Mureka Ai

Get AI composed songs ready to post, without touching a single slider. Upload your audio files (MP3, WAV, MP4, AAC, up to 200MB), say something like "generat...

Security Scan

The skill's instructions largely match a cloud music-generation service, but there's an unexplained mismatch (a requested config path appears in the skill frontmatter but not in the registry) and a few implementation details you should confirm before installing.

Purpose & Capability

Name/description and the runtime instructions consistently describe a cloud-based AI music/video render service that uploads audio and returns MP4/other assets; requesting a NEMO_TOKEN (the service token) is coherent. However, the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) that would grant the skill access to a user config directory — the registry metadata showed no required config paths. This mismatch is unexplained and disproportionate to the stated purpose.

Instruction Scope

The SKILL.md instructs the agent to (a) use NEMO_TOKEN if present or obtain an anonymous token by POSTing to the provider, (b) create sessions, (c) upload user-supplied audio files via multipart or URL, and (d) use SSE polling. Those steps directly map to the stated functionality. The only scope concerns: references to auto-detecting an install path for X-Skill-Platform and the frontmatter config path permission — both imply access to local paths/config that are not justified elsewhere in the document.

Install Mechanism

No install spec and no code files — instruction-only skill — so nothing is written to disk by an installer. This is the lowest install risk.

Credentials

The skill asks for a single service credential (NEMO_TOKEN) which is appropriate for a cloud API. But the presence of a declared config path in the frontmatter implies the skill may read local configuration (~/.config/nemovideo/) in addition to the env var. The registry did not list that configPath as required, so the requested local path access is unexplained and could expose unrelated local config files.

Persistence & Privilege

always is false and the skill doesn't request elevated or permanent platform privileges. It does instruct saving session_id and using tokens for API calls (normal for session-based APIs). There is no instruction to modify other skills or global agent settings.

What to consider before installing

This skill appears to be a wrapper for a cloud music/video rendering API and generally asks for the expected token (NEMO_TOKEN) and file uploads. Before installing, confirm two things: (1) why the SKILL.md frontmatter references a local config path (~/.config/nemovideo/) — ask the author whether the skill will read files from your home directory and whether that is necessary, and (2) verify the API domain (mega-api-prod.nemovideo.ai) and the expected behavior for anonymous tokens (they expire and grant limited credits). Avoid installing if you cannot confirm the config-path usage, and do not supply sensitive files or credentials unrelated to the service. If you proceed, prefer using a short-lived/anonymous token rather than a long-lived secret in NEMO_TOKEN, and monitor what files the agent sends (only upload the audio you intend to process).

Getting Started

Share your audio files and I'll get started on AI music generation. Or just tell me what you're thinking.

Try saying:

• "generate my audio files"
• "export 1080p MP4"
• "generate a full song with instruments"

Automatic Setup

On first interaction, connect to the processing API before doing anything else. Show a brief status like "Setting things up...".

Token: If NEMO_TOKEN environment variable is already set, use it and skip to Session below.

Free token: Generate a UUID as client identifier, then POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id: <uuid>. The response field data.token becomes your NEMO_TOKEN (100 credits, 7-day expiry).

Session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Save session_id from the response.

Confirm to the user you're connected and ready. Don't print tokens or raw JSON.

Mureka AI — Generate Songs from Audio

Drop your audio files in the chat and tell me what you need. I'll handle the AI music generation on cloud GPUs — you don't need anything installed locally.

Here's a typical use: you send a a 30-second vocal melody recording, ask for generate a full song with instruments from my hummed melody, and about 1-2 minutes later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — shorter seed clips produce more focused and consistent results.

Matching Input to Actions

User prompts referencing mureka ai, aspect ratio, text overlays, or audio tracks get routed to the corresponding action via keyword and intent classification.

