Kling Ai 30

Skip the learning curve of professional editing software. Describe what you want — generate a 30-second cinematic video from this image with slow camera move...

Security Scan

The skill's requests and runtime instructions are broadly consistent with a remote AI video-rendering service: it needs a service token, uploads user media, and calls an external API — nothing obviously unrelated to its stated purpose, but there are a few small inconsistencies and privacy considerations to review before installing.

Purpose & Capability

Name/description (30-second AI video generation) match the required credential (NEMO_TOKEN) and the API endpoints the SKILL.md instructs the agent to call. Requiring a service token to render videos on a remote GPU is proportionate to the stated purpose.

Instruction Scope

The SKILL.md contains concrete runtime steps: anonymous-token generation (if NEMO_TOKEN not set), session creation, SSE message streaming, multipart file uploads, polling renders, and returning download URLs. Those actions are expected for a remote render pipeline. Two things to note: (1) the instructions derive a header value from an 'install path' to set X-Skill-Platform — that implies the agent might inspect its install location or environment to construct headers (this is not harmful per se but is a filesystem/environment access step not explicitly declared elsewhere); (2) the instructions assume the agent can upload files by path ("files=@/path") which requires the agent to access user-supplied attachments or local paths — ensure the agent will only upload files the user explicitly provides.

Install Mechanism

This is an instruction-only skill with no install spec and no code files — lowest install risk. No external archives or installers are requested.

Credentials

Only a single credential (NEMO_TOKEN) is required, which aligns with the service. The frontmatter in SKILL.md also references a config path (~/.config/nemovideo/) while the registry metadata lists no required config paths — this discrepancy should be clarified (does the skill read or write that directory?). The SKILL.md instructs the agent to generate an anonymous token by POSTing to an external endpoint and then use/store it as NEMO_TOKEN; confirm where and how that token is persisted and whether the agent will display or transmit it (SKILL.md warns not to print tokens).

Persistence & Privilege

The skill is not marked always:true and has no special persistence or system-wide privileges. It does instruct saving session_id and using tokens for subsequent calls (normal for session-based APIs). Autonomous invocation is allowed by default; combined with the narrow scope and single service token, this is not an elevated privilege by itself.

Assessment

This skill appears to do what it says — call a remote Nemovideo API to render short videos — but check these before installing: (1) Verify the API domain (mega-api-prod.nemovideo.ai) is the legitimate service you expect; (2) Ask how and where NEMO_TOKEN (and session_id) will be stored and for how long; tokens are bearer credentials and grant the service access to render and manage jobs; (3) Be cautious uploading sensitive media — uploaded files may be stored and processed on the vendor’s servers; (4) Clarify the SKILL.md/configPaths discrepancy (~/.config/nemovideo/) — confirm whether the skill will read or write that directory and why; (5) If you don’t already have a trusted NEMO_TOKEN, the skill can generate an anonymous token with limited credits — decide whether you want that token auto-created. If any of these are unacceptable, avoid installing or request a version of the skill that documents token storage and data-retention/privacy policies.

Getting Started

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

Try saying:

• "generate a photo of a mountain landscape into a 1080p MP4"
• "generate a 30-second cinematic video from this image with slow camera movement"
• "generating 30-second AI videos from images or text prompts for content creators"

Automatic Setup

On first interaction, connect to the processing API before doing anything else. Show a brief status like "Setting things up...".

Token: If NEMO_TOKEN environment variable is already set, use it and skip to Session below.

Free token: Generate a UUID as client identifier, then POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id: <uuid>. The response field data.token becomes your NEMO_TOKEN (100 credits, 7-day expiry).

Session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Save session_id from the response.

Confirm to the user you're connected and ready. Don't print tokens or raw JSON.

Kling AI 30-Second Video — Generate 30-Second AI Videos

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 "generate a 30-second cinematic video from this image with slow camera movement", and you'll get a 1080p MP4 back in roughly 1-3 minutes. All rendering happens server-side.

Worth noting: 30-second clips use more credits than shorter ones — preview at 5 seconds first to check motion quality.

Matching Input to Actions

User prompts referencing kling ai 30, 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.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is kling-ai-30, 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).

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

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.

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 → "generate a 30-second cinematic video from this image with slow camera movement" → 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 "generate a 30-second cinematic video from this image with slow camera movement" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across social platforms.