From synthflow-voice-ai
Guide users through obtaining and configuring a Synthflow API key. Use when the user needs to set up Synthflow, when API calls fail due to missing keys, or when the user mentions needing access to Synthflow's voice AI platform.
How this skill is triggered — by the user, by Claude, or both
Slash command
/synthflow-voice-ai:setup-api-keyThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Guide the user through obtaining and configuring a Synthflow API key for the voice AI platform.
Guide the user through obtaining and configuring a Synthflow API key for the voice AI platform.
Tell the user:
To set up Synthflow, open your dashboard at: https://app.synthflow.ai
(Need an account? Create one at https://app.synthflow.ai/signup first)
Navigate to Settings → API Keys and:
- Click "Create API Key"
- Name your key (e.g., "development")
- Copy the key immediately — it is only shown once
Paste your API key here when ready.
Then wait for the user's next message which should contain the API key.
Once the user provides the API key:
Validate the key by making a request:
curl -s -o /dev/null -w "%{http_code}" https://api.synthflow.ai/v2/assistants/ \
-H "Authorization: Bearer <the-api-key>"
If validation fails (non-200 response):
If validation succeeds (200 response), save the API key:
Check if a .env file exists. If so, append to it. If not, create one:
SYNTHFLOW_API_KEY=<the-api-key>
Confirm success:
Your Synthflow API key is configured and stored in
.envasSYNTHFLOW_API_KEY.You can now use Synthflow's API to create assistants, make calls, and build voice AI agents.
Keep this key safe — do not commit it to version control.
Check if .gitignore exists and contains .env. If not, add it:
.env
All Synthflow skills expect the API key in the SYNTHFLOW_API_KEY environment variable. The base URL for all API requests is:
https://api.synthflow.ai/v2
Authentication is via Bearer token:
Authorization: Bearer $SYNTHFLOW_API_KEY
You can also authenticate using the Synthflow CLI:
pip install synthflow
synthflow auth login
The CLI stores the key securely in your system keychain. Run synthflow auth status to verify.
After the API key is successfully validated and saved, send an anonymous usage event. Skip this step if DO_NOT_TRACK or DISABLE_TELEMETRY is set:
[ -z "$DO_NOT_TRACK" ] && [ -z "$DISABLE_TELEMETRY" ] && \
curl -s -o /dev/null https://eu.i.posthog.com/i/v0/e/ \
-H "Content-Type: application/json" \
-d '{
"api_key": "phc_dlyyp4oL77penk6jXtJRUUpotT7eiUk3wRSY1KzzpLi",
"distinct_id": "'$(echo $USER | shasum -a 256 | cut -d" " -f1)'",
"event": "skill_used",
"properties": {"skill": "setup-api-key", "success": true}
}'
This skills repository includes a Synthflow documentation MCP server (synthflow-docs) that gives your AI agent access to the full Synthflow knowledge base. Use the searchDocs tool to look up anything beyond what this skill covers — advanced configuration, troubleshooting, SDK details, and more.
Auto-configured: If you cloned or installed these skills, the MCP server is already configured via .mcp.json (Claude Code), .cursor/mcp.json (Cursor), or .vscode/mcp.json (VS Code Copilot).
Manual setup: If your agent doesn't auto-detect the config, run:
claude mcp add synthflow-docs -- npx -y mcp-remote https://docs.synthflow.ai/_mcp/server
See the README for full setup instructions across all supported agents.
npx claudepluginhub synthflowai/synthflow-skills --plugin synthflow-voice-aiCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.