User says...	Action	Skip SSE?
"export" / "导出" / "download" / "send me the video"	→ §3.5 Export	✅
"credits" / "积分" / "balance" / "余额"	→ §3.3 Credits	✅
"status" / "状态" / "show tracks"	→ §3.4 State	✅
"upload" / "上传" / user sends file	→ §3.2 Upload	✅
Everything else (generate, edit, add BGM…)	→ §3.1 SSE	❌

Cloud Render Pipeline Details

Each export job queues on a cloud GPU node that composites video layers, applies platform-spec compression (H.264, up to 1080x1920), and returns a download URL within 30-90 seconds. The session token carries render job IDs, so closing the tab before completion orphans the job.

Three attribution headers are required on every request and must match this file's frontmatter:

Header	Value
X-Skill-Source	mureka-ai
X-Skill-Version	frontmatter version
X-Skill-Platform	auto-detect: clawhub / cursor / unknown from install path

All requests must include: Authorization: Bearer <NEMO_TOKEN>, X-Skill-Source, X-Skill-Version, X-Skill-Platform. Missing attribution headers will cause export to fail with 402.

API base: https://mega-api-prod.nemovideo.ai

Create session: POST /api/tasks/me/with-session/nemo_agent — body {"task_name":"project","language":"<lang>"} — returns task_id, session_id.

Send message (SSE): POST /run_sse — body {"app_name":"nemo_agent","user_id":"me","session_id":"<sid>","new_message":{"parts":[{"text":"<msg>"}]}} with Accept: text/event-stream. Max timeout: 15 minutes.

Upload: POST /api/upload-video/nemo_agent/me/<sid> — file: multipart -F "files=@/path", or URL: {"urls":["<url>"],"source_type":"url"}

Credits: GET /api/credits/balance/simple — returns available, frozen, total

Session state: GET /api/state/nemo_agent/me/<sid>/latest — key fields: data.state.draft, data.state.video_infos, data.state.generated_media

Export (free, no credits): POST /api/render/proxy/lambda — body {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll GET /api/render/proxy/lambda/<id> every 30s until status = completed. Download URL at output.url.

Supported formats: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.

SSE Event Handling

Event	Action
Text response	Apply GUI translation (§4), present to user
Tool call/result	Process internally, don't forward
heartbeat / empty data:	Keep waiting. Every 2 min: "⏳ Still working..."
Stream closes	Process final response

~30% of editing operations return no text in the SSE stream. When this happens: poll session state to verify the edit was applied, then summarize changes to the user.

Translating GUI Instructions

The backend responds as if there's a visual interface. Map its instructions to API calls:

• "click" or "点击" → execute the action via the relevant endpoint
• "open" or "打开" → query session state to get the data
• "drag/drop" or "拖拽" → send the edit command through SSE
• "preview in timeline" → show a text summary of current tracks
• "Export" or "导出" → run the export workflow

Draft JSON uses short keys: t for tracks, tt for track type (0=video, 1=audio, 7=text), sg for segments, d for duration in ms, m for metadata.

Example timeline summary:

Timeline (3 tracks): 1. Video: city timelapse (0-10s) 2. BGM: Lo-fi (0-10s, 35%) 3. Title: "Urban Dreams" (0-3s)

Error Codes

• 0 — success, continue normally
• 1001 — token expired or invalid; re-acquire via /api/auth/anonymous-token
• 1002 — session not found; create a new one
• 2001 — out of credits; anonymous users get a registration link with ?bind=<id>, registered users top up
• 4001 — unsupported file type; show accepted formats
• 4002 — file too large; suggest compressing or trimming
• 400 — missing X-Client-Id; generate one and retry
• 402 — free plan export blocked; not a credit issue, subscription tier
• 429 — rate limited; wait 30s and retry once

Common Workflows

Quick edit: Upload → "generate a full song with instruments from my hummed melody" → Download MP4. Takes 1-2 minutes for a 30-second clip.

Batch style: Upload multiple files in one session. Process them one by one with different instructions. Each gets its own render.

Iterative: Start with a rough cut, preview the result, then refine. The session keeps your timeline state so you can keep tweaking.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "generate a full song with instruments from my hummed melody" — concrete instructions get better results.

Max file size is 200MB. Stick to MP3, WAV, MP4, AAC for the smoothest experience.

Export as MP4 to pair your generated track with a visual for social media.