RepoAlerts

shadcn/improve

AI skill

Can I trust it?

Worth a closer look before you use it.

  • Stars from real accounts OK

    Our fake-star check passed. In a sample of 31 stargazers, 0% were accounts under a month old and 3% had no followers or repos.

  • Active Check

    Last change 65 days ago.

  • Licence OK

    MIT: you can use it for free, also in a commercial product. Keep the licence notice.

Quick checks from public data. They help, but they are no guarantee.

What it is

An agent skill that audits a codebase with a capable model and writes self-contained implementation plans, which cheaper models or humans then execute. The skill itself does not implement changes; it covers audit, prioritization, plan writing, plan execution dispatch and backlog…

Who it's for

Developers using AI coding agents who want a capable model to audit their repository and cheaper models to implement the resulting plans

How to use it

Install

npx skills add shadcn/improve

From its README. Check it there before running it.

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up shadcn/improve in my project. Follow its README: https://github.com/shadcn/improve. Explain each step and check it is safe before running anything.

Star curve

12KFrom 9,176 to 11,999 stars between 7 Oct 2026 and 16 Nov 2026.

Get alerts for repos like this

We'll email you when something in AI agents starts rising. Free, once a week, only what matches.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![shadcn/improve on RepoAlerts](https://repoalerts.com/badge/shadcn/improve.svg)](https://repoalerts.com/repo/shadcn/improve?ref=badge)
Share on X

  • YTruman/better-skill

    A standards handbook for auditing, scoring and building AI agent skills. It defines architecture paradigms, a P0/P1/P2 audit checklist with red-line rules, five comparison metrics, and an eval loop fo

    AI skillAI agents277 stars · +24 this week · 20 days old

  • cloudflare/security-audit-skill

    A coding-agent skill that runs multi-phase security audits of a codebase. It orchestrates isolated agents through reconnaissance, coverage-led hunting, candidate validation, structured findings output

    AI skillAI agentsJavaScript · 73,842 stars · +5,902 this week · 151 days old

  • better-isms/grcskills

    A library of 60 open agent skills in SKILL.md format covering governance, risk and compliance work such as scope statements, statements of applicability, risk registers, audit preparation, evidence ga

    AI agentsJavaScript · 59 stars · +2 this week · 28 days old

  • arla6ka/design.how

    A collection of agent skills that help coding agents build and migrate design systems, review UI screens, document components and make fonts or motion graphics videos. It also ships four shadcn-based

    AI skillAI agentsTypeScript · 482 stars · +194 this week · 50 days old

  • NVIDIA/SkillEvaluator

    Multi-tier framework for evaluating AI agent skills. It runs static quality checks, detects semantic overlap between skills, generates synthetic evaluation datasets, and runs live agent evaluations th

    CLI toolAI agentsPython · 2,554 stars · +1,886 this week · 146 days old

  • MiniMax-AI/mcode-stack

    A collection of workflow skills and checklists used by the MiniMax Code team, covering subagent splitting, small PRs, context audits, long commands, code review and experiments. Each skill is a SKILL.

    AI skillAI agentsJavaScript · 725 stars · +169 this week · 20 days old