Diff Story

A pull request summarizer app idea: a tool that explains a big diff in reading order. Weekend build with Node.js, Claude API, React and Vite, for solo developers reviewing large ai-generated changes.

See the spec
Why now

Why now

OmniDiff on Hacker News shows people want better diff tooling, and the Ask HN thread 'Are you tired too in this AI era?' describes the load of reading enormous amounts of generated text. A reading-order summary goes straight at that pain. From the signals of the week of 2 Nov 2026.

The spec

The spec

Paste a branch or diff and get the changes grouped by intent and ordered so they make sense to read, with risky edits like deleted checks or changed config called out first. It cuts the tiredness of reading huge amounts of generated code.

Build time

WeekendAPIs or integrations · Level 3 of 5

Audience

Solo developers reviewing large AI-generated changes.

Stack

  • Node.js
  • Claude API
  • React
  • Vite

Fun factor

It turns a wall of green and red into a short story you can actually follow.

Core features

  • Local git diff input from a CLI or paste box
  • Changes grouped into themes with file lists
  • Risk flags for deleted tests, changed permissions and config edits
  • Checklist you tick off as you review

AI features

  • Model groups hunks by intent and writes a one-line reason for each group
  • Model compares the diff against the stated task and lists anything that looks unrelated

Stretch goals

  • GitHub Action that posts the summary on pull requests
  • Remember repeated review notes per repo
  • Export the review as a markdown file

First version

A CLI that reads git diff output and opens a local page showing grouped changes with risk flags and a review checklist.

Build plan

Build plan

4 milestones, in the order you would build them. Saved ideas get this plan with checkboxes and notes.

Parse the diffSplit git diff output into files and hunks.
Start here
Group by intentAsk the model to cluster hunks and name each group.
Render the review pageShow groups in reading order with risk flags on top.
Add the checklistSave ticked items locally so a review can be resumed.
The build prompt

The build prompt

Paste this into ChatGPT, Claude, Codex, or Cursor, then build the first version before anything else.

diff-story.prompt.md
# Build Diff Story

You are a senior full-stack engineer pairing with me on a side project. Build a working first version of the product described below. Read the whole brief before writing any code, then follow "How to work" at the end.

## The idea

**Diff Story.** Paste a branch or diff and get the changes grouped by intent and ordered so they make sense to read, with risky edits like deleted checks or changed config called out first. It cuts the tiredness of reading huge amounts of generated code.

**Why now:** OmniDiff on Hacker News shows people want better diff tooling, and the Ask HN thread 'Are you tired too in this AI era?' describes the load of reading enormous amounts of generated text. A reading-order summary goes straight at that pain.

**Who it is for:** Solo developers reviewing large AI-generated changes

**What makes it fun:** It turns a wall of green and red into a short story you can actually follow.

## Scope

- **Build time:** Weekend. Size every decision to ship a working first version inside this window.
- **Technical ambition:** Level 3 of 5, "APIs or integrations". The product leans on third-party APIs. Wrap each integration in its own module, handle its failures and rate limits, and cache what is safe to cache.
- **First version only.** Ship the core features below end to end. Stretch goals are listed so you can design around them, not build them.

## Core features (each must work end to end in the first version)

1. Local git diff input from a CLI or paste box
2. Changes grouped into themes with file lists
3. Risk flags for deleted tests, changed permissions and config edits
4. Checklist you tick off as you review

## AI features

- Model groups hunks by intent and writes a one-line reason for each group
- Model compares the diff against the stated task and lists anything that looks unrelated

How to build them:
- Put every model call behind one server-side module with a typed interface, so the provider can change without touching the UI.
- Read API keys from environment variables only, and document each one in `.env.example`.
- Write prompts as versioned constants with clear instructions and an example of the expected output; parse and validate responses before using them.
- Handle timeouts, rate limits, and malformed output with a graceful fallback the user can understand. Stream responses where a wait would exceed a couple of seconds.
- Never let a feature depend on the model being perfect. Show the result, let the user edit or retry.

## Stretch goals (later, not in the first version)

- GitHub Action that posts the summary on pull requests
- Remember repeated review notes per repo
- Export the review as a markdown file

Leave clean seams for these (a module boundary, a nullable column, a feature flag), but do not implement them unless I ask.

