Item detail

shadcn/improve

shadcn/improve is a agent skill that audits any code that RepoRadar is tracking in its MIT agent skill (Agent Skills format) that audit section, currently rated Gold tier with a 'try now' verdict. Its strongest signal is workflow potential, scored 10.0 out of 10.

Score8.5
Popularity6172.0
Risklow
TierGold
Score breakdown
Usefulness9.0
Novelty9.0
Momentum9.0
Maturity9.1
Open-source/build8.4
Evidence7.2
Workflow potential10.0
Setup ease8.8

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for engineering teams running Claude Code / Cursor / Codex / OpenCode who want their most capable model to do the part where intelligence compounds (audit + spec) and their cheaper models to do the part where execution speed compounds: shadcn/improve is the MIT agent skill that audits any codebase and writes prioritized, self-contained implementation plans for other agents to execute; for e

Who should use it

Engineering teams running Claude Code / Cursor / Codex / OpenCode who want their most capable model to do the part where intelligence compounds (audit + spec) and their cheaper models to do the part where execution speed compounds (execution)Engineering managers who want a single command (`/improve`) that maps a repo's stack + conventions + build/test/lint commands, fans out parallel subagents across 9 audit categories, vets the findings, prioritizes by leverage, and writes one plan per finding to `plans/`Security-conscious teams that need a plan-writer that never runs commands that mutate the working tree (read, search, and read-only analysis only) and never reproduces secret values (locations and credential types only, rotation always recommended)Engineering teams that want plans to be self-contained + machine-checkable (exact file paths, current-state code excerpts, repo conventions with an exemplar file, verified commands, explicit STOP conditions) so a much smaller model can execute them without judging whether it succeededEngineering leads who want a tech-lead-style review loop (`/improve execute <plan>` dispatches a cheaper executor in an isolated git worktree, reviews the result against the plan, verdict: approve / send back for revision / block and refine, max 2 revision rounds)Teams adopting Agent Skills format that want a single skill that also works for `/improve quick` (cheap pass: hotspots + top findings), `/improve deep` (exhaustive: every package, every category), `/improve security` (focused audit), `/improve branch` (audit only what the current branch changes), `/improve next` (feature suggestions), and `/improve reconcile` (verify DONE plans, unblock BLOCKED, refresh drifted plans, retire independently-fixed findings)Organizations that want a mechanical drift check before any executor touches code (each plan stamps the git commit it was written against, and the executor runs a drift check before touching anything)Engineering teams that want plans to land in the workflow they already use (the `--issues` flag publishes plans as GitHub issues with the same self-contained body, so any agent or human can pick them up where work already lives)Small teams who can't afford a dedicated tech lead (the vet + review loop is the same one a senior engineer would run on a junior engineer's PR, but the senior is the expensive model and the junior is the cheap model)

Who should skip it

Pass on shadcn/improve if its scope or audience does not match what your team is building right now.

About this signal

shadcn/improve is tracked by RepoRadar as a agent skill that audits any code in the MIT agent skill (Agent Skills format) that audit section. It was first seen on 2026-06-25 and last updated on 2026-06-25. The current verdict is 'try now' with a Gold tier and easy setup difficulty. The standout signals for shadcn/improve are workflow potential (10.0) and maturity (9.1), while evidence quality (7.2) trails — that balance shapes where it fits best. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.

How this item is evaluated

RepoRadar assigned shadcn/improve a composite score of 8.5 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 6172.0 and never affects the composite score or tier. The risk label of 'low' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.

Risk explanation

**Plan-writer never modifies source code; merging stays your call.** The hard rule is that the plan-writer never modifies source code and never runs commands that mutate the working tree (read, search, and read-only analysis only). The `/improve execute <plan>` path dispatches a cheaper executor in an isolated git worktree, but the merge is always the user's call. Treat plans as spec, not as PRs; review the diff against intent before merging; **Cheap-model executors need the self-contained plan to do good work.** The plans are written for the weakest plausible executor (a model that has never seen the advisor session and may be much smaller) — self-contained (all context inlined, no 'as discussed above'), verification gates (every step ends with a command and its expected output), hard boundaries (explicit out-of-scope lists, STOP conditions). A weak executor given a thin plan will improvise and fail; a weak executor given a self-contained plan will execute the steps mechanically and verify. Run the executor with the strongest model the team can afford if the plan is shorter than expected; **Direction findings are evidence-cited by design, but the team still owns the roadmap.** The direction category surfaces feature suggestions where every finding must cite evidence from the repo itself (no generic idea-slop), but the team still owns the roadmap — `improve` is a discovery surface, not a replacement for product judgment. Use `/improve next` as input to the planning conversation, not as the planning conversation.

Evidence links

Closest alternatives / related signals

improveshadcnshadcn-improveagent-skillsagent-skills-formatskills-formatclaude-codecursor