explaingit

shadcn/improve

Analysis updated 2026-07-03

3,687Audience · developerComplexity · 2/5LicenseSetup · moderate

TLDR

Improve is an AI agent skill that audits a codebase and writes detailed improvement plans as markdown files, without ever touching your source code directly.

Mindmap

mindmap
  root((improve))
    What it does
      Audit codebase
      Write plans
      Rank findings
    How it works
      Maps repo structure
      Nine concern categories
      Parallel sub-processes
    Output
      Plans directory
      Impact vs effort table
      Executor-ready docs
    Workflow
      Review findings
      Pick plans to execute
      Reconcile drift
Click or tap to explore — scroll the page freely

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Run a security and correctness audit on a codebase and get a ranked table of issues without any code being changed automatically.

USE CASE 2

Generate a self-contained markdown plan for a specific bug fix that a cheaper AI model or junior developer can execute without needing the original context.

USE CASE 3

Periodically reconcile existing improvement plans against the codebase to find which have been completed and which have drifted.

USE CASE 4

Hand off planned improvements to a separate executor agent running in an isolated copy of the repository, then review before merging.

How does it compare?

shadcn/improveandrew-d/static-binariescanonical/cloud-init
Stars3,6873,6873,687
LanguageShellPython
Setup difficultymoderateeasymoderate
Complexity2/52/53/5
Audiencedeveloperops devopsops devops

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 30min

Requires an AI model integration, you need to configure the skill with a capable model before running the audit.

MIT, use freely for any purpose, including commercial, just keep the copyright notice.

In plain English

Improve is an agent skill that audits a codebase and writes detailed plans for improvements, but deliberately stops short of making any changes itself. The reasoning behind this separation is that understanding a codebase and judging what is worth fixing requires more intelligence than actually carrying out a well-specified task. So the skill is designed to run on a powerful, more expensive AI model that handles the thinking, and the resulting plans can then be handed to a cheaper model, another agent, or a human to execute. When you run it, the skill first maps the repository: it reads the code structure, identifies the build and test commands, and ingests any design documents or architecture decision records it finds. It then fans out across nine categories of concerns including correctness, security, performance, test coverage, and technical debt. Multiple sub-processes handle different categories in parallel and report their findings. Before showing you anything, the skill re-reads the cited code locations itself to filter out false positives and wrong attributions. Findings are presented in a table ranked by impact relative to effort. You pick which ones to plan, and it writes one markdown file per finding into a plans/ directory. Each plan is designed to be read by an executor that knows nothing about the original audit session. It includes exact file paths, current code excerpts, the repository's own lint and test commands as verification steps, and explicit stop conditions for when the real state of the code does not match what the plan assumed. From there, an execute command can dispatch a separate cheaper model in an isolated copy of the repository to carry out a specific plan, then review the result before anything is merged. A reconcile command revisits existing plans to check which have been completed, which have drifted as the codebase changed, and which need to be unblocked. The skill never writes to your source files directly. All its output goes to the plans/ directory. Merging any changes produced by an executor is always left to you. It is released under the MIT license by the creator of shadcn/ui.

Copy-paste prompts

Prompt 1
I have a Python web app codebase. Run the shadcn/improve skill on it, show me the impact-vs-effort ranking table, and generate plans for the top three security findings.
Prompt 2
Using shadcn/improve, generate an executor-ready markdown plan for fixing a test coverage gap in my repo, include exact file paths, code excerpts, and verification steps.
Prompt 3
Walk me through how shadcn/improve's reconcile command decides which plans have drifted and what output it produces.
Prompt 4
I want to use shadcn/improve with a powerful model for auditing and a cheaper model for execution. What does the handoff look like between audit output and execute command?
Prompt 5
Show me the nine concern categories that shadcn/improve checks during an audit and what kinds of issues each one targets.

Frequently asked questions

What is improve?

Improve is an AI agent skill that audits a codebase and writes detailed improvement plans as markdown files, without ever touching your source code directly.

What license does improve use?

MIT, use freely for any purpose, including commercial, just keep the copyright notice.

How hard is improve to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is improve for?

Mainly developer.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Scan in gitsafehub Deploy in gitdeployhub shadcn on gitmyhub

Verify against the repo before relying on details.