Image To Video Dance

Turn a single portrait photo of a person into 1080p dancing video clips just by typing what you need. Whether it's animating photos of people into dancing vi...

Security Scan

The skill's functionality (animating photos via a cloud API) matches its requirements, but the runtime instructions ask the agent to access a local config path and detect install paths (not declared in the registry) and will upload user images and session tokens to a third‑party API — verify the service and privacy before use.

Purpose & Capability

Name/description match the declared primaryEnv (NEMO_TOKEN) and cloud-render workflow. However the SKILL.md frontmatter lists a configPath (~/.config/nemovideo/) that is not present in the registry metadata — an inconsistency between what the file claims it will use and what the skill declares.

Instruction Scope

Instructions direct the agent to obtain/upload user images and to POST/GET many endpoints on mega-api-prod.nemovideo.ai (auth, upload, render, state). They also instruct detecting the install path to set an attribution header and reference storing session_id and using/setting NEMO_TOKEN. Reading/writing '~/.config/nemovideo/' and probing install paths could expose local info; uploading user photos and tokens to an external service is expected for this capability but is a privacy-sensitive action that users should explicitly accept.

Install Mechanism

No install spec and no code files — instruction-only skill. This minimizes disk footprint and installer risk.

Credentials

Only NEMO_TOKEN is declared as required, which is proportionate for a third-party API. But SKILL.md also references a local config directory and asks the agent to derive headers from an install path — those local accesses are not justified by the registry listing and may expose additional local state.

Persistence & Privilege

The skill instructs saving a session_id and potentially storing/using an acquired anonymous token (NEMO_TOKEN). It does not request always:true, nor does it attempt to modify other skills, but persistent session tokens and local config writes are possible and should be limited/inspected.

What to consider before installing

This skill will upload images and session tokens to a third-party service (mega-api-prod.nemovideo.ai) and may read/write a local config directory and probe install paths. That is coherent with an online image-to-video renderer, but you should: 1) confirm the service's identity and privacy/retention policy before sending photos (avoid sensitive images), 2) prefer using an anonymous/ephemeral token (and verify where the agent stores it), 3) be cautious about allowing the skill to read '~/.config/nemovideo/' or detect install paths because that can reveal local info, and 4) if unsure about the origin of this skill (source is unknown), do not install or test with real personal data until you can verify the domain and operator.

Getting Started

Share your still images and I'll get started on AI dance video generation. Or just tell me what you're thinking.

Try saying:

• "animate my still images"
• "export 1080p MP4"
• "make this photo dance to a"

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.

Image to Video Dance — Animate Photos into Dance Videos

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

Here's a typical use: you send a a single portrait photo of a person, ask for make this photo dance to a hip-hop beat, and about 30-90 seconds later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — clear front-facing photos with the full body visible produce the most accurate dance animations.

Matching Input to Actions

User prompts referencing image to video dance, 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.

All calls go to https://mega-api-prod.nemovideo.ai. The main endpoints:

1. Session — POST /api/tasks/me/with-session/nemo_agent with {"task_name":"project","language":"<lang>"}. Gives you a session_id.
2. Chat (SSE) — POST /run_sse with session_id and your message in new_message.parts[0].text. Set Accept: text/event-stream. Up to 15 min.
3. Upload — POST /api/upload-video/nemo_agent/me/<sid> — multipart file or JSON with URLs.
4. Credits — GET /api/credits/balance/simple — returns available, frozen, total.
5. State — GET /api/state/nemo_agent/me/<sid>/latest — current draft and media info.
6. Export — POST /api/render/proxy/lambda with render ID and draft JSON. Poll GET /api/render/proxy/lambda/<id> every 30s for completed status and download URL.

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

Headers are derived from this file's YAML frontmatter. X-Skill-Source is image-to-video-dance, 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).

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

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)

Backend Response Translation

The backend assumes a GUI exists. Translate these into API actions:

Backend says	You do
"click [button]" / "点击"	Execute via API
"open [panel]" / "打开"	Query session state
"drag/drop" / "拖拽"	Send edit via SSE
"preview in timeline"	Show track summary
"Export button" / "导出"	Execute 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.

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 "make this photo dance to a hip-hop beat" — concrete instructions get better results.

Max file size is 200MB. Stick to JPG, PNG, WEBP, HEIC for the smoothest experience.

Export as MP4 for widest compatibility with social media platforms.

Common Workflows

Quick edit: Upload → "make this photo dance to a hip-hop beat" → Download MP4. Takes 30-90 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.