Test AI provider endpoints and generate a Markdown report.
npx skills add https://github.com/tegnike/aituber-kit --skill verify-endpoints
Please help me install this Agent Skill. Skill: verify-endpoints Source: https://github.com/tegnike/aituber-kit/tree/main/.claude/skills/verify-endpoints Command: npx skills add https://github.com/tegnike/aituber-kit --skill verify-endpoints
This Skill automates testing all AI provider endpoints (chat, TTS, STT, Embedding) and generates a consolidated report to identify configuration gaps and integration issues.
Run the endpoint verification tests against your local development server and generate the report.
Example commands:
curl -s -w "\n%{http_code}" -X POST http://localhost:3000/api/ai/vercel/
-H "Content-Type: application/json"
-d '{"messages":[{"role":"user","content":"Hello, verify endpoints"}],"aiService":"openai","model":"gpt-4.1-mini","stream":false,"temperature":0.5,"maxTokens":50}'
--max-time 30
curl -s -N -X POST http://localhost:3000/api/ai/vercel/
-H "Content-Type: application/json"
-d '{"messages":[{"role":"user","content":"Hello, verify endpoints"}],"aiService":"openai","model":"gpt-4.1-mini","stream":true,"temperature":0.5,"maxTokens":50}'
--max-time 30
High-intent search queries and answers about installing and using this skill.
Automate AI endpoint testing by running curl commands against your local server to validate non-streaming and streaming paths across providers, generating a consolidated markdown report.
Yes, you can test both streaming and non-streaming paths for AI services by sending curl POST requests to your localhost server with the stream parameter set to true or false in the JSON payload.
You need a local development server running at http://localhost:3000 and the required API keys configured as environment variables for the AI providers you want to test.
Endpoint testing results are saved as a markdown report under the reports/endpoints/ directory, named with a timestamp like verify-YYYY-MM-DD-HHmmss.md, consolidating all provider checks.
The timeout limit when testing AI provider endpoints with curl is 30 seconds, applied via the --max-time flag to prevent hanging requests from blocking the automated testing process.
0xRayAICoordinate agent workflows via the local xray HTTP API for code analysis and system commands.
Snowflake-LabsA concise summary of your roleplay character: name,</name> personality, and/or behavior, formatted as a single string sentence. Typically不超过50字，此处省略
gevreyRoute Discord voice speech through STT, Claude processing, and TTS playback.
nacos-groupSync Swagger/OpenAPI api.json with Nacos markdown docs via per-endpoint updates.
