omc-setup
Setup and configure oh-my-claudecode (the ONLY command you need to learn)
Install
mkdir -p .claude/skills/omc-setup && curl -L -o skill.zip "https://mcp.directory/api/skills/download/1078" && unzip -o skill.zip -d .claude/skills/omc-setup && rm skill.zipInstalls to .claude/skills/omc-setup
About this skill
OMC Setup
This is the only command you need to learn. After running this, everything else is automatic.
Note: All ~/.claude/... paths in this guide respect CLAUDE_CONFIG_DIR when that environment variable is set.
Pre-Setup Check: Already Configured?
CRITICAL: Before doing anything else, check if setup has already been completed. This prevents users from having to re-run the full setup wizard after every update.
# Check if setup was already completed
CONFIG_FILE="$HOME/.claude/.omc-config.json"
if [ -f "$CONFIG_FILE" ]; then
SETUP_COMPLETED=$(jq -r '.setupCompleted // empty' "$CONFIG_FILE" 2>/dev/null)
SETUP_VERSION=$(jq -r '.setupVersion // empty' "$CONFIG_FILE" 2>/dev/null)
if [ -n "$SETUP_COMPLETED" ] && [ "$SETUP_COMPLETED" != "null" ]; then
echo "OMC setup was already completed on: $SETUP_COMPLETED"
[ -n "$SETUP_VERSION" ] && echo "Setup version: $SETUP_VERSION"
ALREADY_CONFIGURED="true"
fi
fi
If Already Configured (and no --force flag)
If ALREADY_CONFIGURED is true AND the user did NOT pass --force, --local, or --global flags:
Use AskUserQuestion to prompt:
Question: "OMC is already configured. What would you like to do?"
Options:
- Update CLAUDE.md only - Download latest CLAUDE.md without re-running full setup
- Run full setup again - Go through the complete setup wizard
- Cancel - Exit without changes
If user chooses "Update CLAUDE.md only":
- Detect if local (.claude/CLAUDE.md) or global (~/.claude/CLAUDE.md) config exists
- If local exists, run the download/merge script from Step 2A
- If only global exists, run the download/merge script from Step 2B
- Skip all other steps
- Report success and exit
If user chooses "Run full setup again":
- Continue with Step 0 (Resume Detection) below
If user chooses "Cancel":
- Exit without any changes
Force Flag Override
If user passes --force flag, skip this check and proceed directly to setup.
Graceful Interrupt Handling
IMPORTANT: This setup process saves progress after each step. If interrupted (Ctrl+C or connection loss), the setup can resume from where it left off.
State File Location
.omc/state/setup-state.json- Tracks completed steps
Resume Detection (Step 0)
Before starting any step, check for existing state:
# Check for existing setup state
STATE_FILE=".omc/state/setup-state.json"
# Cross-platform ISO date to epoch conversion
iso_to_epoch() {
local iso_date="$1"
local epoch=""
# Try GNU date first (Linux)
epoch=$(date -d "$iso_date" +%s 2>/dev/null)
if [ $? -eq 0 ] && [ -n "$epoch" ]; then
echo "$epoch"
return 0
fi
# Try BSD/macOS date
local clean_date=$(echo "$iso_date" | sed 's/[+-][0-9][0-9]:[0-9][0-9]$//' | sed 's/Z$//' | sed 's/T/ /')
epoch=$(date -j -f "%Y-%m-%d %H:%M:%S" "$clean_date" +%s 2>/dev/null)
if [ $? -eq 0 ] && [ -n "$epoch" ]; then
echo "$epoch"
return 0
fi
echo "0"
}
if [ -f "$STATE_FILE" ]; then
# Check if state is stale (older than 24 hours)
TIMESTAMP_RAW=$(jq -r '.timestamp // empty' "$STATE_FILE" 2>/dev/null)
if [ -n "$TIMESTAMP_RAW" ]; then
TIMESTAMP_EPOCH=$(iso_to_epoch "$TIMESTAMP_RAW")
NOW_EPOCH=$(date +%s)
STATE_AGE=$((NOW_EPOCH - TIMESTAMP_EPOCH))
else
STATE_AGE=999999 # Force fresh start if no timestamp
fi
if [ "$STATE_AGE" -gt 86400 ]; then
echo "Previous setup state is more than 24 hours old. Starting fresh."
rm -f "$STATE_FILE"
else
LAST_STEP=$(jq -r ".lastCompletedStep // 0" "$STATE_FILE" 2>/dev/null || echo "0")
TIMESTAMP=$(jq -r .timestamp "$STATE_FILE" 2>/dev/null || echo "unknown")
echo "Found previous setup session (Step $LAST_STEP completed at $TIMESTAMP)"
fi
fi
If state exists, use AskUserQuestion to prompt:
Question: "Found a previous setup session. Would you like to resume or start fresh?"
