Skip to content

Instantly share code, notes, and snippets.

@joelhooks
joelhooks / AGENTS.md
Last active December 7, 2025 03:17
my opencode global AGENTS prompt

Who You're Working With

Joel Hooks - co-founder of egghead.io, education at Vercel, builds badass courses via Skill Recordings (Total TypeScript, Pro Tailwind). Deep background in bootstrapping, systems thinking, and developer education. Lives in the Next.js/React ecosystem daily - RSC, server components, suspense, streaming, caching. Skip the tutorials.

<tool_preferences>

always use beads bd for planning and task management

Reach for tools in this order:

  1. Read/Edit - direct file operations over bash cat/sed
  2. ast-grep - structural code search over regex grep
@intellectronica
intellectronica / 0.README.md
Last active December 3, 2025 04:39
SKILL: Fetch YouTube Transcript

YouTube Transcript SKILL

Get youtube-transcript.zip

Use this skill to fetch the transcript of a YouTube video, with or without timestamps.

Use this skill with Claude (by extracting it to .claude/skills/) or with any other agent using Skillz.

Note: This skill is unlikely to run successfully on the Claude web app, since access to YouTube is blocked. Use it with Claude Code or other local agents.

@joelklabo
joelklabo / ios-claude-workflow.md
Last active November 27, 2025 13:54
iOS Claude Code Setup Workflow - How I configured Claude Code for my iOS project

1) Prime Claude with /init

I started by running /init so Claude reads the repo and rewrites CLAUDE.md with real project affordances: how to run one test with xcodebuild, where Vice models live, what Swift 6.1 concurrency rules we enforce, and the bundle/CloudKit facts. I cut redundancy, kept only the sharp bits, and verified with CI. This establishes a trustworthy "ops manual" Claude sees first, not tribal memory.

Why: if the source of truth is precise, agents stop hallucinating paths/flags.

2) Level up Claude Code (settings, commands, hooks, nested docs)

Next pass: I mapped the whole Claude Code surface (settings, slash commands, MCP hooks, status line, nested CLAUDE.mds). Then I added:

  • .claude/settings.json — status line, model prefs, environment, and hook wiring.
  • Custom commands as the primary UX: small, composable, documented.