Soulgen Ai

generate text prompts or images into AI character videos with this skill. Works with JPG, PNG, MP4, WebM files up to 200MB. content creators, digital artists...

Security Scan

The skill's API usage and single required token (NEMO_TOKEN) are consistent with a video-generation integration, but there are metadata mismatches and small privacy/persistence concerns that warrant caution.

Purpose & Capability

The name/description (AI character video rendering) aligns with the APIs and NEMO_TOKEN credential described in SKILL.md. Requesting a token and session for a cloud render service is expected. However, the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) while the registry metadata reported no required config paths — this inconsistency is unexplained and could affect where credentials/session state are stored.

Instruction Scope

Instructions are focused on connecting to the nemovideo backend, creating an anonymous token if none is provided, creating sessions, uploading user-supplied media, and polling export status. They do not instruct reading arbitrary host files. Two items to note: (1) SKILL.md instructs auto-generation and storage of session_id/token but doesn't specify a safe storage location; (2) the X-Skill-Platform header is to be auto-detected from the install path, which implies the agent may inspect its install/runtime path — an extra filesystem/environment access not strictly necessary for core functionality.

Install Mechanism

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

Credentials

Only one credential is declared (NEMO_TOKEN), which is appropriate for a third-party API. The skill also documents how to obtain an anonymous token if none is set. The frontmatter's configPaths entry suggests the skill expects or may use ~/.config/nemovideo/ for persistence, but the registry listing did not show required config paths — this mismatch could lead to unexpected local storage of session/token data.

Persistence & Privilege

The skill instructs the agent to 'store the returned session_id for all subsequent requests' and the frontmatter references a user config directory. Persisting session tokens to disk (or otherwise keeping long-lived state) increases privacy risk. The skill is not always-enabled, but the potential for local persistent storage of credentials/session state (and the mismatch about whether config paths are required) is a notable concern.

What to consider before installing

This skill mostly does what it says: it talks to a nemovideo API and needs an API token. Before installing, consider: (1) The SKILL.md lists a local config path (~/.config/nemovideo/) but the registry metadata omitted it — ask the publisher where session/token data is stored and whether it will be written to disk. (2) Decide whether you want the skill to obtain an anonymous token automatically or provide your own NEMO_TOKEN; automatic token issuance means the skill will make network calls to https://mega-api-prod.nemovideo.ai. (3) The skill may inspect its install/runtime path to fill the X-Skill-Platform header — confirm whether filesystem access will be performed. (4) Uploaded media (photos with faces) will be sent to a third-party service — review privacy implications and the service's policies before uploading sensitive content. (5) Because the source and homepage are unknown, prefer to obtain more publisher info or a published privacy/security policy before use.

Getting Started

Share your text prompts or images and I'll get started on AI image and video generation. Or just tell me what you're thinking.

Try saying:

• "generate my text prompts or images"
• "export 1080p MP4"
• "generate a realistic AI character video"

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.

SoulGen AI — Generate AI Character Videos

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

Here's a typical use: you send a a portrait photo or written character description, ask for generate a realistic AI character video from a text description, 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 face photos produce more accurate and consistent character outputs.

Matching Input to Actions

User prompts referencing soulgen 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.

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

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

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

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

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.

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 → "generate a realistic AI character video from a text description" → 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "generate a realistic AI character video from a text description" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across social platforms.