Explorar skills

Clojure-specific philosophy, idioms, and judgment frameworks. Use when working with Clojure code. Emphasizes data-oriented design, runtime validation with spec, REPL-driven development, and the philosophy of simplicity over ease.

Use when writing, reviewing, or troubleshooting ABAP Cloud code, RAP business objects, CDS views, released APIs, or any ABAP development in S/4HANA Public Cloud or BTP ABAP Environment.

{{ 𝛀𝛀𝛀 }} Run a structured interview to discover new features and produce a batch roadmap proposal. Use this skill when the user wants to explore what to build next, brainstorm features, expand the roadmap, plan a new phase, or says things like 'what should we add', 'help me think through features', 'let's plan the next milestone', or 'interview me about what to build'. Produces a structured pr

Validate git conventions (commit messages, branch naming, PR format, issue linkage) by detecting project-specific rules from CLAUDE.md and settings, inferring patterns from recent history. Use when creating commits, preparing PRs, or reviewing for convention compliance. This skill MUST be consulted because convention-violating history is a defect that every future contributor must question and wor

Generate a human-facing AI usage policy with approved tools, data classification, risk model explanations, and exception processes — saved to $HOME/.ai-first-kit/. Produces a policy document for HUMANS (not agents) that explains what AI tools are approved, what data can be used with AI, and the reasoning behind each decision. Use when the user says 'AI usage policy', 'AI handbook', 'what tools are

Engenheiro de prompts Seedance 2.0 com modos ESCREVER (linguagem natural para prompt de produção), LINT (diagnóstico de anti-padrões) e CORRIGIR (reescrita automática de prompts). Ele aplica formatação e restrições específicas, gerando uma saída compatível com qualquer cliente Seedance.

Um sistema de correção de trabalhos de casa por IA baseado em rubricas que pontua as submissões dos alunos, avalia-as contra as rubricas e gera feedback personalizado. Ele suporta submissões de texto, imagem e modalidade mista, inclui processamento em lote e possui um ciclo de qualidade PDCA com mitigação de viés.

Fluxo de trabalho de assistente de estudo que converte material de estudo em entregáveis focados em exames, como transcrições, notas, explicações (estilo aula e ELI5), flashcards, mapas mentais Mermaid, questionários e perguntas dissertativas.

Run a comprehensive pre-launch website audit covering technical SEO, AI accessibility, security, performance, and on-page SEO. Detects tech stack, tailors checks to framework, orchestrates 5 sub-audits with parallel execution, and delivers a prioritized report with stack-specific fix recommendations. Use when the user asks to audit a site before launch, check staging, review a site before go-live,

Use when a task requires parallel work by multiple specialized agents — e.g., simultaneous code review + security audit + performance check, or multi-object development where different agents handle different components. Orchestrates agent dispatch, manages dependencies, and merges results.

Pre-flight checklist for adding a new feature to a Next.js 15 + TypeScript app. Load when creating a new page, route, server action, or feature module. Forces feature-driven colocation, RSC-first thinking, and the typed cache-tag pattern from line one — prevents the most common AI failures (1500-line page.tsx, 'use client' on the layout, scattered revalidateTag magic strings).

Deep methodology knowledge for MAIC including assumptions, weight diagnostics, ESS interpretation, and anchored vs unanchored decisions. Use when conducting or reviewing MAIC analyses.