Improve Codebases with Advisor Plans
Teams often know a repository needs improvement but lack a clear, verified execution plan. This skill surveys the codebase, prioritizes evidence-backed findings, and writes plans that another agent can execute safely.
Copie esta solicitação para o seu Agente. Ela inclui a página canônica do Skill e o manifesto.
Review the Skillstore skill "improve" from https://skillstore.io/skills/shadcn-improve.md and its manifest at https://skillstore.io/api/skills/shadcn-improve/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Seu Agente ainda deve apresentar o plano e solicitar qualquer confirmação exigida pela política de segurança.
Use estes links quando um agente de IA, crawler ou script precisar de contexto limpo em vez de ler a página completa.
Usando "improve". Audit this repository for the best next improvements.
Resultado esperado:
Usando "improve". Create a plan for improving test coverage around payments.
Resultado esperado:
Usando "improve". Review an existing plan before another agent executes it.
Resultado esperado:
A critique of missing context, ambiguous steps, unsafe scope, weak verification, and suggested plan edits.
The static findings are false positives caused by Markdown backticks, examples, and defensive audit guidance rather than executable code. The skill is intentionally read-only for source code, includes safeguards for secrets and prompt injection, and gates outward-facing issue publication behind explicit user confirmation. No evidence of malicious intent, credential exfiltration, hidden command execution, or unsafe prompt injection was found in the reviewed files.
Compartilhe o relatório de avaliação versionado, o badge neutro, o cartão incorporável e as citações. A Skillstore apresenta evidências sem decidir se este Skill é seguro.
https://skillstore.io/skills/shadcn-improve/audits/2?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/shadcn-improve?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/shadcn-improve?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/shadcn-improve/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/shadcn-improve.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>shadcn. (2026). improve security audit report (audit version 2) [Author version 1.0.0]. Skillstore. https://skillstore.io/skills/shadcn-improve/audits/2@techreport{shadcn-shadcn-improve-2026,
author = {shadcn},
title = {improve security audit report (audit version 2)},
institution = {Skillstore},
year = {2026},
number = {2},
url = {https://skillstore.io/skills/shadcn-improve/audits/2},
note = {Author version 1.0.0}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "improve security audit report (audit version 2)"
version: "1.0.0"
type: report
authors:
- name: "shadcn"
date-released: "2026-07-07"
url: "https://skillstore.io/skills/shadcn-improve/audits/2"
identifiers:
- type: other
value: "skillstore:shadcn-improve:audit:2"
description: "Skillstore immutable audit report identifier"
Find high-leverage refactors, test gaps, and architecture cleanup work with concrete evidence and execution order.
Turn a vague improvement goal into a detailed plan that a lower-cost executor model can follow without session context.
Audit changed files and related callers for introduced or pre-existing issues before implementation plans are written.
Use improve to audit this repository and recommend the top improvement plans. Keep the audit standard depth.
Use improve with a security focus. Identify evidence-backed findings, reject false positives, and propose the highest-value plans.
Use improve plan to specify how to migrate this package to the new API. Include exact files, verification gates, and stop conditions.
Use improve branch deep. Audit changed files since the merge base, include related callers, and prepare plans for the top findings.
Autor
shadcnLicença
MIT
Versão do autor
v1.0.0
Revisão da Skillstore
r1
Referência
b2036d7931ef61c79ffdf43dae2a82ea8514f89a
Atualidade da manutenção
18/07/2026
Uso
2 downloads · 1 visualizações
Estrutura de arquivos
Review Defects and Verify Root-Cause Repairs
por aakashh242
Reviews can miss failure conditions or accept fixes without reliable evidence. Gauntlet guides scoped adversarial reviews, authorized repairs, and revision-bound verification within a finite budget.
Audit NestJS Code with Evidence-Backed Findings
por amirtaherkhani
NestJS repositories can hide boundary flaws and runtime risks that lint results alone cannot reveal. This skill combines local evidence collection and semantic review into one prioritized report.
Revisar código com verificações estruturadas de qualidade
por alirezarezvani
Revisões de código podem deixar passar problemas de qualidade, segurança e manutenibilidade. Esta skill orienta revisões estruturadas com scripts, checklists e geração de relatórios.
Analisar a Qualidade de Componentes do Claude Code
por C0ntr0lledCha0s
As equipes precisam de revisões consistentes antes de publicar componentes do Claude Code. Esta skill pontua clareza, permissões, gatilhos, segurança e usabilidade com orientações concretas de melhoria.
Crie APIs de Backend Confiáveis
por davila7
As equipes de backend precisam de orientação consistente sobre arquitetura, banco de dados e segurança entre os serviços. Esta skill fornece prompts direcionados, referências e scripts auxiliares para design de APIs e revisão de backend.
Estruture o Desenvolvimento de IA com Especificações
por 89jobrien
Projetos complexos assistidos por IA podem perder clareza antes mesmo do início da implementação. Esta skill orienta equipes por meio de especificações em fases, governança, planejamento, análise e execução de tarefas.