Receber por email

Explorar skills

31.375 skills encontradas

debug

11

Use when encountering ANY bug, test failure, unexpected behavior, or error — before proposing fixes. Also use when someone says 'fix this', 'it's broken', 'not working', 'debug', or when a test fails. ESPECIALLY use when under time pressure, when you've already tried a fix that didn't work, or when 'just one quick fix' seems obvious. Never skip this for simple-seeming bugs.

Desenvolvimento #ai #test por burhankhatri

message-bus-security

11

Secure NATS, RabbitMQ, Kafka, and similar message buses against misconfiguration and cross-tenant leakage. Covers account or vhost isolation, deny-default subject and topic permissions, producer and consumer authentication, replay protection, consumer-side idempotency, and encryption in transit and at rest. Invoke when introducing a bus, adding multi-tenancy, or after a cross-tenant message-leakag

Segurança #ai #api por GoldenWing-360

email-deliverability-security

11

Configure email authentication so legitimate mail lands and spoofed mail is blocked. Covers SPF, DKIM, DMARC (with the p=none → p=quarantine → p=reject migration path), MTA-STS, TLS-RPT, ARC, and BIMI. Invoke when launching a new sending domain, when domains are being spoofed, or when transactional email is landing in spam.

Desenvolvimento #ai #api por GoldenWing-360

mbb-decks

11

Use ao gerar apresentações de slides de nível consultoria, apresentações estilo MBB, ou qualquer apresentação de negócios que exija narrativas com títulos de ação, estrutura de princípio da pirâmide, itens MECE e um sistema visual editorial limpo, renderizado em um arquivo .pptx real.

Documentos #ai #pptx por floflo11

golang-samber-do

11

Implementa injeção de dependência em Golang usando samber/do. Utilize esta skill para injeção de dependência, configuração de containers de serviço, gerenciamento de ciclo de vida, refatoração, verificações de saúde, desligamento gracioso ou organização de serviços em escopos/módulos, especialmente com github.com/samber/do/v2.

Desenvolvimento #ai #git por yzfly

ai-infrastructure-together-ai

11

Together AI SDK patterns for TypeScript — client setup, chat completions, streaming, structured output, function calling, embeddings, image generation, fine-tuning, and OpenAI-compatible endpoints

DevOps e Infra #ai #typescript por agents-inc

verify-citations

11

Audit citations in LaTeX files -- check all \cite keys exist in .bib and verify via literature search

Pesquisa e Web #ai #mcp por Agentic-Assets

ai-patterns-tool-use-patterns

11

Provider-agnostic patterns for LLM function calling, tool loops, and agentic workflows

Design e Frontend #ai #llm por agents-inc

dependency-supply-chain

11

Audit and defend against malicious dependencies in npm, pnpm, PyPI, and similar ecosystems. Covers lockfile hygiene, the limits of npm audit, behavior-level scanning with socket.dev, postinstall script review, typosquat and slopsquat detection, and minimum-permission CI runs. Invoke when adding a new dependency, after a supply-chain incident, or as periodic audit.

Segurança #ai #api por GoldenWing-360

facebook-post

11

Write and polish Facebook posts on any topic. Trigger on requests to draft, rewrite, polish, improve a Facebook post, or create cross-platform Facebook, X, and LinkedIn bundles, especially when the user starts with `fbp`.

Automação #ai #llm por mickpletcher

navaigate-notebooklm

11

A integração NavAIgate NotebookLM oferece uma API completa para o Google NotebookLM, com acesso programático total a recursos além da interface web. Permite criar notebooks, adicionar fontes, gerar todos os tipos de artefatos e baixá-los em vários formatos, ativando-se por comando explícito ou intenções.

Automação #ai #api por skyremote

attack-path-architect

11

Generates strategic attack trees and kill chains from reconnaissance data or domain input. Maps MITRE ATT&CK TTPs, identifies chaining opportunities, trust relationships, and prioritizes attack paths by feasibility and impact. Use when user asks for "attack path", "kill chain", "attack tree", "threat modeling from recon", "attack surface analysis", or "prioritize targets". Requires prior recon dat

Desenvolvimento #ai #python por Orizon-eu