oura-setup
The oura-setup Claude Code skill automates OAuth2 integration between a user's Oura Ring and the Oura Cloud API V2 to access health metrics including sleep, heart rate, readiness, and activity data. Use this skill when a user wants to connect their Oura Ring (Gen 3 or later) with an active membership to enable health data retrieval through an assistant application.
git clone --depth 1 https://github.com/vellum-ai/vellum-assistant /tmp/oura-setup && cp -r /tmp/oura-setup/skills/oura-setup ~/.claude/skills/oura-setupSKILL.md
# Oura Ring Integration
Connect the user's Oura Ring to pull sleep, heart rate, readiness, activity, and other health data via the Oura Cloud API V2.
## Prerequisites
- An Oura Ring (Gen 3 or Ring 4) with an active Oura Membership ($6/mo required for API access)
- The Oura app installed and paired with the ring
- An Oura Cloud account at https://cloud.ouraring.com
## Setup
### 1. Register a Developer Application
Have the user go to https://developer.ouraring.com/applications and create a new application:
- **Display Name:** The user's preferred name for the integration
- **Description:** Brief description of the integration
- **Contact Email:** User's email
- **Website:** Any valid URL (e.g. a personal website)
- **Privacy Policy / Terms of Service:** Any valid URLs (required fields, not enforced for personal apps)
- **Redirect URIs:** `http://localhost:3000/callback`
- **Scopes:** Enable all scopes needed. Recommended: `personal`, `daily`, `heartrate`, `sleep`, `workout`, `spo2`, `stress`, `heart_health`, `session`, `ring_configuration`
Save the **Client ID** and **Client Secret**.
### 2. Run the OAuth Flow
Store the client secret securely using `assistant credentials prompt`, then write and run the OAuth helper script on the user's machine:
```python
#!/usr/bin/env python3
"""Oura Ring OAuth2 helper — catches auth code and exchanges for tokens instantly."""
from http.server import HTTPServer, BaseHTTPRequestHandler
from urllib.parse import urlparse, parse_qs, urlencode
import urllib.request, json, webbrowser, ssl
CLIENT_ID = 'YOUR_CLIENT_ID'
CLIENT_SECRET = 'YOUR_CLIENT_SECRET'
REDIRECT_URI = 'http://localhost:3000/callback'
SCOPES = 'email personal daily heartrate workout tag session spo2 ring_configuration stress heart_health'
class Handler(BaseHTTPRequestHandler):
def do_GET(self):
parsed = urlparse(self.path)
if parsed.path == '/':
params = urlencode({
'response_type': 'code', 'client_id': CLIENT_ID,
'redirect_uri': REDIRECT_URI, 'scope': SCOPES, 'state': 'assistant'
})
self.send_response(302)
self.send_header('Location', f'https://cloud.ouraring.com/oauth/authorize?{params}')
self.end_headers()
elif parsed.path == '/callback':
code = parse_qs(parsed.query).get('code', [''])[0]
if code:
token_data = urlencode({
'grant_type': 'authorization_code', 'code': code,
'redirect_uri': REDIRECT_URI, 'client_id': CLIENT_ID,
'client_secret': CLIENT_SECRET,
}).encode()
try:
req = urllib.request.Request('https://api.ouraring.com/oauth/token',
data=token_data,
headers={'Content-Type': 'application/x-www-form-urlencoded'},
method='POST')
resp = urllib.request.urlopen(req, context=ssl.create_default_context())
result = json.loads(resp.read())
with open('/tmp/oura_tokens.json', 'w') as f:
json.dump(result, f, indent=2)
self.send_response(200)
self.send_header('Content-Type', 'text/html')
self.end_headers()
self.wfile.write(b'<html><body><h1>Connected! You can close this tab.</h1></body></html>')
print(f'\nTokens saved to /tmp/oura_tokens.json')
except Exception as e:
self.send_response(500)
self.end_headers()
self.wfile.write(f'Token exchange failed: {e}'.encode())
def log_message(self, *a): pass
print('Opening browser for Oura authorization...')
webbrowser.open('http://localhost:3000')
HTTPServer(('localhost', 3000), Handler).serve_forever()
```
Run with `python3 /path/to/script.py` on the user's machine (`host_bash`). The user authorizes in their browser, the script catches the code and exchanges it for tokens in under a second.
**Important:** Auth codes expire in ~30 seconds. Do NOT have the user paste codes manually — use this script to catch and exchange them automatically.
### 3. Store Tokens
After the OAuth flow, read tokens from `/tmp/oura_tokens.json` and store them:
- `access_token` — store in credential vault with injection template for `api.ouraring.com` Authorization header (Bearer prefix) and `allowed_tools: ["bash"]`
- `refresh_token` — store in credential vault for token refresh
- Tokens expire in ~30 days. Set a reminder to refresh before expiry.
### 4. Verify Connection
Test with the personal info endpoint:
```bash
curl -s -H "Authorization: Bearer $TOKEN" "https://api.ouraring.com/v2/usercollection/personal_info"
```
## Available Endpoints
All endpoints use `GET https://api.ouraring.com/v2/usercollection/{type}` with query params `start_date` and `end_date` (YYYY-MM-DD format).
| Endpoint | Data | Notes |
| ------------------------------------ | ----------------------------------------------------------------- | ------------------------------------------- |
| `/v2/usercollection/daily_sleep` | Sleep score, duration, efficiency, stages | Best checked after user's typical wake time |
| `/v2/usercollection/sleep` | Detailed sleep periods with HR, HRV, movement | Raw sleep period data |
| `/v2/usercollection/daily_readiness` | Readiness score, HRV balance, recovery | Good morning check-in metric |
| `/v2/usercollection/daily_activity` | Steps, calories, movement, inactivity | Activity summary |
| `/v2/usercollection/heartrate` | Continuous HR (use `start_datSet up, authenticate, and run external coding agents (Claude Code, Codex) via the Agent Client Protocol
Shop on Amazon and Amazon Fresh through your browser
Record and analyze API surfaces of web services
Build and edit small, personal visual tools and artifacts — dashboards, trackers, calculators, data visualizations, charts, simple landing pages, and slide decks the user wants for THEMSELVES. This is the right skill whenever the user asks to "visualize this," "make a chart," or "build an artifact" for their own use, or to edit an app they already built here. Do NOT reach for a ui_show dynamic_page to fake an artifact — build a real persistent app here. A one-off diagram, chart, or explainer that just accompanies an answer belongs to the visualize skill (ui_show visual), not an app. NOT for complex, multi-user, or shippable products — those go to a real project folder with a coding agent (see Scope below).
Drive a specific named macOS app via raw input bypassing the Accessibility tree
Migrate from ChatGPT, Claude, OpenClaw, Hermes, Manus, and other AI assistants into Vellum by inspecting their data exports, conversation archives, files, prompts, custom instructions, memory, saved memories, tools, GPTs, workflows, integrations, and relationships, then mapping as much as safely possible into Vellum primitives. Handles single-source and multi-source migrations with a unified, deduplicated inventory.
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready text for search, Q&A, and summarization without building a custom parsing pipeline.
Import conversation history from ChatGPT into Vellum