected pages are re-confirmed before persistence.

Quick Start

Ask the AI to parse your SaaS product spec into a validated PageSpec[] with explicit vs inferred provenance, chunking for large inputs, deduplicated shared components, derived backend spec, and gap analysis before saving.

Frequently Asked Questions about saas-dev:spec-parser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I turn rough SaaS product ideas into validated page specifications?▼

To turn rough SaaS ideas into validated page specifications, you can paste raw spec text or use a guided questioning flow to generate a structured PageSpec[] with composable core, UI, data, and analytics layers.

How does provenance marking work when generating SaaS specs from product notes?▼

Provenance marking works by tagging every item in the generated page specification as either explicitly provided in the original notes or AI-inferred, ensuring product teams can review and validate every detail before persistence.

What is the best way to handle gap analysis for missing critical flows in SaaS specs?▼

The best way to handle gap analysis for missing flows is to run a post-processing step that flags missing critical flows with blocking or recommended severities, stopping persistence until explicit approval is granted.

How do I deduplicate shared components when parsing large SaaS product specs?▼

To deduplicate shared components when parsing large SaaS specs, the system performs chunking and reconstruction for oversized inputs, automatically identifying and merging duplicate components to ensure a clean specification.

Can I derive backend specs directly from UI page specifications?▼

Yes, you can derive backend specs directly from UI page specifications by using backend-derivation workflows that analyze the validated UI pages and generate the corresponding backend requirements automatically.

How do I surgically edit a page spec without re-confirming the entire document?▼

To surgically edit a page spec without re-confirming everything, you can use apply-and-flag edits that isolate changes, ensuring only the affected pages require re-confirmation before saving to the pipeline phase.