A skill for coding agents that runs a structured, multi-phase security audit of a codebase. It uses separate agents to find, challenge and verify vulnerabilities, then writes the results as machine-readable records and readable reports.
improve
by shadcn
An agent skill that has a capable AI model audit a codebase and write detailed, self-contained implementation plans as markdown files. Cheaper models or people can then carry out those plans, which keeps costs down.
Proof level: ReadWorth a lookMIT
No demo yet
Proof level: Read. We read its README and licence and ran our automatic checks. We have not run it yet. So this page is based on its README and our automatic checks.
The catch
Check this first: Needs an AI coding agent and model access, which usually means paid usage.
Things to check
- Needs an AI coding agent and model access, which usually means paid usage
- Audit quality depends on the model used, so findings still need human review
Can you use improve commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Did it work for you?
One answer per person for each tool a day, with no account and no cookies. Your answer is remembered in this browser only. How we count
What can you do with improve?
- Run a full or quick audit of a codebase and get a ranked table of findings
- Turn chosen findings into step-by-step plan files with checks and stop conditions
- Hand a plan to a cheaper model in an isolated worktree and have the result reviewed
How do you get improve running?
Install with `npx skills add shadcn/improve` in any agent that supports the Agent Skills format.
Follow the official instructions in the project README.
Make money with it
A freelance developer could offer fixed-price codebase audits, using the generated findings and plans as the deliverable.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Audit an existing product's code for bugs, security and performance issues without paying for a full manual code review
- Write clear specs that cheaper AI models can implement, lowering the cost of ongoing maintenance work
Who's talking about it
Checked 13 Nov 2026. Summary drafted by AI from the project's README. Proof level 1 of 4, Read: we read its readme and licence and ran our automatic checks. we have not run it yet.
Similar tools in Agent skills and plugins
A skill for Claude Code and Codex that reviews a screen built with AI tools, finds the generic "AI look" such as purple gradients, glows and uneven spacing, and fixes it step by step. It is for making dashboards, apps and landing pages look designed rather than auto-generated.
A small collection of agent skills, each a folder with a SKILL.md file of instructions for an AI agent. At present it holds one skill, a Socratic tutor that teaches a topic through questions, a skill map and spaced review.