shadcn/improve

★12,068MIT⑂ 491Issue 8Updated Sep 12, 2026

Use your most capable model to audit your codebase and write plans for cheaper models to execute.

An Agent Skill That Splits Thinking From Execution — A skill for the Agent Skills format that audits a codebase with your most capable model and writes self-contained markdown plans for cheaper models to implement. It never executes code itself — it handles findings, prioritization, and spec-writing, then hands off to an executor agent, keeping expensive reasoning separate from cheap execution.

AI agents

Metrics

Relative growth (7d)+4%Growth over the last 7 days relative to size
Acceleration-79%Change in growth pace from the week before
Attention33The three metrics scaled to 0–100 and combined

Retention can be computed 30 days after a repository first trends (it isn't shown until then). See About for how each metric is defined.

Star growth and Trending appearances (last 30 days)

First listed+719★/dayDaily
Oct 22, 2026Nov 20, 2026

Bands mark days on the trending list (darker = higher rank)

Daily trending ranks as a table (1 days)
DateDaily
Nov 12, 2026
#4 +361

Created Jun 10, 2026 · First on trending Nov 12, 2026

Other notable repositories in the same category (AI agents)

See all AI agents repositories →

Get the weekly digest by email

Every Monday: the repositories that grew most last week, and how the buzz spread between the global and Japanese-language web. Unsubscribe any time. See the privacy and ad policy for how we handle your address.