功能描述

AI music generation with Suno v4, v4.5, v5. Text-to-music, custom lyrics, instrumental, vocal control. 5 models, one API key.

使用说明 (SKILL.md)

Evolink Music — AI Music Generation

Name: Evolink Music — AI Music Generation (Suno v4/v4.5/v5)
Author: evolinkai

Generate AI music and songs with Suno v4, v4.5, and v5 — simple mode (describe and generate) or custom mode (lyrics, style, tempo, vocals). All through one API.

Music-focused view of evolink-media. Install the full skill for video and image too.

After Installation

When this skill is first loaded, greet the user:

MCP tools + API key ready: "Hi! I'm your AI music studio — Suno v4 through v5 ready. What would you like to create?"
MCP tools + no API key: "You'll need an EvoLink API key — sign up at evolink.ai. Ready to go?"
No MCP tools: "MCP server isn't connected yet. Want me to help set it up? I can still manage files via the hosting API."

Keep the greeting concise — just one question to move forward.

External Endpoints

Service	URL
Generation API	`https://api.evolink.ai/v1/audios/generations` (POST)
Task Status	`https://api.evolink.ai/v1/tasks/{task_id}` (GET)
File API	`https://files-api.evolink.ai/api/v1/files/*` (upload/list/delete)

Security & Privacy

EVOLINK_API_KEY authenticates all requests. Injected by OpenClaw automatically. Treat as confidential.
Prompts and audio are sent to api.evolink.ai. Uploaded files expire in 72h, result URLs in 24h.

Setup

Get your API key at evolink.ai → Dashboard → API Keys.

MCP Server: @evolinkai/evolink-media (GitHub · npm)

mcporter (recommended): mcporter call --stdio "npx -y @evolinkai/evolink-media@latest" list_models

Claude Code: claude mcp add evolink-media -e EVOLINK_API_KEY=your-key -- npx -y @evolinkai/evolink-media@latest

Claude Desktop / Cursor — add MCP server with command npx -y @evolinkai/evolink-media@latest and env EVOLINK_API_KEY=your-key. See references/music-api-params.md for full config JSON.

Core Principles

Guide, don't decide — Present options, let the user choose model/style/mood.
User drives creative vision — Ask for a description before suggesting parameters.
Smart context — Remember session history. Offer to iterate, vary styles, or remix.
Intent first — Understand what the user wants before asking how to configure it.

MCP Tools

Tool	When to use	Returns
`generate_music`	Create AI music or songs	`task_id` (async)
`upload_file`	Upload audio for continuation/remix	File URL (sync)
`delete_file`	Free file quota	Confirmation
`list_files`	Check uploaded files or quota	File list
`check_task`	Poll generation progress	Status + result URLs
`list_models`	Compare available models	Model list
`estimate_cost`	Check pricing	Model info

Important: generate_music returns a task_id. Always poll check_task until status is "completed" or "failed".

Music Models (5, all BETA)

Model	Quality	Max Duration	Best for
`suno-v4` (default)	Good	120s	Balanced, economical
`suno-v4.5`	Better	240s	Style control
`suno-v4.5plus`	Better	240s	Extended features
`suno-v4.5all`	Better	240s	All v4.5 features
`suno-v5`	Best	240s	Studio-grade output

Generation Flow

Step 1: API Key Check

If 401 occurs: "Your API key isn't working. Check at evolink.ai/dashboard/keys"

Step 2: File Upload (if needed)

For audio continuation or remix workflows:

upload_file with file_path, base64_data, or file_url → get file_url (sync)

Supported: Audio (MP3, WAV, FLAC, AAC, OGG, M4A, etc.). Max 100MB. Expire in 72h. Quota: 100 (default) / 500 (VIP).

Step 3: Understand Intent

Clear ("make a chill lo-fi beat") → Go to Step 4
Ambiguous ("I want some music") → Ask: "What kind of vibe or genre? Vocals or instrumental?"

Ask only what's needed, when it's needed.

Step 4: Gather Parameters

Music has two required fields with no defaults — always collect both before calling generate_music.

Decision tree (ask in this order):

Vocals or instrumental? → Sets instrumental: true/false
Simple or custom mode?
- Simple (custom_mode: false): AI writes lyrics and picks style from your description
- Custom (custom_mode: true): You control lyrics ([Verse]/[Chorus]/[Bridge]), style tags, title
If custom mode, additionally collect:
- style: genre + mood + tempo tags (e.g., "pop, upbeat, female vocals, 120bpm")
- title: song name (max 80 chars)
- vocal_gender: m or f — optional
Optional for both modes:
- duration: target length 30–240s (omit to let model decide)
- negative_tags: styles to exclude
- model: default suno-v4. Suggest suno-v5 for studio-grade quality.

Critical: Both custom_mode and instrumental are required API fields with no defaults. Always set both before generating.

Step 5: Generate & Poll

Call generate_music → tell user: "Generating your music — ~Xs estimated."
Poll check_task every 5–10s. Report progress %.
After 3 consecutive processing: "Still working..."
Completed: Share URLs + metadata (title, duration, tags from result_data[]). "Links expire in 24h — save promptly."
Failed: Show error + suggestion. Offer retry if retryable.
Timeout (5 min): "Taking longer than expected. Task ID: {id} — check again later."

