Freebeat Ai

Cloud-based freebeat-ai tool that handles automatically syncing video cuts to music beats. Upload MP4, MOV, AVI, WebM files (up to 500MB), describe what you...

Security Scan

The skill's required data, runtime instructions, and network calls are coherent with a cloud video-syncing service; nothing requests unrelated credentials or installs arbitrary code.

Purpose & Capability

The name/description (syncing video cuts to music beats on a cloud backend) matches the actions described in SKILL.md: creating sessions, uploading video, SSE messaging, rendering and returning download URLs. The single declared credential (NEMO_TOKEN) is appropriate for a cloud API client.

Instruction Scope

Runtime instructions only call the listed nemo API endpoints, handle SSE, upload user-provided files, and manage session tokens. The agent is instructed to obtain an anonymous token if no NEMO_TOKEN exists — this is consistent with a public anonymous usage flow. The skill asks to read its own YAML frontmatter and detect install path for attribution headers; this is narrow and related to attribution, not broad system access.

Install Mechanism

There is no install spec and no code files; the skill is instruction-only so nothing is downloaded or written to disk by an installer.

Credentials

Only NEMO_TOKEN is required (primary credential). Metadata also lists a config path (~/.config/nemovideo/) which is plausible (local client config), but SKILL.md does not explicitly use that path — minor mismatch worth noting but not inherently suspicious.

Persistence & Privilege

always is false and autonomous invocation is default; the skill does not request persistent or system-wide privileges. It does maintain session_id for the lifetime of a job, which is expected for a cloud render workflow.

Assessment

This skill appears to be a normal cloud video-processing client. Before installing: confirm you trust the Nemo service domain (mega-api-prod.nemovideo.ai) and where NEMO_TOKEN will come from; anonymous tokens are obtained from that API and last ~7 days. Only upload files you intend to send — the skill will POST uploads to the remote service. Because the registry entry has no homepage and an unknown source, be cautious: if you need stronger assurance, ask the publisher for documentation or a homepage, or test with non-sensitive sample videos first.

Getting Started

Ready when you are. Drop your video clips here or describe what you want to make.

Try saying:

• "sync a 60-second dance or workout clip into a 1080p MP4"
• "sync my video cuts to the beat of this track automatically"
• "automatically syncing video cuts to music beats for TikTok creators"

Quick Start Setup

This skill connects to a cloud processing backend. On first use, set up the connection automatically and let the user know ("Connecting...").

Token check: Look for NEMO_TOKEN in the environment. If found, skip to session creation. Otherwise:

• Generate a UUID as client identifier
• POST https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with X-Client-Id header
• Extract data.token from the response — this is your NEMO_TOKEN (100 free credits, 7-day expiry)

Session: POST https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Keep the returned session_id for all operations.

Let the user know with a brief "Ready!" when setup is complete. Don't expose tokens or raw API output.

Freebeat AI — Sync Videos to Music Beats

Drop your video clips in the chat and tell me what you need. I'll handle the AI beat-sync editing on cloud GPUs — you don't need anything installed locally.

Here's a typical use: you send a a 60-second dance or workout clip, ask for sync my video cuts to the beat of this track automatically, and about 30-60 seconds later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — shorter clips with clear beat drops produce the tightest sync results.

Matching Input to Actions

User prompts referencing freebeat 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.

Skill attribution — read from this file's YAML frontmatter at runtime:

• X-Skill-Source: freebeat-ai
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

Every API call needs Authorization: Bearer <NEMO_TOKEN> plus the three attribution headers above. If any header is missing, exports return 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.

Reading the SSE Stream

Text events go straight to the user (after GUI translation). Tool calls stay internal. Heartbeats and empty data: lines mean the backend is still working — show "⏳ Still working..." every 2 minutes.

About 30% of edit operations close the stream without any text. When that happens, poll /api/state to confirm the timeline changed, then tell the user what was updated.

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 field mapping: t=tracks, tt=track type (0=video, 1=audio, 7=text), sg=segments, d=duration(ms), m=metadata.

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

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "sync my video cuts to the beat of this track automatically" — concrete instructions get better results.

Max file size is 500MB. Stick to MP4, MOV, AVI, WebM for the smoothest experience.

Export as MP4 for widest compatibility across social platforms.

Common Workflows

Quick edit: Upload → "sync my video cuts to the beat of this track automatically" → Download MP4. Takes 30-60 seconds 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.