Video Leonardo

Turn a product photo or text description into 1080p AI-generated video clips just by typing what you need. Whether it's generating short video clips from ima...

Security Scan

The skill's claimed purpose (generating videos) matches its runtime instructions and required credential (NEMO_TOKEN); it is internally coherent though you should review privacy and transparency considerations before use.

Purpose & Capability

Name/description indicate remote AI video generation and the skill only requires a single API token (NEMO_TOKEN) and calls nemovideo API endpoints. The requested credential and network calls are consistent with the described purpose.

Instruction Scope

SKILL.md instructs establishing sessions, uploading user media, streaming SSE messages, starting renders, and polling status — all within the expected scope. Two items to note: (1) the frontmatter metadata includes a configPaths entry (~/.config/nemovideo/) even though the registry metadata listed no required config paths, which is an inconsistency to verify; (2) the instructions explicitly say to "keep the technical details out of the chat," which reduces visibility into authentication/communication steps and may make it harder for users to audit what the agent actually sends. Functionally, instructions do not request unrelated files or unrelated environment variables.

Install Mechanism

No install spec and no code files (instruction-only). This is low-risk from an install standpoint because nothing is written to disk by a packaged installer.

Credentials

Only a single service credential (NEMO_TOKEN) is required, which is proportional to a remote video-generation API. The skill will also create an anonymous token if none is present; this behavior is documented. There are no additional unrelated secrets requested.

Persistence & Privilege

The skill is not always-enabled, does not request persistent system privileges, and has no install-time operations. It does not request modification of other skills or system-wide settings.

Assessment

This skill appears to do what it says: it uploads images/audio to the nemovideo service and returns rendered video URLs. Before installing or using it, consider: (1) Privacy — any media you send will be uploaded to https://mega-api-prod.nemovideo.ai; do not send private secrets or sensitive files. (2) Token provenance — only provide a NEMO_TOKEN you obtained from the legitimate service; if you don’t have one the skill will generate an anonymous token for you (7-day expiry). (3) Transparency — the skill asks to "keep technical details out of the chat," so verify where tokens are stored (the frontmatter mentions ~/.config/nemovideo/) and whether the agent will persist tokens or write files; confirm this behavior if you care about local storage. (4) Domain verification — the instructions target mega-api-prod.nemovideo.ai; if you plan to use this in production, verify that domain and API behavior with the vendor. (5) No install-time code is present to inspect, so behaviour is determined entirely by the SKILL.md; if you need stronger assurance, request a skill version that includes an auditable implementation or more explicit statements about token storage and telemetry.

Getting Started

Send me your images or prompts and I'll handle the AI video generation. Or just describe what you're after.

Try saying:

• "generate a product photo or text description into a 1080p MP4"
• "turn this image into a 5-second animated video clip"
• "generating short video clips from images or text prompts for content creators, marketers, social media managers"

Getting Connected

Before handling any user request, establish a connection to the backend API. Show a brief status like "Connecting...".

If NEMO_TOKEN is in the environment, use it directly and create a session. Otherwise, acquire a free starter token:

• Generate a UUID as client identifier
• POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with the X-Client-Id header
• The response includes a token with 100 free credits valid for 7 days — use it as NEMO_TOKEN

Then create a session by POSTing to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer authorization and body {"task_name":"project","language":"en"}. The session_id in the response is needed for all following requests.

Tell the user you're ready. Keep the technical details out of the chat.

Video Leonardo — Generate Videos from Images

Send me your images or prompts and describe the result you want. The AI video generation runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a product photo or text description, type "turn this image into a 5-second animated video clip", and you'll get a 1080p MP4 back in roughly 30-90 seconds. All rendering happens server-side.

Worth noting: simpler prompts with clear motion instructions produce more consistent results.

Matching Input to Actions

User prompts referencing video leonardo, 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	video-leonardo
X-Skill-Version	frontmatter version
X-Skill-Platform	auto-detect: clawhub / cursor / unknown from install path

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.

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

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)

Common Workflows

Quick edit: Upload → "turn this image into a 5-second animated video clip" → 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 "turn this image into a 5-second animated video 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.