Tiangong Music AI Composer
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md to install @user_e493aefd/xing-he-tiangong-music.
About this skill
Problem
Music generation skills often break on operational details: asking users to log in before understanding the request, inventing failure explanations, ending with status logs instead of a playable result page, or leaving audio links that cannot be played in sandboxed frontends. This skill turns the flow into a constrained execution chain: confirm creative requirements, check login state, submit, poll, render results, and keep user-facing errors to fixed, plain-language templates.
How it works
The core rule is to use only the documented HTTP REST endpoints under the fixed base URL https://ai.growingth.com/api. The typical path includes parsing lyrics, style, and intent; reading MIAOYIN_API_TOKEN from config.json in the skill directory; if not logged in, guiding the user first and creating a QR-code session only after an explicit login intent; after submission, polling every 10s and reporting both status and elapsed progress; and after completion, generating an HTML result page opened in an embedded browser. If the sandbox server hosts the page, its Content-Security-Policy response header must allow https://file.growingth.com for media-src, img-src, and connect-src, while clickable rewritten audio links are still provided in the chat.
Boundaries: avoid MCP, WebSocket, web fetching, endpoint guessing, token-format validation, fabricated responses, extra advice, or manual workarounds. Errors such as insufficient balance, copyright protection, and expired login should use fixed templates instead of exposing internal technical terms to the user.
Use Cases
- Confirm lyrics and style from one prompt, submit generation, and poll progress until the song finishes.
- When not logged in, show the confirmed creative plan first, then start QR login only after the user asks.
- After completion, open the HTML result page and provide rewritten clickable audio links for playback.
- On balance, copyright, or login errors, reply with fixed user-facing copy and the required action link.
Best For
- Engineers integrating song generation into chat agents and needing controlled login and polling.
- Indie developers building AI music result pages with audio links and fixed error copy.
- Testers covering balance, copyright, and expired-login edges in music API workflows.
- Agent app builders who need a guided flow for song creation, login, and playback.
Related Skills
Generate an interactive HTML product detail page from images and copy, with multi-product carousel, inline text editing, design controls, and PDF/JPG/PSD export support.
Enter a material name to get preview and download links for free, commercially usable video assets, with paid platform options, pricing, and search suggestions when results are limited.
A local CLI for Dreamina image and video generation, including credit checks, async submission, result queries, and task history review.
Generate and validate JianYing drafts from storyboard JSON with narrated commentary, original-sound preservation, timing checks, and draft inspection.