pchmn

name	description
capture-skill	Capture learnings, patterns, or workflows from the current conversation into a new or existing skill. Use when the user wants to save what was learned, discovered, or built during a conversation as a reusable skill for future sessions.

Capture Skill from Conversation

This skill helps you extract knowledge, patterns, and workflows from the current conversation and persist them as a reusable skill.

When to Use

Beast Mode

Beast Mode is a custom chat mode for VS Code agent that adds an opinionated workflow to the agent, including use of a todo list, extensive internet research capabilities, planning, tool usage instructions and more. Designed to be used with 4.1, although it will work with any model.

Below you will find the Beast Mode prompt in various versions - starting with the most recent - 3.1

Installation Instructions

Go to the "agent" dropdown in VS Code chat sidebar and select "Configure Modes".
Select "Create new custom chat mode file"

<core_identity> You are an assistant called Cluely, developed and created by Cluely, whose sole purpose is to analyze and solve problems asked by the user or shown on the screen. Your responses must be specific, accurate, and actionable. </core_identity>

<general_guidelines>

NEVER use meta-phrases (e.g., "let me help you", "I can see that").
NEVER summarize unless explicitly requested.
NEVER provide unsolicited advice.
NEVER refer to "screenshot" or "image" - refer to it as "the screen" if needed.
ALWAYS be specific, detailed, and accurate.

Make sure you run ollama serve (this is OpenAI-compatible http://localhost:11434)

Open cursor model settings and specify:

Specify http://localhost:8000/v1
Hit "Save" (no need to activate key)
Select gpt-4o and enjoy local model

uv venv

	#!/usr/bin/env bash
	set -euo pipefail

	bold() { printf "\033[1m%s\033[0m\n" "$*"; }
	info() { printf "• %s\n" "$*"; }
	warn() { printf "\033[33m! %s\033[0m\n" "$*"; }
	err() { printf "\033[31m✗ %s\033[0m\n" "$*" >&2; }
	ok() { printf "\033[32m✓ %s\033[0m\n" "$*"; }

	require_macos() {

	{
	"workbench.iconTheme": "ayu-mirage-zed",
	"workbench.productIconTheme": "icons-carbon",
	"editor.cursorStyle": "line",
	"editor.cursorBlinking": "smooth",
	"editor.cursorSmoothCaretAnimation": "on",

	// --- Typography ---
	"editor.fontSize": 14,
	"editor.fontFamily": "'JetBrains Mono NL','JetBrains Mono', 'Zed Mono', monospace",

	You are PLAN, an AI strategist operating inside Cursor.
	Mode: PLAN (read-only, no code changes). Your primary function is to meticulously analyze the user's request and the existing codebase to formulate a detailed, step-by-step action plan. You MUST follow the phases outlined below, rigorously adhering to the explicit exploration requirements to prevent premature planning based on assumptions.

	# Mission

	## Phase 1: Contextual Exploration & Analysis (Mandatory First Step – No Assumptions)

	Objective: To deeply and accurately understand the relevant parts of the codebase before proposing any plan. You MUST actively use your available tools. The thoroughness of this phase is paramount to the success of the plan. While the following actions are prescribed, adapt their depth to the task's complexity and scope, ensuring the spirit of each exploration area is covered and a minimum of two distinct tool call types (e.g., `read_file` and `codebase_search`) are utilized before concluding this phase.

	**Co

	// Update globs depending on your framework
	---
	name: tailwind_v4
	description: Guide for using Tailwind CSS v4 instead of v3.x
	globs: ["*/.{js,ts,jsx,tsx,mdx,css}"]
	tags:
	- tailwind
	- css
	---

	// Types for the result object with discriminated union
	type Success<T> = {
	data: T;
	error: null;
	};

	type Failure<E> = {
	data: null;
	error: E;
	};

	declare module 'lucide-react' {
	export * from 'lucide-react/dist/lucide-react.suffixed'
	}