# AI use cases for AI Goodpractice (xop01/ai_goodpractice)

Repo: [xop01/ai_goodpractice](https://github.com/xop01/ai_goodpractice) | Use cases: 3 | Page: https://dedupedai.com/use-cases/xop01-ai-goodpractice/

A hand-written guide to setting up an AI-driven coding workflow with rules, skills, MCPs and documentation, plus one MCP for tracking project progress.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Set coding style rules for a repo from existing code: https://dedupedai.com/use-cases/xop01-ai-goodpractice/set-repo-coding-style-rules-from-existing-code/
- Keep an AI on a project roadmap with project progress MCP: https://dedupedai.com/use-cases/xop01-ai-goodpractice/track-project-roadmap-with-project-progress-mcp/
- Write feature docs so AI finds code without full reads: https://dedupedai.com/use-cases/xop01-ai-goodpractice/write-feature-docs-so-ai-finds-code-without-full-reads/

## How to set coding style rules for a repo from existing code with AI Goodpractice

Repo: [xop01/ai_goodpractice](https://github.com/xop01/ai_goodpractice) | Difficulty: Beginner | Time: 30 minutes | Basis: From the README

Turn the code style of a reference codebase into a repo rule that the AI follows.

**Who it is for:** A developer starting a new project, or adding AI to an existing one, who wants the AI to keep a consistent code style.

**The problem:** Without rules, AI output drifts and the code style can go out of hand quickly.

**The outcome:** A repo rule that captures the code style of a reference folder and that the AI applies to the target repo.

### Steps

1. Open the target repo in your AI-enabled IDE, such as Cursor, VS Code, or Claude Code.
2. Get the path or URL of a reference folder whose code style you want to copy.
3. Prompt the AI: analyze the code style from the reference folder in depth and apply it as a rule for this repo.
4. Review the rule the AI writes, and refine the prompt if the result is vague.
5. Decide whether the rule belongs to the repo or to your user rules, then save it. The guide says code style usually fits the repo.

### Prompt to paste into your agent

```text
Using the ai_goodpractice guide workflow, analyze the code style of <reference folder path> in depth and write it as a repo rule for <target repo path>. Expected output: one rule file describing naming, formatting and structure. Verify that each rule points to a pattern actually found in the reference folder.
```

### Caveat

The rule is only as good as the reference code you pick, so choose a reference codebase you actually want the AI to copy.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/xop01-ai-goodpractice/set-repo-coding-style-rules-from-existing-code/

## How to keep an AI on a project roadmap with project progress MCP with AI Goodpractice

Repo: [xop01/ai_goodpractice](https://github.com/xop01/ai_goodpractice) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README

Run the project progress MCP so the AI records changes and future goals as it works.

**Who it is for:** A developer building a multi-step project with an AI agent who keeps getting pulled into side features and loses the main path.

**The problem:** The AI drifts off the intended path and can forget what it was doing after a side feature.

**The outcome:** A roadmap the AI keeps updated, so it can branch to a side feature and return to the main path afterwards.

### Steps

1. Open the project-progress-mcp repository at https://github.com/xop01/project-progress-mcp and read its README.
2. Clone the repository and build it. The README says it is written in Zig and is compilable on every OS. (inferred, check the README)
3. Register the built MCP in the MCP settings of your AI tool, such as Cursor. (inferred, check the README)
4. Start working on your project and ask the AI to record the current progress and future goals as it works.
5. When a side feature comes up, let the AI branch to it, then have it return to the main roadmap.

### Prompt to paste into your agent

```text
Use the project progress MCP from xop01/project-progress-mcp on <project path>. Record completed changes, the current feature and the next goals as you work. Expected output: an updated roadmap and the next step after finishing a side task. Verify that the main path is still listed after the side task.
```

### Caveat

The README says this is likely not an automatic path to completion, and the author does not know all of its possibilities.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/xop01-ai-goodpractice/track-project-roadmap-with-project-progress-mcp/

## How to write feature docs so AI finds code without full reads with AI Goodpractice

Repo: [xop01/ai_goodpractice](https://github.com/xop01/ai_goodpractice) | Difficulty: Beginner | Time: 30 minutes | Basis: From the README

Keep short docs for each important feature so the AI can locate code and behavior quickly.

**Who it is for:** A developer on a growing project who wants the AI to understand parts of the code without re-reading every file each time.

**The problem:** Without docs, the AI has to read files in their entirety to learn which code does what.

**The outcome:** Feature documents the AI can read first to find related code, expected behavior and open follow-ups.

### Steps

1. Pick one important feature or infrastructure part of your project.
2. Write a short doc yourself, or ask the AI to write it, covering what the part does and how it behaves.
3. Ask the AI to record bugs and their fixes in docs, including follow-ups that are not done yet.
4. Tell the AI to read the relevant doc before opening source files.
5. Review the docs regularly and check whether any open follow-up has become easier to solve.

### Prompt to paste into your agent

```text
In <project path>, write a documentation file for the <feature name> part that explains what it does, how it behaves and which files relate to it. Expected output: one doc file in the project's docs area. Verify that the doc ends with a list of any open follow-up items.
```

### Caveat

The guide gives no fixed doc format, so choose a structure you will keep up to date.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/xop01-ai-goodpractice/write-feature-docs-so-ai-finds-code-without-full-reads/