Code to PRD

Read an existing project and document its functionality, behavior and requirements.

Available in app
A source folder connects to a structured requirements booklet.

Overview

Reverse-engineer an existing codebase into a complete PRD: a global scan identifies the stack, page-by-page and endpoint-by-endpoint analysis follows, then structured documents are generated. Frontends covered: React, Vue, Angular, Svelte, Next.js, Nuxt, SvelteKit, Remix, Astro; backends: NestJS, Express, Django, FastAPI, Flask; fullstack projects merge pages and APIs into one document. Routes, components, state, models, enums and calls are evidenced one by one, and demo fixtures are distinguished from real integrations — mock data never gets written up as product truth.

Two audiences are served: product and partners read what each page does, while engineers or AI agents get enough detail to reconstruct fields, interactions and relationships — business language, zero business details omitted.

The delivery is a PRD package: per-page documents, an enum dictionary, an API inventory and model schemas, with a completeness check attached. The process only reads code and writes new documents; the analyzed project itself is never modified.

Where it helps

  • Produce reconstruction-grade PRDs for undocumented internal systems
  • On inheriting a legacy frontend, get pages and routes inventoried first
  • Export a Django backend's models and permissions as a data dictionary
  • Identify which endpoints are real integrations and which still mock
#prd#reverse#code#documentation

Examples

Examples describe the request and the shape of the expected deliverable; they are not completed run results.

Example prompt

Reverse-engineer this Next.js fullstack repo into a PRD: merge pages and APIs into one document, tabulate enums separately, and mark every mock.

Expected output

A PRD package: per-page docs, an enum dictionary and an API inventory, with mock data called out separately.

Example prompt

A new team takes over this Django project next week: produce a business-readable overview plus engineer-grade model and endpoint specs.

Expected output

A dual-audience set: feature meaning in business language, specs down to fields and permissions.

Requirements and limits

Install platforms
iOS: iOS · Android: Android
Script runtime
No script runtime (guidance and workflow)
Minimum app version
iOS: 1.7.59
Reviewed permission scope

iOS · Android

Capabilities
Read workspace filesWrite workspace files
Review decision
Approved
Review stage
Static content review
Reviewed on
2026-10-28
Implementation and runtime details
Adaptation stage
frozen

iOS

Capabilities
Read workspace filesWrite workspace files

Android

Capabilities
Read workspace filesWrite workspace files

License and source

Source and trace details

License

MIT

MIT (root LICENSE)

The pinned skill subtree and shipped references were audited; full applicable license and per-file adaptation/asset notes are preserved under references/licenses/ and references/PROVENANCE.md.

Image and material attribution

Image attribution
Floe original, AI-assisted illustration.
Source
https://github.com/alirezarezvani/claude-skills
Upstream path
product-team/code-to-prd/skills/code-to-prd
Upstream pin
6d2f02ea07
Source checked
2026-10-26
Publisher
JiangNanGenius
Publication commit (retrieval)
25e07dbeeb6cc93c2fe83ddc72a34302cc40832a
Audited source commit
84c524b6fb483e4cad94db076e7d9c9962966c19
Signed catalog digest
iOS 46196ba57ed7ea7f22085e74b113207f31193e820ab8983cf7a60eee953f2340 · Android 16de89d019e2057804a40f215485ccb09d5495a25864b34d681168eeaf8f9697
Publication snapshot (UTC)
2026-10-31

Publication commit 25e07dbeeb, audited source 84c524b6fb; catalog digest iOS 46196ba57ed7… · Android 16de89d019e2….

Versions and status

Version records ship with the signed catalog; the target and released versions are shown below.

Adaptation
Ready
Publication state
Curated skills are available
Released version
1.0.1