Use your most capable model to audit your codebase and write plans for cheaper models to execute.
★ 11,945⑂ 481👁 37⑃ 19● 10▤ 0
+97
Daily
+2,619
Weekly
+2,723
Monthly
11,945
stars
481
forks
37
watchers
19
prs
10
issues
0
releases
README
improve
An agent skill that audits any codebase and writes implementation plans for other agents to execute.
The idea: use your most capable model for the part where intelligence compounds — understanding the codebase, judging what's worth doing, writing the spec — and hand execution to cheaper models. The skill never implements anything itself. The plan is the product.
you → /improve (expensive model, advises)
plans/ → 001-fix-n-plus-one.md (self-contained specs)
other agent → implements, tests, ships (cheap model, executes)
Install
bash
npx skills add shadcn/improve
Works in any agent that supports Agent Skills format. The plans it writes are plain markdown, so any agent (or human) can pick them up.
Usage
/improve full audit → prioritized findings → plans
/improve quick cheap pass: hotspots, top findings only
/improve deep exhaustive: every package, every category
/improve security focused audit (also: perf, tests, bugs, ...)
/improve branch audit only what the current branch changes
/improve next feature suggestions — where to take the project
/improve plan skip the audit, spec one thing
/improve review-plan critique and tighten an existing plan
/improve execute dispatch a cheaper executor, review its work
/improve reconcile refresh the backlog: verify, unblock, retire
/improve ... --issues also publish plans as GitHub issues
How to use
A typical first run, start to finish:
1. Open your agent in the repo and run /improve (or /improve quick to keep it cheap).
2. It maps the repo, audits it, and comes back with a findings table. Reply with the ones you want planned — "plan 1, 3 and 5".
3. Plans land in plans/ — one file each, plus an index with the recommended order. Read them; they're meant to be reviewed.
4. Hand a plan to any agent ("implement plans/001-.md"), or let the skill run it: /improve execute 001. It dispatches a cheaper model in an isolated worktree, reviews the diff against the plan, and reports back with a verdict. Merging stays up to you.
5. Next session, run /improve reconcile to clean up the backlog: verify what landed, refresh what drifted, unblock what got stuck.
Before a PR, /improve branch does the same thing scoped to just what your branch changes.
Example
A run against shadcn/ui came back with findings like:
| | Finding | Category | Effort | Confidence |
|---|------------------------------------------------|-----------|--------|------------|
| 1 | shadow-config duplicated in search.ts/view.ts, | tech-debt | M | HIGH |
| | copies already drifted (TODO at search.ts:31) | | | |
| 2 | O(n²) icon migration (migrate-icons.ts:168) | perf | S | HIGH |
…and rejected a few, with reasons recorded so they don't comeTop issues
#2Keep execute-mode disposable worktrees inside the workspace by default3 comments · 2026-06-11#30execute scope check misses changes already committed by the executor0 comments · 2026-11-11#29Fix dropdown not showing correctly when dark mode is turned on0 comments · 2026-09-08#25execute: batch mode — run the backlog through one warm worktree, commit per plan, checkpoint gates0 comments · 2026-08-13#19Security related triggers change from fable to opus.0 comments · 2026-07-01#14Clarify that subagents inherit the parent model unless explicitly configured0 comments · 2026-06-16