Dreamface Ai

Skip the learning curve of professional editing software. Describe what you want — animate my photo to lip-sync with this audio clip — and get animated face...

Security Scan

The skill's runtime instructions mostly match a cloud face-animation service, but missing provenance, a frontmatter/registry mismatch (configPaths), opaque token storage and automatic token minting, and uploading personal media to an unverified third‑party endpoint make this risky without more information.

Purpose & Capability

The name/description (animate photos to talking videos) aligns with the endpoints and flows in SKILL.md. Requiring a NEMO_TOKEN is reasonable for an API-backed rendering service. However the skill frontmatter references a config path (~/.config/nemovideo/) that isn't declared in the registry metadata — this mismatch could indicate the skill expects to read/write a local config directory (for caching tokens/sessions) even though the registry said no config paths required.

Instruction Scope

Instructions tell the agent to obtain anonymous tokens, create and persist a session_id, upload user-supplied images/audio to the remote API, and to 'keep the token' while also instructing not to show raw tokens to users. Where/how the token and session_id should be stored is unspecified (in-memory, env var, or written to disk under the ~/.config path). The skill also requires adding attribution headers and auto-detecting an install path, which implies reading agent/install metadata. Uploading potentially sensitive personal media to an external domain is expected for this function but should be explicit to users.

Install Mechanism

Instruction-only skill with no install spec or code files — lowest installation risk. There is no download, binary, or package installation step described.

Credentials

Only one credential (NEMO_TOKEN) is declared as primary, which is proportionate. However the skill's ability to mint an anonymous token on the user's behalf and the unclear storage semantics (and the frontmatter-configPath mismatch) increase the chance the skill will write/authenticate somewhere on the host or in agent state. No other unrelated secrets are requested.

Persistence & Privilege

always:false (normal). The skill can be invoked autonomously (platform default) which increases blast radius only if combined with broad privileges — here the skill's privileges are limited, but autonomous invocation plus network access and token use still merits caution.

What to consider before installing

This skill appears to implement a cloud face-animation workflow, but it posts user photos/audio to https://mega-api-prod.nemovideo.ai (unknown vendor) and will mint/store an anonymous token. Before installing or using it, confirm the service owner, privacy policy, and data retention rules; ask where the token and session_id are saved (in-memory vs written to ~/.config/nemovideo/); avoid uploading sensitive or private images; prefer creating a throwaway account/token if you test it; and verify the domain and service legitimacy (homepage, company info, or open-source repo). The frontmatter/configPaths discrepancy and lack of a homepage are the main red flags. If you want, I can draft questions to ask the author or suggest safer alternatives.

Getting Started

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

Try saying:

• "animate a single selfie or portrait photo into a 1080p MP4"
• "animate my photo to lip-sync with this audio clip"
• "animating still photos to talk or sing for content creators"

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.

DreamFace AI — Animate Photos Into Talking Videos

Drop your portrait photos in the chat and tell me what you need. I'll handle the AI face animation on cloud GPUs — you don't need anything installed locally.

Here's a typical use: you send a a single selfie or portrait photo, ask for animate my photo to lip-sync with this audio clip, 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 — front-facing portraits with clear lighting produce the most accurate lip-sync results.

Matching Input to Actions

User prompts referencing dreamface 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.

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.

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

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

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

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

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 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)

Common Workflows

Quick edit: Upload → "animate my photo to lip-sync with this audio clip" → 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 photo to lip-sync with this audio clip" — 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.