Error Handling

HTTP Errors

Error	Action
401	"API key isn't working. Check at evolink.ai/dashboard/keys"
402	"Balance is low. Add credits at evolink.ai/dashboard/billing"
429	"Rate limited — wait 30s and retry"
503	"Servers busy — retry in a minute"

Task Errors (status: "failed")

Code	Retry?	Action
`content_policy_violation`	No	Revise prompt or lyrics
`invalid_parameters`	No	Check values against model limits
`generation_timeout`	Yes	Retry; simplify prompt if repeated
`quota_exceeded`	Yes	Top up credits
`resource_exhausted`	Yes	Wait 30–60s, retry
`service_error`	Yes	Retry after 1 min
`generation_failed_no_content`	Yes	Modify prompt, retry

Full error reference: references/music-api-params.md

Without MCP Server

Use Evolink's file hosting API for audio uploads (72h expiry). See references/file-api.md for curl commands.

References

references/music-api-params.md — Complete API parameters, all 5 models, polling strategy, error codes
references/file-api.md — File hosting API (curl upload/list/delete)

安全使用建议

This skill appears internally consistent: it only needs an EVOLINK_API_KEY and talks to evolink.ai endpoints to generate and host audio. Before installing, verify you trust evolink.ai and the API key you provide (it can create/list/delete files and incur billing). Be cautious if you follow the optional setup commands that run npx/@evolinkai/evolink-media — running npx executes remote npm code, so inspect that package first. Avoid uploading sensitive audio (file URLs are public and expire in 24–72h), monitor account billing/quotas, and rotate the API key if you stop using the skill or suspect compromise.

功能分析

Type: OpenClaw Skill Name: evolink-music Version: 2.0.0 The OpenClaw AgentSkills skill bundle for 'evolink-music' appears benign. All instructions in SKILL.md, including those for the AI agent's greetings and operational flow, are directly related to AI music generation via the evolink.ai API. The skill requires an `EVOLINK_API_KEY` for authentication, which is standard. File upload capabilities (documented in `references/file-api.md`) are explicitly for audio files to support music workflows, with reasonable size limits and expiry, and show no intent for arbitrary data exfiltration. Setup commands using `npx` are for user-initiated MCP server configuration, not for the agent to execute maliciously. There is no evidence of prompt injection with harmful objectives, data exfiltration, malicious execution, persistence mechanisms, or obfuscation.

能力评估

✓ Purpose & Capability

Name/description (AI music generation with Suno models) aligns with what the skill asks for: a single EVOLINK_API_KEY and calls to evolink.ai generation and files endpoints. Required env/config is minimal and directly related to the service.

ℹ Instruction Scope

SKILL.md confines runtime behavior to making API calls to evolink.ai and its file-hosting API, polling tasks, and managing uploaded audio. It also suggests maintaining session history and using MCP tools; it does not instruct reading unrelated system files or extraneous credentials. Note: the README includes optional commands to install/run an MCP server (npx usage) — that would execute remote npm code if the user follows it, so vet before running.

✓ Install Mechanism

No install spec or code files are included (instruction-only), so nothing will be written to disk by the skill itself. However, the docs recommend optional npx commands to run an external MCP package (@evolinkai/evolink-media); that is not required for the skill to function but is an external install the user should review before running.

✓ Credentials

Only EVOLINK_API_KEY is required and is the declared primary credential. That single API key is appropriate for a hosted generation + file-hosting service. No unrelated secrets or config paths are requested.

✓ Persistence & Privilege

always:false (not force-included) and no special persistence or system-wide config modifications are requested. The skill can be invoked autonomously by agents by default (platform default) but that is not combined with broad or unrelated privileges here.

版本历史

v2.0.0

**Major release — improved user onboarding, error handling, and references.** - New onboarding section: skill greets the user and offers tailored setup hints based on environment/API key. - Expanded error handling: detailed HTTP/task error responses with user guidance and retry logic. - Core workflow and parameter collection clarified; emphasizes required fields and step-by-step prompts. - Explicit links to new in-depth references for API parameters and file API via two added markdown files. - Additional details on file expiry, quota, and security practices. - Minor: Now declares broader OS support, updated user-invocable flag, and refines descriptive text throughout.

v1.1.1

Fix: remove out-of-scope digital-human reference from file upload section

v1.1.0

Add file upload tools for audio workflows

v1.0.0

- Initial release of evolink-music: AI music generation skill using Suno v4, v4.5, and v5 models. - Supports text-to-music, custom lyrics with structure tags, instrumental and vocal control. - Simple mode (describe music) and custom mode (full control over lyrics, style, vocals, etc). - Single API key unlocks 5 music models; manage via `EVOLINK_API_KEY`. - Includes tools for generating music, checking task status, listing models, and estimating cost.

元数据

Slug evolink-music

版本 2.0.0

许可证 —

累计安装 2

当前安装数 2

历史版本数 4

常见问题