Give Claude Eyes — watch any video frame-by-frame, 100% local (buildwith.conrad)
🛠️ Want the rest of my tools? Grab them at get.caffier-agency.com/start
Freebie for the EYES keyword (reel-47, "Give Claude eyes"). Deliver as a public GitHub Gist — numbered steps the user can run today, not a raw link. Value-first: by the end you have a Claude Code skill that sees a video (every cut, every on-screen detail), not just reads its transcript.
Most people run Claude Code like a smarter autocomplete. The thing that flips it into an actual agent is MCP — the Model Context Protocol, the standard "plug" that lets Claude reach real tools instead of only talking about them: the live web, a browser, your GitHub, your Notion, your Figma. You connect a server once and Claude can use it in any project.
You don't need a tutorial from me for the wiring — Anthropic's own guide walks you through adding any server in a minute, and each tool below links its own setup docs. Start here for the "how do I add one" part: Connect Claude Code to tools via MCP. Then pick from the five below — I've written what each actually unlocks, and given you the official place to grab it and the how-to docs to set it up properly.
One rule before you install anything: only add servers you trust, and keep every API key or token on your own machine.
| name | subagent-intern-setup |
|---|---|
| description | The exact setup to make Claude Code hire its own interns — dispatch multiple subagents from ONE prompt so it works several tracks in parallel while you watch. Numbered steps you can start from today. Triggers the INTERN keyword reel freebie. |
| keyword | INTERN |
| reel | reel-49-subagent-intern |
The exact setup from the "Your AI agent just hired itself an intern" reel. This isn't a prompt or a
Anthropic quietly shipped this in May 2026: Claude for Small Business — 15 done-for-you agentic workflows, built into Claude, no extra cost on your existing plan. Most owners don't know it's there. Here's the exact list, plus the free course Anthropic built to walk you through it.
Freebie for the BUILD keyword (reel-44, "Stop Paying For Software"). Deliver as a public GitHub Gist (numbered steps the user can start from today — not a raw link). Value-first: this alone should replace one subscription you're paying for right now.
The exact method I use to replace a paid app with a tool I own — plus the copy-paste prompt that makes
Freebie for the INBOX keyword (reel-42). Deliver as a GitHub Gist (numbered steps the user can actually start from — not a raw link). Value-first: this alone should save them ~2h/week.
Claude reads an incoming email and writes back a reply that sounds like you — ready to send. You skim, tweak one line, hit send. Set up once, use every morning.
---
name: hook-lab
description: Generate 10 scroll-stopping hooks for a topic — 10 directions, each privately scored 1–100. You pick your favourite blind, then the scores are revealed, then you choose — and get a focused strategy brief for the hook you picked. Reads _creator-profile.md for voice/audience. Triggers: "hooks for", "write hooks", "hook ideas", or after content-calendar.
---
This is a real Claude Code skill — the actual
hook-labfrom my Content-to-Cash pack, given away free. It's not a prompt or a swipe file. Drop it into Claude Code and it writes 10 hooks across proven frameworks, scores each one 1–100 for how hard it stops your audience, and hands you a strategy brief for the one you
---
name: validate-idea
description: Pressure-test a digital-product idea before building it, using only Claude Code. Interviews you one question at a time, separates real evidence from wishful thinking, ranks the one assumption that would kill the idea, and ends in a single PROCEED / PIVOT / STOP call plus one cheap, falsifiable experiment. Triggers: "validate my idea", "is this worth building", "first product idea".
---
This is a real Claude Code skill — the actual
validate-ideafrom my First Product pack, given away free. It's not a prompt or a checklist. Drop it into Claude Code and it runs the whole interview, scores your idea, and hands you a verdict a paid validator would charge for. Built by @buildwith.conrad.
Everyone feels 10× more productive with AI. Almost nobody measures it. Here's the exact setup I use to track agent leverage as a live KPI — how many hours my agents work for every hour I put in. Mine moves week to week — recomputed straight from the logs every time, currently around 7:1.
The whole thing reads from data you already have: your Claude Code session logs.
CC Switch is a free, open-source desktop app (107K ★) that tracks your Claude Code spend per model — and lets you switch providers in one click. macOS, Windows, Linux.
Download the latest release for your OS: