Receber por email

Explorar skills

2.582 skills encontradas

karpathy-article-writing

11

Write technical blog posts in the voice of Andrej Karpathy — first-person, build-from-scratch, mixing deep technical substance with conversational warmth, dry humor, vivid analogies, and intellectually honest hedging. Use when the user asks for a post "in Karpathy's style," a "Karpathy-flavored" writeup, or wants to turn an experiment/reproduction/tutorial into something that reads like karpathy.g

Escrita e Conteúdo #llm por IrtezaAsadRizvi

postgres-hardening

11

Harden a PostgreSQL deployment whether managed or self-hosted. Covers pg_hba network and authentication rules, role separation (read-only, read-write, migration), row-level security for multi-tenant data, TLS configuration, backup encryption, and pg_audit logging. Invoke when provisioning a new Postgres, before opening it to a new app, or when reviewing a multi-tenant schema for isolation gaps.

Segurança #ai #api por GoldenWing-360

x-post

11

Write posts for X on tech, PowerShell, IT automation, and fitness topics. Always trigger immediately when the user's message starts with "xp". Produce a single post within 280 characters, no emojis, avoid em dashes in final X post output, and use 2 to 3 hashtags maximum.

Automação #ai #llm por mickpletcher

incident-response

11

Run a structured response to a suspected web or server compromise. Follows SANS PICERL — Preparation, Identification, Containment, Eradication, Recovery, Lessons Learned — and includes a post-mortem template. Invoke when a site is defaced, when malware or webshells appear, when admin accounts arrive unannounced, or when a provider sends an abuse notice.

Segurança #ai #api por GoldenWing-360

llm-coding-failure-modes

11

Recognize the recurring security failure modes of LLM coding agents — Claude Code, Copilot, Cursor, Windsurf, and similar. Covers bulk operations without per-item review, safety-guard bypass as friction removal, acting on indirect injection, secrets in logs and commits, slopsquatting, outdated training patterns, sycophancy on insecure proposals, and silent error swallowing. Invoke when reviewing L

Segurança #ai #api por GoldenWing-360

blog-post

11

Escreva ou rascunhe uma postagem para o blog de TI do Mick em mickitblog.blogspot.com. Acione quando Mick solicitar uma postagem ou quiser documentar uma solução técnica, projeto ou descoberta, combinando seu estilo de escrita com prosa simples em primeira pessoa, foco prático, notas de status honestas, blocos de código relevantes e links do GitHub quando aplicável.

Escrita e Conteúdo #ai #git por mickpletcher

med-vault

11

Securely track medications, supplements, interactions, and schedules using manual entry or uploaded prescription label images.

Automação #ai #llm por mickpletcher

blog-to-social

11

Convert a finished blog post into three ready-to-post social media versions in one pass for Facebook, X, and LinkedIn. Trigger when the user pastes or links a blog post and asks to share it, promote it, or turn it into social content.

Escrita e Conteúdo #ai #llm por mickpletcher

fitness-log

11

Track workouts, log fitness progress, adjust the training program, and generate Facebook posts from workout data. Trigger on workout logging, PR updates, program questions, and fitness progress summaries.

Automação #ai #llm por mickpletcher

github-repo-architect

11

Convert a repository idea into a complete GitHub repository architecture. Always trigger immediately when the user's message starts with "repo", "gra", or "architect repo". Also trigger on "build a repo structure", "design a GitHub repo", "scaffold this repository", "create repository architecture", "turn this idea into a repo", or any request to generate README, folder layout, prompts, GitHub Act

Design e Frontend #ai #git por mickpletcher

travel-planning

11

Plan trips, build itineraries, research destinations, estimate budgets, and organize logistics for Mick's travel. Always trigger immediately when the user mentions planning a trip, asks about flights, hotels, itineraries, destinations, or uses phrases like "trip to", "travel to", "planning a visit", "what should I do in", "how do I get to", "how much will this cost", or references any upcoming tra

Design e Frontend #ai #llm por mickpletcher

api-security

11

Apply the OWASP API Security Top 10 to REST and GraphQL endpoints. Covers broken object-level authorization (BOLA), mass assignment, excessive data exposure, unrestricted resource consumption, SSRF, broken function-level authorization, and GraphQL depth and complexity limits. Invoke when designing a new API, reviewing one before scaling, or after API abuse (scraping, account takeover).

Segurança #ai #api por GoldenWing-360