naticorrea-03
- 17 skills
- 0 followers
- 14 hours ago last updated
- ▌ Lean · naticorrea-03 bundleUse when the user invokes /lean, says "save tokens", "token efficient", "don't drain my tokens", "watch the budget", "cheap mode", or at the start of any large multi-step task where token cost matters. Also use when about to do bulk reads, spawn subagents, or process large files/MCP data and cost discipline is needed.
- ▌
- ▌ Swipe · naticorrea-03 bundleTurn a pile of digital cleanup into a Tinder-style swipe deck on your phone. Point it at a folder (or your unread texts) and it serves a card deck to your phone over local WiFi. Swipe each card left or right, and the chosen action runs in one reversible batch at the end. Files swipe to Trash (recoverable, never deleted outright), texts swipe to skip or reply (replies are staged, never auto-sent). Cards show a real preview whenever possible, not just a filename, so you are never swiping blind. Built for the kind of task paralysis where 300 screenshots in a folder is easier to ignore than to face. Trigger on "/swipe", "let me swipe through my desktop", "swipe to clean out <folder>", "swipe my screenshots", "swipe my downloads", "swipe my unread texts", "give me a deck to clean out X".
- ▌ Flow Map · naticorrea-03 bundleUse when someone wants to audit their whole automation system and see it as a visual map - which agents, crons, routines, and scheduled jobs actually run, where data flows in and out, what writes to what, and what's stale or dead. Trigger on "/flow-map", "map my data flows", "audit my system and map it", "make a flow map", "where does my data actually move", "map my automations".
- ▌ Imessage · naticorrea-03Read and send iMessages via local macOS capabilities (no third-party API). Two modes. Send mode drafts a message and uses AppleScript (`osascript`) on explicit "send it" and requires only Automation, Messages permission (scoped, revocable). Read mode pulls from `~/Library/Messages/chat.db` via sqlite3 and requires Full Disk Access for Terminal, which is a broad permission, so it is opt-in only. Trigger on phrases like "text [person]", "iMessage [person]", "draft an imessage", "read my texts from [person]", "what did [person] text me", "/imessage". Defaults to drafts-only, never auto-sends.
- ▌ Build Mode · naticorrea-03A teach-while-building working mode for leveling up engineering judgment with AI. When ON, after writing any non-trivial code Claude gives a short plain-English explanation plus the one design choice it made, surfaces design decisions as options-with-tradeoffs for you to pick (never silently chooses), explains fundamentals in context (2-minute, plain English), one-tap logs anything unclear to a running learning log, and runs a 2-3 question gut-check at the end of a build session. Push-not-pull, no streaks, no guilt, no cutoffs. Applies to ANY build, not one project. Trigger on "/build-mode", "build mode on", "build mode off", "learn mode", "teach mode", or when you start a coding/build session and ask for it.
- ▌ Meta Prompt · naticorrea-03 bundleBuilds ready-to-paste Meta AI (Muse Spark) prompts for reading Instagram, Facebook, and Threads directly. Describe a research goal (find micro-influencers or ambassadors, find videos to react to, monitor brand mentions, scan niche trends, check saturation, mine comments, tear down a competitor, verify handles, study a creator's voice before a pitch) and this skill asks a few clarifying questions, fills the variables (niche, follower range, brand, time window, etc.), and outputs a copy-paste prompt for the meta.ai app. It also hands out the Hook Machine, a full multi-turn workflow that analyzes a creator's top reels, extracts why the winners win, builds a grading rubric, then generates, grades, and rewrites hooks. It never calls Meta AI itself and never invents capabilities. Trigger on "/meta-prompt", "build a meta ai prompt", "meta prompt for <goal>", "find microinfluencers on instagram", "find videos to react to", "monitor mentions of <brand>", "what's trending on instagram for <niche>", "hook machine", "ana
- ▌
- ▌ Problem Log · naticorrea-03 bundleA hands-off daily log of how you actually solve problems. Once a day it reads your Claude Code sessions and writes a short entry per real problem-solving arc (the problem, how you worked it, the outcome) to a local markdown file. Great for standups, reviews, interviews, or just remembering what you figured out.
- ▌ AI Writing QA · naticorrea-03Scrubs scripts and copy for AI tells before they ship, then hands back a clean rewrite in your voice. Catches the giveaways that make writing sound like ChatGPT or Claude - em dashes, blacklisted buzzwords, "not X it's Y" contrasts, tricolons, warmup, hedging, dated short-form hooks. Auto-detects register (client-facing / internal / creative) and applies that voice. Trigger on "/ai-writing-qa", "scrub this", "de-slop this", "does this sound like AI", "QA this script", "QA this copy", "check this for AI tells", "make this sound human", or when you paste a script, caption, email, or piece of copy and want it cleaned before it ships. On-demand only, never auto-fires, never sends, never saves.
- ▌ Build Capture · naticorrea-03 bundleA hands-off daily log of everything you build in Claude Code. Once a day it reads that day's sessions and the files that changed, and appends a short entry per real build (what it is, what shipped) to a local markdown file. No /wrap, no manual step. Perfect for standups, changelogs, or a running record of what you've made.
- ▌
- ▌ Pressure Test · naticorrea-03Brutally honest startup cofounder that pressure-tests a business idea against Sam Altman's Startup Playbook. NOT a yes-machine. Grades the idea across five areas (Idea, Product, Team/You, Execution, Market/Timing), names the most likely way you quietly kill it yourself, and ends with three ranked weaknesses plus the one thing to do first. Trigger on "/pressure-test", "pressure-test my idea", "stress-test this business", "be my brutal cofounder", "is this a good startup idea", "poke holes in this", "what's wrong with this idea". Use for evaluating a business/side-venture concept, NOT for code, fulfillment, or client work. A cold, playbook-driven, harsh read of a business idea.
- ▌ Video Breakdown · naticorrea-03 bundleBreak down any video (YouTube, Loom, Instagram, TikTok, local file) frame by frame. Downloads the video, rips scene-change frames + a timestamped transcript locally, then Claude reads the visuals AND the words together to produce a content teardown — hooks, structure, on-screen visuals, why it works. Built in-house, no third-party code, only yt-dlp + ffmpeg. Trigger on "/video-breakdown", "break down this video", "analyze this reel/video", "teardown <url>", "what's working in this video".
- ▌ Viral Hook Creator · naticorrea-03 bundleGenerates OR grades viral social media hooks using a library of proven patterns, structures, a swipe file, and trigger words. Trigger on "/viral-hook-creator", "write viral hooks for <topic>", "draft hook options for <topic>" (GENERATE mode), or "grade this hook", "is this hook strong", "strengthen this hook", "score my hook", "make this hook better" (GRADE mode).
- ▌
- ▌ Working With Claude · naticorrea-03Anthropic's official best practices for collaborating with Claude well, distilled from the Anthropic Academy courses. Covers the 4D framework (Delegation, Description, Discernment, Diligence), Claude's real capabilities and limitations, the prompting techniques that actually move quality, and the operating discipline for Claude Code. Use when starting a build / code / design / strategy task, when deciding what to hand to AI vs keep human, when a prompt is not landing, when evaluating whether Claude's output is trustworthy, or whenever you want to work with Claude the way Anthropic teaches. Complements build-mode (teach-while-building), frontend-design (UI aesthetics), and claude-api (API/model reference); this skill is the high-level "how to collaborate with Claude" layer.