Explorar skills
2.582 skills encontradas
karpathy-article-writing
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
postgres-hardening
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.
x-post
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.
incident-response
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.
llm-coding-failure-modes
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safety-guard bypass as friction removal, acting on indirect injection, secrets in logs and commits, slopsquatting, outdated training patterns, sycophancy on insecure proposals, and silent error swallowing.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
blog-post
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.
med-vault
Securely track medications, supplements, interactions, and schedules using manual entry or uploaded prescription label images.
blog-to-social
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.
fitness-log
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.
github-repo-architect
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
travel-planning
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
api-security
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).