## Tech stack

Use exactly: Node.js, Claude, React, Vite.

Stay on current stable versions, follow each tool's official conventions, and add a library only when the standard library or the chosen stack cannot do the job cleanly. If part of this stack is a poor fit for a specific requirement, say so and propose the smallest change.

## Owner's notes

Written by me, the project owner. Treat these as requirements and preferences that override the generated material above when they conflict.

The first version should be exactly this, and no bigger: A CLI that reads git diff output and opens a local page showing grouped changes with risk flags and a review checklist.

## Build plan (with saved progress)

0 of 4 steps complete. Resume at step 1: Parse the diff. Before you start it, check what is already implemented so you do not repeat finished work.

1. **Parse the diff** [not started]
   Split git diff output into files and hunks.

2. **Group by intent** [not started]
   Ask the model to cluster hunks and name each group.

3. **Render the review page** [not started]
   Show groups in reading order with risk flags on top.

4. **Add the checklist** [not started]
   Save ticked items locally so a review can be resumed.

## Definition of done for the first version

- [ ] Local git diff input from a CLI or paste box works end to end, with real data, not a placeholder.
- [ ] Changes grouped into themes with file lists works end to end, with real data, not a placeholder.
- [ ] Risk flags for deleted tests, changed permissions and config edits works end to end, with real data, not a placeholder.
- [ ] Checklist you tick off as you review works end to end, with real data, not a placeholder.
- [ ] Every screen handles loading, empty, and error states.
- [ ] Typecheck, lint, and any tests pass, and the main user flow was exercised by hand.
- [ ] A README explains setup, environment variables, and how to run it locally.

## Quality bar

- Responsive from a phone to a desktop, keyboard-accessible, semantic HTML, visible focus states, labelled inputs, and sensible contrast.
- Loading, empty, and error states for every screen that reads or writes data. Errors say what happened and what to do next.
- Validate on the server, never trust the client, and keep secrets in environment variables with a committed `.env.example`.
- Type-safe end to end. No `any` without a comment explaining why.
- Small, readable modules named after what they do. No premature abstraction, no dead code, no TODOs left for later without a note.
- Sensible defaults over settings. If a choice is not in this brief, pick the simplest option that keeps the product coherent and say what you chose.

## How to work

1. **Read, then restate.** Summarize the product in three sentences and list your assumptions. Ask only the questions that block implementation. For everything else, decide and note the decision.
2. **Plan before code.** List the files and modules you will create, in build order, mapped to the core features. If a build plan is included above, use it instead: resume at the first step not marked done and check what already exists before touching it.
3. **Set up.** If a project already exists, inspect its code, instructions, and conventions first and build on them. Otherwise scaffold the stack above with linting, formatting, a typecheck script, `.env.example`, and a README stub.
4. **Model the data first.** Define the types, schema, and any migrations before the UI, so the shape of the product is settled early.
5. **Build in vertical slices.** Finish one core feature end to end (data, logic, UI) before starting the next. Keep the app runnable after every slice and commit each slice with a message that says what changed and why.
6. **Then the interface.** Apply the quality bar above to each screen as it lands, not as a final pass.
7. **Verify.** Run typecheck, lint, and tests. Exercise the main user flow by hand. Check each item in the definition of done and each acceptance criterion.
8. **Report.** Tell me what works, what you tested and how, what is not done, every setup step I must complete myself, and the three most useful next steps. Never claim a service, test, or flow was verified when it was not.

If you can edit and run the project, start implementing right after the short plan. If you cannot, give me concrete code and the exact commands to run for the next step.

Rules: keep the product name and the scope as written, do not invent features, prefer boring and proven choices, and stop to ask me when a decision would be expensive to reverse.

How to use

  1. Copy the prompt above.
  2. Open ChatGPT, Claude, or your AI editor and paste it into a new conversation.
  3. Build milestone one, run it, then move to the next. Add stretch goals only after the first version works.

Want ideas built around you instead? Generate four from your own interests, time, and stack.

Frequently asked questions

FAQ

Frequently asked questions

Answers on what Diff Story is, how to build it, and where example ideas come from.

Similar ideas

Similar to Diff Story

More developer tools ideas, then a few from other categories.

Generate your own

Ready to generate yours?

Four ideas per round, shaped by your interests, skill level, and how much time you have.