Options:
- Resume from step $LAST_STEP - Continue where you left off
- Start fresh - Begin from the beginning (clears saved state)
If user chooses "Start fresh":
rm -f ".omc/state/setup-state.json"
echo "Previous state cleared. Starting fresh setup."
Save Progress Helper
After completing each major step, save progress:
# Save setup progress (call after each step)
# Usage: save_setup_progress STEP_NUMBER
save_setup_progress() {
mkdir -p .omc/state
cat > ".omc/state/setup-state.json" << EOF
{
"lastCompletedStep": $1,
"timestamp": "$(date -Iseconds)",
"configType": "${CONFIG_TYPE:-unknown}"
}
EOF
}
Clear State on Completion
After successful setup completion (Step 7/8), remove the state file:
rm -f ".omc/state/setup-state.json"
echo "Setup completed successfully. State cleared."
Usage Modes
This skill handles three scenarios:
- Initial Setup (no flags): First-time installation wizard
- Local Configuration (
--local): Configure project-specific settings (.claude/CLAUDE.md) - Global Configuration (
--global): Configure global settings (~/.claude/CLAUDE.md)
Mode Detection
Check for flags in the user's invocation:
- If
--localflag present → Skip Pre-Setup Check, go to Local Configuration (Step 2A) - If
--globalflag present → Skip Pre-Setup Check, go to Global Configuration (Step 2B) - If
--forceflag present → Skip Pre-Setup Check, run Initial Setup wizard (Step 1) - If no flags → Run Pre-Setup Check first, then Initial Setup wizard (Step 1) if needed
Step 1: Initial Setup Wizard (Default Behavior)
Note: If resuming and lastCompletedStep >= 1, skip to the appropriate step based on configType.
Use the AskUserQuestion tool to prompt the user:
Question: "Where should I configure oh-my-claudecode?"
Options:
- Local (this project) - Creates
.claude/CLAUDE.mdin current project directory. Best for project-specific configurations. - Global (all projects) - Creates
~/.claude/CLAUDE.mdfor all Claude Code sessions. Best for consistent behavior everywhere.
Step 2A: Local Configuration (--local flag or user chose LOCAL)
CRITICAL: This ALWAYS downloads fresh CLAUDE.md from GitHub to the local project. DO NOT use the Write tool - use bash curl exclusively.
Create Local .claude Directory
# Create .claude directory in current project
mkdir -p .claude && echo ".claude directory ready"
Download Fresh CLAUDE.md
# Define target path
TARGET_PATH=".claude/CLAUDE.md"
# Extract old version before download
OLD_VERSION=$(grep -m1 "^# oh-my-claudecode" "$TARGET_PATH" 2>/dev/null | grep -oE 'v[0-9]+\.[0-9]+\.[0-9]+' || echo "none")
# Backup existing
if [ -f "$TARGET_PATH" ]; then
BACKUP_DATE=$(date +%Y-%m-%d_%H%M%S)
BACKUP_PATH="${TARGET_PATH}.backup.${BACKUP_DATE}"
cp "$TARGET_PATH" "$BACKUP_PATH"
echo "Backed up existing CLAUDE.md to $BACKUP_PATH"
fi
# Download fresh OMC content to temp file
TEMP_OMC=$(mktemp /tmp/omc-claude-XXXXXX.md)
trap 'rm -f "$TEMP_OMC"' EXIT
curl -fsSL "https://raw.githubusercontent.com/Yeachan-Heo/oh-my-claudecode/main/docs/CLAUDE.md" -o "$TEMP_OMC"
if [ ! -s "$TEMP_OMC" ]; then
echo "ERROR: Failed to download CLAUDE.md. Aborting."
