Ai Image Video

convert images into animated image videos with this skill. Works with JPG, PNG, WEBP, HEIC files up to 200MB. social media creators use it for converting ima...

Security Scan

The skill mostly matches its stated purpose (upload images to a cloud service and return videos) but has small metadata/instruction mismatches and will automatically create and persist tokens and upload user files — things you should understand before installing.

Purpose & Capability

The skill's name/description (image→video) aligns with the declared required credential (NEMO_TOKEN) and the API endpoints used. However there's an inconsistency: the registry metadata above lists no required config paths, but the skill's SKILL.md frontmatter metadata references a config path (~/.config/nemovideo/). Also the SKILL.md instructs the agent to auto-generate an anonymous NEMO_TOKEN if none is present, which means a pre-provided env var isn't strictly required — that is coherent but different from a strict 'requires env var' model.

Instruction Scope

Instructions stay within the advertised purpose (upload images, send SSE for edits, poll render status, return download URL). They explicitly instruct uploading user files to https://mega-api-prod.nemovideo.ai and to create/store session tokens. Two items to note: (1) the skill tells the agent to detect the install path to populate an X-Skill-Platform header (this requires reading local paths and is only for attribution), and (2) the agent is instructed to automatically obtain an anonymous token and store session_id/token for subsequent calls — meaning credentials and user files will be sent to the remote service without the user manually providing a token.

Install Mechanism

No install spec and no code files (instruction-only). This is low-risk from an install perspective because nothing is downloaded or written by an installer step — but runtime network activity and persistence are performed by the agent following the instructions.

Credentials

Only one environment credential is declared (NEMO_TOKEN), which makes sense for calling the nemo backend. But the skill provides an anonymous-token fallback flow (POST to /api/auth/anonymous-token) and references a config path (~/.config/nemovideo/) for storing state; that implies the skill may persist tokens/session data to disk. The declared registry metadata omitted config paths while SKILL.md includes them — an inconsistency that affects where credentials might be stored.

Persistence & Privilege

always:false (normal). The SKILL.md instructs saving session_id (and implicitly the anonymous token) for subsequent requests and references a config directory; so the skill will likely persist credentials/session state locally. Autonomous invocation is allowed (default) — combined with network upload of user images, this increases privacy impact but is consistent with the skill's stated function.

What to consider before installing

This skill will upload your images and create or use a NEMO_TOKEN to call a remote service (https://mega-api-prod.nemovideo.ai). Before installing or enabling it: 1) Only use it with non-sensitive images you’re comfortable sending to an external cloud service. 2) Be aware the skill can auto-generate an anonymous token and persist the token/session (SKILL.md references ~/.config/nemovideo/) — check that location after use and delete tokens if you want to revoke access. 3) If you prefer control, set your own NEMO_TOKEN (instead of relying on anonymous token generation) so you can revoke it later. 4) The registry metadata and the skill frontmatter disagree about config paths — ask the publisher for source or clarification (homepage is missing and owner is unknown) if you need stronger assurance. 5) Monitor network activity if you are concerned and consider running the skill in a restricted environment. If you want higher assurance, request the skill's source code or a verified publisher before use.

Getting Started

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

Try saying:

• "convert my images"
• "export 1080p MP4"
• "turn these images into a 30-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.

AI Image to Video — Convert Images Into MP4 Videos

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

Say you have five product photos in JPG format and want to turn these images into a 30-second slideshow video with transitions and music — the backend processes it in about 30-60 seconds and hands you a 1080p MP4.

Tip: using 5-10 images gives the smoothest pacing for short videos.

Matching Input to Actions

User prompts referencing ai image 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.

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

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

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

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.

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 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

Common Workflows

Quick edit: Upload → "turn these images into a 30-second slideshow video with transitions and music" → 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 "turn these images into a 30-second slideshow video with transitions and music" — 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.