A2e Ai Image To Video

Get animated video clips ready to post, without touching a single slider. Upload your static images (JPG, PNG, WEBP, HEIC, up to 200MB), say something like "...

Security Scan

The skill mostly matches its stated function (cloud image→video) and only needs a service token, but it asks for filesystem/config access and auto-generates/uses anonymous tokens from an external domain with no source/homepage — these mismatches warrant caution.

Purpose & Capability

The skill's stated purpose (convert images to video via the NEMO backend) aligns with requiring a NEMO_TOKEN and calling the provider's APIs. However metadata declares a required config path (~/.config/nemovideo/) and the runtime instructions ask the agent to detect install paths (e.g., ~/.clawhub/, ~/.cursor/skills/) to set an attribution header. Neither the config path nor scanning other install directories is clearly necessary for basic image→video operation and represents unnecessary access to user files/config.

Instruction Scope

SKILL.md instructs network interactions with https://mega-api-prod.nemovideo.ai (expected) and to auto-generate anonymous tokens when NEMO_TOKEN isn't present (also plausible). But it also directs deriving X-Skill-Platform from local install paths (implies reading home dirs) and includes a metadata configPaths entry — this extends the agent's runtime actions beyond handling only user-provided images and API calls. The doc otherwise does not instruct reading arbitrary system files or exfiltrating unrelated data.

Install Mechanism

Instruction-only skill with no install spec or code files; no downloads or on-disk installs are required. This is the lowest-risk install model.

Credentials

Only one credential is declared (NEMO_TOKEN), which is appropriate for an API-backed service. However, requiring a config path (~/.config/nemovideo/) in metadata is disproportionate and unexplained. The skill's fallback behavior to request an anonymous token from the external API is acceptable, but note it will cause network calls that create and store short-lived tokens if the env var isn't provided.

Persistence & Privilege

always:false and no install steps; the skill does not request persistent, system-wide privileges or modify other skills. It may store a session_id for the session, which is normal for an API client.

What to consider before installing

This skill appears to do what it says (convert images to short videos using a cloud backend) and only needs a NEMO_TOKEN. Still, be cautious: there is no listed source or homepage for the service domain (mega-api-prod.nemovideo.ai), and the skill's metadata/instructions request access to user config paths and to detect install directories — access that is not strictly required to create videos. Before installing/providing credentials, consider: (1) Do you trust the external domain? Look for an official homepage or docs. (2) Prefer manually supplying a token (NEMO_TOKEN) rather than allowing the skill to auto-create/store one. (3) Ask the maintainer why the skill needs ~/.config/nemovideo/ and why it should detect ~/.clawhub or ~/.cursor paths; decline or restrict filesystem access if you’re uncomfortable. (4) Monitor outgoing network calls if possible and avoid giving broad filesystem permissions to the agent. If the publisher/source is unknown and you cannot verify their privacy/terms, treat this as higher risk and avoid installing or test in an isolated environment.

Getting Started

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

Try saying:

• "convert my static images"
• "export 1080p MP4"
• "animate this image into a 5-second"

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.

A2E AI Image to Video — Convert Images into Video Clips

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

Here's a typical use: you send a a single product photo or illustrated scene, ask for animate this image into a 5-second video clip with smooth motion, 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 — high-contrast images with clear subjects animate more naturally than busy backgrounds.

Matching Input to Actions

User prompts referencing a2e ai image to 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.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is a2e-ai-image-to-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).

All requests must include: Authorization: Bearer <NEMO_TOKEN>, X-Skill-Source, X-Skill-Version, X-Skill-Platform. Missing attribution headers will cause export to fail with 402.

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.

SSE Event Handling

Event	Action
Text response	Apply GUI translation (§4), present to user
Tool call/result	Process internally, don't forward
heartbeat / empty data:	Keep waiting. Every 2 min: "⏳ Still working..."
Stream closes	Process final response

~30% of editing operations return no text in the SSE stream. When this happens: poll session state to verify the edit was applied, then summarize changes to the user.

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

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)

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

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "animate this image into a 5-second video clip with smooth motion" — 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 across social platforms and video editors.

Common Workflows

Quick edit: Upload → "animate this image into a 5-second video clip with smooth motion" → 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.