Liveportrait

Get animated portrait video ready to post, without touching a single slider. Upload your portrait images (JPG, PNG, WEBP, MP4, up to 200MB), say something li...

Security Scan

The skill's actions (uploading user images to an external API using a NEMO_TOKEN) match its stated purpose, but there are minor inconsistencies and missing provenance (no homepage, unknown source) plus metadata/instruction mismatches that you should understand before installing.

Purpose & Capability

Name/description (animate portrait images) align with the runtime instructions: the SKILL.md describes uploading images, creating sessions, streaming edits, and exporting MP4 via the nemovideo API. Requesting a single service token (NEMO_TOKEN) is proportional to this purpose. However, the skill has no published homepage or known source, which reduces provenance and increases risk.

Instruction Scope

Instructions explicitly tell the agent to obtain/use NEMO_TOKEN, generate an anonymous token when missing, POST files and messages to mega-api-prod.nemovideo.ai, and stream SSE results. Those are all consistent with the stated function. Concern: the SKILL.md metadata asks the agent to read this file's YAML frontmatter at runtime and to detect install paths (e.g. ~/.clawhub/, ~/.cursor/). The registry metadata shown to you earlier claims no required config paths while the SKILL.md includes a configPaths entry (~/.config/nemovideo/). That mismatch implies either the published registry info is incomplete or the runtime instructions expect filesystem access that wasn't declared.

Install Mechanism

Instruction-only skill with no install spec and no code files — lowest install risk. The skill issues network requests to a third-party API, but it does not download or install code.

Credentials

Only NEMO_TOKEN (primary credential) is required and the SKILL.md includes a path to acquire an anonymous token if none is set. This is proportional to a cloud rendering service. Note: the skill will upload user media to an external service (expected for the purpose); users should be aware this transmits potentially sensitive image/audio data off-device.

Persistence & Privilege

always:false and no install hooks are present. The skill does not request persistent platform privileges and does not attempt to modify other skills or system-wide config. It asks the agent to store session_id and use tokens for the session (normal for a remote API).

What to consider before installing

This skill appears to do what it claims (animate portraits by sending your images to nemovideo's API) and only requests a single token (NEMO_TOKEN). Before installing: (1) be aware that your images/audio will be uploaded to an external service — do not upload sensitive or private images unless you trust the provider; (2) provenance is weak (no homepage, unknown owner); consider whether you trust the endpoint mega-api-prod.nemovideo.ai and search for the service and privacy policy; (3) note the metadata mismatch: SKILL.md mentions a config path (~/.config/nemovideo/) and asks the agent to read this SKILL.md frontmatter and detect install paths — that suggests filesystem reads that were not declared in the registry metadata; if you need stricter guarantees, ask the skill author to clarify why the configPath is required and to publish a homepage/privacy policy and source. If you proceed, avoid using highly sensitive images and rotate any tokens or credentials if you stop using the skill.

Getting Started

Got portrait images to work with? Send it over and tell me what you need — I'll take care of the AI portrait animation.

Try saying:

• "animate a single front-facing photo of a person into a 1080p MP4"
• "animate my portrait photo to talk and move naturally"
• "animating still portrait photos into realistic talking videos for content creators, marketers, social media users"

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.

Live Portrait — Animate portraits into videos

This tool takes your portrait images and runs AI portrait animation through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a single front-facing photo of a person and want to animate my portrait photo to talk and move naturally — the backend processes it in about 30-60 seconds and hands you a 1080p MP4.

Tip: front-facing, well-lit photos with a clear face produce the most realistic animations.

Matching Input to Actions

User prompts referencing liveportrait, 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.

Base URL: https://mega-api-prod.nemovideo.ai

Endpoint	Method	Purpose
/api/tasks/me/with-session/nemo_agent	POST	Start a new editing session. Body: {"task_name":"project","language":"<lang>"}. Returns session_id.
/run_sse	POST	Send a user message. Body includes app_name, session_id, new_message. Stream response with Accept: text/event-stream. Timeout: 15 min.
/api/upload-video/nemo_agent/me/<sid>	POST	Upload a file (multipart) or URL.
/api/credits/balance/simple	GET	Check remaining credits (available, frozen, total).
/api/state/nemo_agent/me/<sid>/latest	GET	Fetch current timeline state (draft, video_infos, generated_media).
/api/render/proxy/lambda	POST	Start export. Body: {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll status every 30s.

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

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

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

Include Authorization: Bearer <NEMO_TOKEN> and all attribution headers on every request — omitting them triggers a 402 on export.

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

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.

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

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 → "animate my portrait photo to talk and move naturally" → 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "animate my portrait photo to talk and move naturally" — concrete instructions get better results.

Max file size is 200MB. Stick to JPG, PNG, WEBP, MP4 for the smoothest experience.

Export as MP4 for widest compatibility across social platforms.