# shadcn/improve

> An Agent Skill that audits a codebase and writes self-contained markdown implementation plans, so an expensive model analyzes while cheaper ones execute.

- Magnitude: 0.6 out of 10 — Quiet
- Stars: 9,233 total · +1 star measured 2026-10-17, 00:25–23:44 UTC
- Star trust: star growth looks organic
- Category: AI agents · License: MIT · Created: 2026-06-10 · Last push: 2026-09-12
- GitHub: https://github.com/shadcn/improve · Page: https://gitnova.dev/en/r/shadcn/improve

## Useful for

- Run a repo audit and get a prioritized findings table
- Generate a plan for a finding and hand it to a cheaper agent to execute
- Publish plans as GitHub issues via the --issues flag

## Why it’s here

- Star-counter measurements on 2026-10-17 (UTC), 00:25–23:44: 9232 → 9233 stars (+1). This is the change over that interval.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 412
- Issues and pull requests: 28
- Watchers: 34
- Average over the last week: 3 per day
- Usual pace: 5 per day

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-30 … 2026-10-29: 4, 4, 2, 8, 5, 3, 6, 3, 5, 2, 2, 2, 8, 4, 2, 4, 3, 1, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 14 days

10-04 1.1, 10-05 1.0, 10-06 1.1, 10-07 1.1, 10-08 0.7, 10-09 1.0, 10-10 0.6, 10-11 0.6, 10-12 0.8, 10-13 1.1, 10-14 1.0, 10-15 0.7, 10-16 0.8, 10-17 0.7

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-17 23:45 UTC, updated every 30 minutes.