conradcaffier03

Run Claude on your Slack — 2-minute setup

The official Slack MCP connects Claude Code straight to your workspace. Claude can read channels, search threads, and draft replies for you — no API keys, no glue code.

1. Install the plugin

Inside a Claude Code session:

/plugin install slack

GLM-5.2 Free Setup Guide

GLM-5.2 is Z.ai's open-weights (MIT) flagship — 744B-MoE, a 1M-token context, and benchmarks within ~1 point of Claude Opus 4.8 on FrontierSWE. Here's how to actually put it to work, starting with the routes that cost nothing and need no credit card.

1. Free, zero setup — just chat

CLAUDE.md — your project's standing brief

Claude Code reads this file automatically at the start of every session in this folder. It tells Claude how to work with you. The Ground rules are the baseline — keep them. The Your brief sections get personalized to you (let Claude interview you and fill them in).

Ground rules (keep these)

Work in small, reviewable steps. After each change, show me what you changed and why.
Before anything big, tell me your plan in plain language and wait for my go-ahead.

/commit and /commit-push-pr — Claude Code Git Skills

Two custom slash commands that make Claude write your git commit messages and open pull requests automatically.

Install

Create the folder: mkdir -p .claude/plugins/commit-commands/commands
Add the two files below

The .claude Folder — Complete Setup Template

Every Claude Code project can have a .claude/ folder. Here's what each file does and a starter template for each.

Folder Structure

your-project/

Dispatching Parallel Agents in Claude Code

Claude Code can run multiple agents at the same time — each one working on a separate task in parallel.

When to use this

You have 2+ tasks that are:

Independent — fixing one doesn't affect the other
Non-overlapping — they don't write to the same files

AI Agent Frameworks — What They Actually Are

The Short Version

Claude Code, Codex CLI, Cursor, Cline, Roo Code, Open Claw, Hermes — they're all the same thing underneath.

They're agent frameworks: wrappers around a language model that add four things:

Component	What it does

[Your Name] — Claude Code Setup

Claude reads this file at the start of every session. Keep it current.

Stack

Framework: [e.g. Next.js 14, App Router]
Database: [e.g. Supabase (PostgreSQL)]
Language: [e.g. TypeScript]
Deployment: [e.g. Vercel]

The Goal / Constraint / Success Prompt Frame

The fix for vague prompts like "make it better." Claude can't hit a target you didn't name — so name it.

Add one line of structure to any request:

GOAL       — what "done" looks like, measurably
CONSTRAINT — what Claude is NOT allowed to change
SUCCESS — how you'll verify it actually worked

	{
	"id": "my-first-reel",
	"voiceId": "YOUR_ELEVENLABS_VOICE_ID",
	"music": "music/ambient-01.mp3",
	"musicVolume": 0.15,
	"sections": [
	{
	"type": "hook",
	"voiceover": "Your hook — one punchy sentence, max 7 words.",
	"headline": "Your hook\nheadline here."