ncloud-maps
Query Naver Cloud Maps APIs for route navigation. Smart routing: Directions5 by default, auto-switches to Directions15 for 5+ waypoints.
Best use case
ncloud-maps is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Query Naver Cloud Maps APIs for route navigation. Smart routing: Directions5 by default, auto-switches to Directions15 for 5+ waypoints.
Teams using ncloud-maps should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/ncloud-maps/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How ncloud-maps Compares
| Feature / Agent | ncloud-maps | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Query Naver Cloud Maps APIs for route navigation. Smart routing: Directions5 by default, auto-switches to Directions15 for 5+ waypoints.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
SKILL.md Source
## Prompt
When a user requests a route calculation with addresses or coordinates, use this skill to calculate driving time, distance, and cost.
**Usage:**
- `/skill ncloud-maps <start> <goal> [waypoints]`
- Start and goal must be in `longitude,latitude` format OR addresses (convert using goplaces/naver-local-search first)
- Returns: distance, duration, toll fare, taxi fare, fuel cost
**Examples:**
- `/skill ncloud-maps "126.9633,37.5524" "127.0165,37.4889"` (coordinates)
- `/skill ncloud-maps 아현역 서초역` (addresses - requires geocoding skill first)
# Ncloud Maps
Query Naver Cloud Maps APIs for intelligent routing (Directions5 + Directions15).
## Key Feature: Smart Routing
**v1.0.8+** — By default, the skill uses **Directions5** for queries with fewer than 5 waypoints, and automatically switches to **Directions15** when you have 5 or more waypoints. No manual selection needed.
| Waypoints | API Used | Max Waypoints |
|-----------|----------|---------------|
| 0–4 | Directions5 | 5 |
| 5+ | Directions15 | 15 |
## Setup
1. **Get API credentials from Naver Cloud Console:**
- Create/register an Application in Naver Cloud Console
- Obtain `Client ID` (API Key ID) and `Client Secret` (API Key)
- Enable "Maps Directions15" API
2. **Set environment variables (or use .env file):**
```bash
export NCLOUD_API_KEY_ID="your-api-key-id"
export NCLOUD_API_KEY="your-api-key-secret"
```
Or create a `.env` file:
```
NCLOUD_API_KEY_ID=your-api-key-id
NCLOUD_API_KEY=your-api-key-secret
```
3. **Install dependencies:**
```bash
cd ~/.openclaw/workspace/skills/ncloud-maps
npm install
```
## Usage
### Using with Address-to-Coordinate Skills
ncloud-maps requires coordinates in `longitude,latitude` format. If you have address-based location data, use one of these compatible skills to convert addresses to coordinates:
**Available Options (choose based on your environment):**
| Skill | Provider | Coordinates | Setup Required |
|-------|----------|-------------|-----------------|
| `goplaces` | Google Places API | Yes (lon,lat) | `GOOGLE_PLACES_API_KEY` |
| `naver-local-search` | Naver Local Search | Yes (lon,lat) | `NAVER_CLIENT_ID`, `NAVER_CLIENT_SECRET` |
| Custom API | Your choice | Yes (lon,lat) | Your setup |
**Example workflow with goplaces:**
```bash
# Get coordinates from address
COORDS=$(goplaces resolve "강남역, 서울" --json | jq -r '.places[0] | "\(.location.longitude),\(.location.latitude)"')
# Use coordinates with ncloud-maps
npx ts-node scripts/index.ts --start "$COORDS" --goal "127.0049,37.4947"
```
**Example workflow with naver-local-search:**
```bash
# Get coordinates from address
COORDS=$(naver-local-search search "강남역" --format json | jq -r '.[0] | "\(.x),\(.y)"')
# Use coordinates with ncloud-maps
npx ts-node scripts/index.ts --start "$COORDS" --goal "127.0049,37.4947"
