Crawl configuration mistakes can hide pages from search engines or produce invalid sitemap data. This skill checks local robots.txt and sitemap XML files and reports actionable findings.

Project documentation becomes stale when it relies on assumptions. This skill inspects repository evidence and creates a tailored README with installation, usage, API, and license sections.

Writing accurate conventional commits from complex staged changes takes time and can produce inconsistent results. This skill inspects staged Git changes and recommends a concise, scoped commit message.

Local applications often fail because runtimes, dependencies, ports, variables, permissions, or services are misconfigured. Env Doctor checks these conditions and returns prioritized, platform-specific fixes without exposing environment values.

Verification tasks often expand beyond their acceptance criteria. This skill selects sufficient checks, reports exact outcomes, and stops when proof is complete.

Broad fixes can introduce unrelated regressions and overwrite existing work. This skill traces each bug to its responsible layer and verifies a focused correction.

Structural code changes can introduce subtle regressions and expand scope. This skill defines behavior boundaries and brackets focused refactors with verification.

Complex migrations can lose data or break compatibility during staged rollouts. This skill structures transitions around preservation, verification, rollback, and mixed-version safety.

Feature work often grows beyond acceptance needs and weakens architectural ownership. Lean Build defines a narrow outcome, reuses repository patterns, and stops after focused verification.

Premature edits can hide causes and introduce new failures. This skill organizes evidence, ranks hypotheses, and identifies a credible mechanism before implementation.

Arquivos de memória longos consomem contexto e tornam sessões repetidas de IA caras. Esta skill compacta arquivos de memória markdown e texto preservando detalhes técnicos, código, URLs e estrutura.

Usuários do Claude Code precisam de recibos de tokens confiáveis sem pedir ao modelo que estime o uso. Esta skill documenta um comando baseado em hook que relata os tokens da sessão e as economias estimadas a partir do log local.

LLM requests can be difficult to measure across SDKs and providers. This skill identifies live callsites, routes them through Caveman, and verifies one measured request.

Revisões de pull request muitas vezes ficam prolixas demais para uma ação rápida. Esta habilidade formata o feedback como comentários concisos, prontos para colar, com localização, problema e correção.

Aggregate repository profiles do not identify a safe or valuable code change by themselves. This skill tests one approved candidate against a controlled baseline.

Experiment lifecycle decisions can be unsafe when evidence or server safeguards are incomplete. This skill reviews current results and recommends one supported action without executing mutations.

Large configuration files and repeated context increase token usage. This skill reviews Caveman reports and applies measured changes with individual approval.

Os usuários podem esquecer os modos, acionadores e opções de configuração do Caveman. Esta skill exibe um cartão de referência compacto sem alterar o modo nem salvar o estado.

Finding relevant code across an unfamiliar repository can consume time and context. This skill searches broadly and returns concise, verified file and line citations.

LLM cost and quality changes are difficult to explain from aggregates alone. This skill produces bounded, trace-supported Caveman Cloud reviews without changing experiments.