Startup Ideas Bank
Automated Codebase Audit and Planning for Developers
AI roast score: 75/100 (B)
The idea
shadcn/improve — Use your most capable model to audit your codebase and write plans for cheaper models to execute.
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
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 <description> skip the audit, spec one thing
/improve review-plan <file> critique and tighten an existing plan
/improve execute <plan> 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:
Open your agent in the repo and run /improve (or /improve quick to keep it cheap).
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".
Plans land in plans/ — one file each, plus an index with the recommended order. Read them; they're meant to be reviewed.
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.
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
The roast
Your plan to use an expensive AI model to audit codebases and generate implementation plans for cheaper models is intriguing but fundamentally flawed. The primary issue is the assumption that developers will pay for a tool that essentially adds another layer of complexity to their workflow. Also, relying on an 'expensive model' for audits means your cost structure is inherently high, making the 'savings' from cheaper models negligible.
Moreover, you seem to be targeting developers who are typically skeptical about automated code audits, especially ones driven by AI. Without significant traction or proof of concept, this idea is more of a science experiment than a viable business. Also, the lack of funding (q14=no_funding) and solo operation (q13=solo) means you lack the resources to iterate quickly based on user feedback.
Red flags: 1) High-cost structure due to expensive models, 2) Complexity added to developer workflows, 3) Lack of funding and team resources.
Verdict: You need to prove developers will actually pay for this before burning cash on expensive models.
Red flags
- High-cost structure due to expensive models
- Complexity added to developer workflows
- Lack of funding and team resources
Verdict
You need to prove developers will actually pay for this before burning cash on expensive models.
Roast your own startup idea →