```
**Or integrate any other geocoding service** that returns `longitude,latitude` coordinates.
### Smart Routing (Default Behavior)
By default, no `--api` flag needed. The skill automatically:
- Uses **Directions5** for 0–4 waypoints (faster)
- Switches to **Directions15** for 5+ waypoints (necessary)
Provide coordinates in `longitude,latitude` format:
```bash
# 0–4 waypoints → Directions5 (automatic)
npx ts-node scripts/index.ts \
--start "127.0683,37.4979" \
--goal "126.9034,37.5087" \
--waypoints "127.0100,37.5000|127.0200,37.5100"
# 5+ waypoints → Directions15 (automatic)
npx ts-node scripts/index.ts \
--start "127.0683,37.4979" \
--goal "126.9034,37.5087" \
--waypoints "127.0100,37.5000|127.0200,37.5100|127.0300,37.5200|127.0400,37.5300|127.0500,37.5400"
```
### Basic route query by coordinates (direct)
```bash
npx ts-node scripts/index.ts \
--start "127.0683,37.4979" \
--goal "126.9034,37.5087"
```
### Force specific API (optional)
If you need to override the smart routing:
```bash
# Force Directions5 (max 5 waypoints)
npx ts-node scripts/index.ts \
--start "127.0683,37.4979" \
--goal "126.9034,37.5087" \
--api directions5 \
--waypoints "127.0100,37.5000|127.0200,37.5100"
# Force Directions15 (max 15 waypoints)
npx ts-node scripts/index.ts \
--start "127.0683,37.4979" \
--goal "126.9034,37.5087" \
--api directions15 \
--waypoints "127.0100,37.5000|127.0200,37.5100|127.0300,37.5200|127.0400,37.5300|127.0500,37.5400"
```
### With waypoints (coordinates only)
```bash
npx ts-node scripts/index.ts \
--start "127.0683,37.4979" \
--goal "126.9034,37.5087" \
--waypoints "127.0100,37.5000"
```
Multiple waypoints:
```bash
npx ts-node scripts/index.ts \
--start "127.0683,37.4979" \
--goal "126.9034,37.5087" \
--waypoints "127.0100,37.5000|127.0200,37.5100"
```
### Route options
Choose from: `trafast` (fast), `tracomfort` (comfort), `traoptimal` (default), `traavoidtoll` (toll-free), `traavoidcaronly` (avoid car-only roads)
```bash
npx ts-node scripts/index.ts \
--start "127.0683,37.4979" \
--goal "126.9034,37.5087" \
--option "traavoidtoll"
```
### Vehicle and fuel settings
```bash
npx ts-node scripts/index.ts \
--start "127.0683,37.4979" \
--goal "126.9034,37.5087" \
--cartype 2 \
--fueltype "diesel" \
--mileage 10.5
```
Vehicle types:
- `1` (default): Small sedan
- `2`: Medium van/cargo
- `3`: Large vehicle
- `4`: 3-axle cargo truck
- `5`: 4+ axle special cargo
- `6`: Compact car
Fuel types: `gasoline` (default), `highgradegasoline`, `diesel`, `lpg`
## Output
```json
{
"success": true,
"start": "127.0683,37.4979",
"goal": "126.9034,37.5087",
"distance": 12850,
"duration": 1145000,
"toll_fare": 0,
"taxi_fare": 18600,
"fuel_price": 1550,
"departure_time": "2026-02-21T14:10:00"
}
```
### Response Fields
- `success` - Whether the query succeeded
- `start` - Starting point coordinates
- `goal` - Destination coordinates
- `distance` - Total distance in meters
- `duration` - Total duration in milliseconds (÷1000 = seconds)
- `toll_fare` - Toll/highway fare in KRW
- `taxi_fare` - Estimated taxi fare in KRW
- `fuel_price` - Estimated fuel cost in KRW
- `departure_time` - Query timestamp
- `error` - Error message (if success=false)
## How It Works
1. **Address Resolution (Optional - any geocoding skill)**
- Use any available skill that provides coordinates (goplaces, naver-local-search, etc.)
- Extract `longitude,latitude` format from the result
- Pass coordinates to ncloud-maps
2. **Coordinate Validation**
- Input: Coordinates in `longitude,latitude` format (direct input or from geocoding skill)
- Validates format and range
- Returns error if format is invalid
3. **Route Calculation (Directions15 or Directions5)**
- Coordinates sent to appropriate Directions API
- Returns distance, duration, tolls, taxi fare, fuel cost
- **Only for vehicle (car) routes** — not for pedestrian or public transit
4. **Waypoints Support**
- Each waypoint must be in `longitude,latitude` format
- All coordinates sent to Directions API
## Limitations
⚠️ **This skill only calculates vehicle (car) routes.** It does not support:
- Public transportation (subway, bus, etc.)
- Walking routes
- Multi-modal journeys
- Transit-specific features (fare, stops, schedules)
For those use cases, use transit-specific APIs (e.g., Kakao Map, Naver Map Transit API).
## Environment Variables
**Required:**
- `NCLOUD_API_KEY_ID` - Naver Cloud API Key ID
- `NCLOUD_API_KEY` - Naver Cloud API Key Secret
## API Limits
**Smart Routing:**
- 0–4 waypoints: Directions5 API (max 5 waypoints)
- 5+ waypoints: Directions15 API (max 15 waypoints)
**General:**
- Real-time traffic information included
- Request rate limits apply per your Naver Cloud plan
## Error Handling
Common errors:
- `좌표 형식 오류` - Invalid coordinate format (use `longitude,latitude`)
- `Authentication Failed` - Invalid API credentials
- `Quota Exceeded` - API rate limit hit
- `No routes found` - No valid route between points
Check Naver Cloud Console for:
- API enablement for your application
- Quota/rate limit status
- Valid coordinates
## References
See [api-spec.md](references/api-spec.md) for detailed API specifications.Related Skills
google-maps
Google Maps tools via OneKey Gateway (geocode, places, distance matrix, elevation, directions).
baidu-maps-sse
Auto-generated skill for baidu-maps-sse tools via OneKey Gateway.
amap-maps-streamableHTTP
Auto-generated skill for amap-maps-streamableHTTP tools via OneKey Gateway.
maps
Distance, routing, and geocoding using free APIs (OSRM + Nominatim/OSM). Use when the user asks about distance between places, travel time, directions, how far something is, or needs to convert a place name to coordinates. No API key required. Requires python3 (3.6+).
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.