Kling Ai Video

Skip the learning curve of professional editing software. Describe what you want — animate this image into a 5-second cinematic video clip — and get AI gener...

Security Scan

The skill's declared purpose (AI video generation) aligns with the environment access and runtime instructions; no high-risk installs or unrelated credentials are requested, but there are small inconsistencies in the skill metadata about config paths and it asks the agent to inspect local install paths for attribution headers.

Purpose & Capability

Name/description, required env var (NEMO_TOKEN), and the API endpoints referenced in SKILL.md all align with a cloud-based AI video generation service.

Instruction Scope

Instructions are specific to the remote rendering service and detail session, SSE, upload and export workflows. They also instruct the agent to read this file's YAML frontmatter and to detect install path (~/.clawhub/, ~/.cursor/skills/) to populate X-Skill-Platform — this requires filesystem probing of install paths (minor scope creep) but is explainable as attribution behavior.

Install Mechanism

No install spec or downloaded code; skill is instruction-only so nothing is written to disk by an installer. This is the lowest-risk install posture.

Credentials

Only NEMO_TOKEN is required (appropriate for the described API). However, the SKILL.md frontmatter also lists a config path (~/.config/nemovideo/) while the registry metadata reported none — this inconsistency should be clarified as it implies the skill may look for local config files.

Persistence & Privilege

always is false and the skill does not request system-wide changes or other skills' credentials. It creates transient remote sessions/tokens as part of normal operation.

Assessment

This skill appears to do what it says: it will call the nemovideo API and needs a NEMO_TOKEN (or will obtain an anonymous token) to render videos. Before installing, confirm that the domain (mega-api-prod.nemovideo.ai) is legitimate for the service you expect and avoid putting a personal/privileged token into NEMO_TOKEN unless you trust the service. Ask the publisher to clarify the mismatch between the registry metadata (no config paths) and the SKILL.md frontmatter (~/.config/nemovideo/) and confirm whether the skill will read files under your home directory (it also checks install paths to set an attribution header). If you need higher assurance, request a published homepage, a source repository, or verifiable publisher identity before use.

Getting Started

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

Try saying:

• "generate my text prompts or images"
• "export 1080p MP4"
• "animate this image into a 5-second"

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.

Kling AI Video — Generate Videos from Images or Text

Send me your text prompts or images 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 photo of a mountain landscape, type "animate this image into a 5-second cinematic video clip", and you'll get a 1080p MP4 back in roughly 1-3 minutes. All rendering happens server-side.

Worth noting: shorter prompts with clear motion descriptions produce more consistent results.

Matching Input to Actions

User prompts referencing kling ai 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.

All calls go to https://mega-api-prod.nemovideo.ai. The main endpoints:

1. Session — POST /api/tasks/me/with-session/nemo_agent with {"task_name":"project","language":"<lang>"}. Gives you a session_id.
2. Chat (SSE) — POST /run_sse with session_id and your message in new_message.parts[0].text. Set Accept: text/event-stream. Up to 15 min.
3. Upload — POST /api/upload-video/nemo_agent/me/<sid> — multipart file or JSON with URLs.
4. Credits — GET /api/credits/balance/simple — returns available, frozen, total.
5. State — GET /api/state/nemo_agent/me/<sid>/latest — current draft and media info.
6. Export — POST /api/render/proxy/lambda with render ID and draft JSON. Poll GET /api/render/proxy/lambda/<id> every 30s for completed status and download URL.

Formats: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.

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

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

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

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)

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

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.

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

Common Workflows

Quick edit: Upload → "animate this image into a 5-second cinematic video clip" → Download MP4. Takes 1-3 minutes 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 this image into a 5-second cinematic video clip" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across social platforms.