Explorar skills

Estimate the sample size and expected duration needed for a product experiment. Use this skill when the user has a primary metric and wants to know how many users are needed to detect a meaningful effect with a chosen confidence level and power.

Use this skill for any documentation task: writing or updating READMEs, creating docstrings, authoring runbooks, writing API documentation, creating onboarding guides, maintaining changelogs, writing architecture docs, or any task where the deliverable is written documentation. Triggers on: "write documentation", "document this", "write a README", "add docstrings", "write a runbook", "API docs", "

Auxilia na criação de artigos para blogs de tecnologia no Zenn, suportando diversos tipos como introduções de projetos, explicações técnicas e registros de TIL/aprendizado.

Pacote de habilidades JUnit 5 para criar, depurar, modernizar, documentar e rotear fluxos de trabalho de teste JVM.

Use when rebuilding a scoped section of legacy code clean-room — when the existing implementation is polluting attempts to improve it and a from-scratch rewrite is wanted. Distills the legacy code to pure functional requirements, builds a firewalled greenfield reimplementation that a separate agent designs WITHOUT ever seeing the legacy code, verifies behavioral parity, and optionally cuts over. T

Gera um Relatório de Auditoria de Prontidão para IA completo e profissional para consultores de IA que trabalham com pequenas e médias empresas. Esta skill auxilia na elaboração de descobertas de auditoria, geração de relatórios para clientes, pontuação da prontidão para IA e transformação de notas de auditoria em um entregável estruturado.

Claude Code 専用。素の `claude` で起動した直後に、タスク説明または issue URL / 番号から命名した git worktree へ `EnterWorktree` で切り替えて作業を開始する。issue 起点・タスク起点どちらでも並列セッション立ち上げに使う。issue URL / 番号入力で Status: Ready の場合は worktree 切り替え後に `issue-implement` へ自動連鎖する。

契約書・利用規約を読み込み、リスク条項・不利な条件・確認すべき点を一覧化するスキル。法的アドバイスではなくチェックリストとして使用する。

Use when (a) operator describes a situation OR a plan step OR the agent shows an inverse pattern, and agent should NAME the right chengyu from the catalog (SELECTOR — default progressive-disclosure; covers current-situation naming, pre-flight plan tagging, and anti-pattern detection); (b) operator asks "what does that mean?" or "what's in this catalog?" (EXPLAINER — four-beat from 成語動畫廊's 熊貓博士 for

Claude Code plugin marketplace + playbook. 9 QA skills (review, security, architecture, performance, WordPress, Terraform) and 8 production guides from an AI-first consultancy.

Comprehensive security and accessibility audit with auto-fix. Spawns 6 agents — two auditors scan in parallel, findings presented by severity for approval, fixes planned with blast radius, applied one-at-a-time with checkpoints, and independently verified.

Compress bios, profile sections, bullets, posts, and visual prompts to strict character limits while preserving hook, proof, mechanism, reader benefit, and CTA.