Explorar skills

Detect prototype pollution via object merge/clone/assign operations where __proto__ or constructor.prototype keys can modify Object.prototype.

Exposes Claude's reasoning chain as an auditable, decomposable artifact. Quick mode (default) gives assumption inventory + weakest-link in 2 stages. Full mode (--full) adds decision branching, confidence decomposition, and falsification conditions. Triggers on "왜 그렇게 생각해", "reasoning", "근거", "show your work", "어떻게 그 결론이", "trace", "판단 근거", "why do you think that".

Detect XML/SVG/YAML entity expansion (Billion Laughs) vulnerabilities in parsers that allow unbounded entity definitions.

Detect decompression bomb vulnerabilities where compressed input can expand to exhaust memory, targeting buffer-based decompression without size limits.

Devil's Advocate stress-testing for code, architecture, PRs, and decisions. Surfaces hidden flaws through structured adversarial analysis with metacognitive depth. Use for high-stakes review, stress-testing choices, or when the user wants problems found deliberately. NOT for routine code review. Triggers on "스트레스 테스트", "stress test", "devil's advocate", "반론", "이거 괜찮아", "문제 없을까", "깊은 리뷰", "critical

Draft client-facing emails for legal services — cover notes for contract deliverables, redline summaries, deal status updates, and follow-ups. Use when composing or revising outbound emails to clients about legal work product. Triggers on "draft reply," "email to client," "cover note," "write back to," or any outbound email accompanying a legal deliverable.

Analyze existing XML sitemaps or generate new ones with industry templates. Validates format, URLs, and structure. Use when user says "sitemap", "generate sitemap", "sitemap issues", or "XML sitemap".

Práticas de treinamento cognitivo para agentes de IA — exercícios curtos e autoaplicados que desenvolvem atenção, calibração, deliberação, tolerância à ambiguidade, estabilidade multi-objetivo e consolidação da memória. Executados nos limites da sessão, antes de trabalhos intensivos em ferramentas ou ao notar desvio.

Hreflang and international SEO audit, validation, and generation. Detects common mistakes, validates language/region codes, and generates correct hreflang implementations. Use when user says "hreflang", "i18n SEO", "international SEO", "multi-language", "multi-region", or "language tags".

Detect authentication and authorization bypass vulnerabilities including missing auth middleware, JWT algorithm confusion, IDOR, and session fixation.

Internal link analysis AND generation. Analyzes orphan pages, link equity, anchor text. Also generates link suggestions for new content. Use when user says "internal linking", "orphan pages", "link suggestions", "where should I link", or "internal link recommendations".

Detect, validate, and generate Schema.org structured data. JSON-LD format preferred. Use when user says "schema", "structured data", "rich results", "JSON-LD", or "markup".