Dance Video

Turn a 2-minute phone recording of a dance routine into 1080p polished dance clips just by typing what you need. Whether it's editing dance footage with beat...

Security Scan

The skill mostly matches a cloud-based video-editing integration, but there are inconsistencies in its metadata and the runtime instructions ask the agent to read/write local paths and manage anonymous tokens — things you should verify before installing or providing files/credentials.

Purpose & Capability

The name/description (cloud AI video editing) align with the API endpoints and the single required credential (NEMO_TOKEN). However the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) and logic to inspect install directories (~/.clawhub/, ~/.cursor/skills/) that are not reflected in the registry 'Requirements' section — an inconsistency worth clarifying.

Instruction Scope

Runtime instructions direct the agent to obtain anonymous tokens, create sessions, upload user video files, poll render jobs, and derive headers by inspecting local install paths. Inspecting filesystem paths to set X-Skill-Platform and writing/storing session state in a local config folder are out-of-band relative to a pure chat-forwarding integration and raise privacy/operational scope questions (where is session stored, what else is read?). The SKILL.md also instructs not to display raw API responses or token values to the user, which is reasonable for safety but also reduces transparency.

Install Mechanism

This is an instruction-only skill with no install spec and no code files, so nothing is written to disk by an installer. That reduces install-time risk.

Credentials

Only one environment variable is declared (NEMO_TOKEN), which matches the described API usage. However the skill describes generating/storing anonymous tokens and references a local config directory in its frontmatter; it's unclear whether session tokens will be persisted on disk and where. The declared registry metadata said no config paths, but SKILL.md implies ~/.config/nemovideo/, so confirm what will actually be stored and accessible.

Persistence & Privilege

The skill is not always-enabled and does not request elevated platform privileges. Still, it instructs the agent to create and retain session IDs and may persist state (frontmatter mentions a config path). Confirm whether session tokens are stored persistently and whether they are scoped/rotated — persistent credentials combined with autonomous invocation could increase blast radius.

What to consider before installing

This skill appears to call an external video-rendering API (mega-api-prod.nemovideo.ai) and can generate anonymous tokens if you don't supply NEMO_TOKEN. Before installing or using it: 1) Verify the API domain and the service's privacy/security posture (is nemovideo.ai a service you trust?). 2) Clarify where session tokens are stored (SKILL.md suggests a config path but registry metadata omits it). If tokens are persisted to ~/.config/nemovideo/, know that anyone with access to that path could use them. 3) The skill may inspect paths like ~/.clawhub/ or ~/.cursor/skills/ to populate headers — if you prefer to avoid exposing filesystem layout, ask the developer to remove that behavior. 4) Prefer using an account/token with limited scope or a disposable account for testing; avoid supplying sensitive credentials or documents. 5) Because this is instruction-only (no code reviewable here), consider testing in an isolated environment (VM/container) and confirm responses and stored files before trusting it with private footage or long-lived credentials.

Getting Started

Share your raw dance footage and I'll get started on AI video editing. Or just tell me what you're thinking.

Try saying:

• "edit my raw dance footage"
• "export 1080p MP4"
• "cut to the beat, add transitions,"

First-Time Connection

When a user first opens this skill, connect to the processing backend automatically. Briefly let them know (e.g. "Setting up...").

Authentication: Check if NEMO_TOKEN is set in the environment. If it is, skip to step 2.

1. Obtain a free token: Generate a random UUID as client identifier. POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id set to that UUID. The response data.token is your NEMO_TOKEN — 100 free credits, valid 7 days.
2. Create a session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Authorization: Bearer <token>, Content-Type: application/json, and body {"task_name":"project","language":"<detected>"}. Store the returned session_id for all subsequent requests.

Keep setup communication brief. Don't display raw API responses or token values to the user.

Dance Video — Edit and Export Dance Clips

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

Here's a typical use: you send a a 2-minute phone recording of a dance routine, ask for cut to the beat, add transitions, and sync the music, 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 clips under 60 seconds process faster and are ideal for Reels or TikTok.

Matching Input to Actions

User prompts referencing dance video, 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.

Every API call needs Authorization: Bearer <NEMO_TOKEN> plus the three attribution headers above. If any header is missing, exports return 402.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is dance-video, X-Skill-Version comes from the version field, and X-Skill-Platform is detected from the install path (~/.clawhub/ = clawhub, ~/.cursor/skills/ = cursor, otherwise unknown).

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.

Error Handling

Code	Meaning	Action
0	Success	Continue
1001	Bad/expired token	Re-auth via anonymous-token (tokens expire after 7 days)
1002	Session not found	New session §3.0
2001	No credits	Anonymous: show registration URL with ?bind=<id> (get <id> from create-session or state response when needed). Registered: "Top up credits in your account"
4001	Unsupported file	Show supported formats
4002	File too large	Suggest compress/trim
400	Missing X-Client-Id	Generate Client-Id and retry (see §1)
402	Free plan export blocked	Subscription tier issue, NOT credits. "Register or upgrade your plan to unlock export."
429	Rate limit (1 token/client/7 days)	Retry in 30s once

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

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.

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)

Common Workflows

Quick edit: Upload → "cut to the beat, add transitions, and sync the music" → 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 "cut to the beat, add transitions, and sync the music" — 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.