rm -f "$TEMP_OMC"
return 1
fi
# Strip existing markers from downloaded content (idempotency)
if grep -q '<!-- OMC:START -->' "$TEMP_OMC"; then
# Extract content between markers (awk is portable across GNU/BSD)
awk '/<!-- OMC:END -->/{p=0} p; /<!-- OMC:START -->/{p=1}' "$TEMP_OMC" > "${TEMP_OMC}.clean"
mv "${TEMP_OMC}.clean" "$TEMP_OMC"
fi
if [ ! -f "$TARGET_PATH" ]; then
# Fresh install: wrap in markers
{
echo '<!-- OMC:START -->'
cat "$TEMP_OMC"
echo '<!-- OMC:END -->'
} > "$TARGET_PATH"
rm -f "$TEMP_OMC"
echo "Installed CLAUDE.md (fresh)"
else
# Merge: preserve user content outside OMC markers
if grep -q '<!-- OMC:START -->' "$TARGET_PATH"; then
# Has markers: replace OMC section, keep user content
# Use awk instead of sed for cross-platform compatibility (GNU/BSD)
BEFORE_OMC=$(awk '/<!-- OMC:START -->/{exit} {print}' "$TARGET_PATH")
AFTER_OMC=$(awk 'p; /<!-- OMC:END -->/{p=1}' "$TARGET_PATH")
{
[ -n "$BEFORE_OMC" ] && printf '%s\n' "$BEFORE_OMC"
echo '<!-- OMC:START -->'
cat "$TEMP_OMC"
echo '<!-- OMC:END -->'
[ -n "$AFTER_OMC" ] && printf '%s\n' "$AFTER_OMC"
} > "${TARGET_PATH}.tmp"
mv "${TARGET_PATH}.tmp" "$TARGET_PATH"
echo "Updated OMC section (user customizations preserved)"
else
# No markers: wrap new content in markers, append old content as user section
OLD_CONTENT=$(cat "$TARGET_PATH")
{
echo '<!-- OMC:START -->'
cat "$TEMP_OMC"
echo '<!-- OMC:END -->'
echo ""
echo "<!-- User customizations (migrated from previous CLAUDE.md) -->"
printf '%s\n' "$OLD_CONTENT"
} > "${TARGET_PATH}.tmp"
mv "${TARGET_PATH}.tmp" "$TARGET_PATH"
echo "Migrated existing CLAUDE.md (added OMC markers, preserved old content)"
fi
rm -f "$TEMP_OMC"
fi
# Extract new version and report
NEW_VERSION=$(grep -m1 "^# oh-my-claudecode" "$TARGET_PATH" 2>/dev/null | grep -oE 'v[0-9]+\.[0-9]+\.[0-9]+' || echo "unknown")
if [ "$OLD_VERSION" = "none" ]; then
echo "Installed CLAUDE.md: $NEW_VERSION"
elif [ "$OLD_VERSION" = "$NEW_VERSION" ]; then
echo "CLAUDE.md unchanged: $NEW_VERSION"
else
echo "Updated CLAUDE.md: $OLD_VERSION -> $NEW_VERSION"
fi
Note: The downloaded CLAUDE.md includes Context Persistence instructions with <remember> tags for surviving conversation compaction.
Note: If an existing CLAUDE.md is found, it will be backed up to .claude/CLAUDE.md.backup.YYYY-MM-DD before downloading the new version.
MANDATORY: Always run this command. Do NOT skip. Do NOT use Write tool.
FALLBACK if curl fails: Tell user to manually download from: https://raw.githubusercontent.com/Yeachan-Heo/oh-my-claudecode/main/docs/CLAUDE.md
Verify Plugin Installation
grep -q "oh-my-claudecode" ~/.c
---
*Content truncated.*
More by Yeachan-Heo
View all skills by Yeachan-Heo →You might also like
flutter-development
aj-geddes
Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.
ui-ux-pro-max
nextlevelbuilder
"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."
drawio-diagrams-enhanced
jgtolentino
Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.
godot
bfollington
This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.
nano-banana-pro
garg-aayush
Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.
pdf-to-markdown
aliceisjustplaying
Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.
Related MCP Servers
Browse all serversManage Alibaba Cloud ECS, monitor metrics, and configure VPC networks effortlessly using natural language commands with
Integrate with Superjolt to manage JavaScript apps, configure domains, set environment variables, and monitor logs using
Connect AI agents to Jira & Confluence securely. Read-only by default, pre-configured connections, compact TSV output. N
Extend your developer tools with GitHub MCP Server for advanced automation, supporting GitHub Student and student packag
Unlock seamless Figma to code: streamline Figma to HTML with Framelink MCP Server for fast, accurate design-to-code work
Terminal control, file system search, and diff-based file editing for Claude and other AI assistants. Execute shell comm
Stay ahead of the MCP ecosystem
Get weekly updates on new skills and servers.