Generator By Link

Get generated video clips ready to post, without touching a single slider. Upload your URL or link (MP4, MOV, WebM, AVI, up to 500MB), say something like "ge...

Security Scan

The skill's declared purpose (generate videos from URLs) matches what its instructions ask for: a single service token (NEMO_TOKEN), calls to nemovideo.ai endpoints, uploads, and session management — nothing in the manifest suggests a different hidden purpose, but there are a few minor implementation mismatches to watch for.

Purpose & Capability

The skill claims to generate videos from links and requires a NEMO_TOKEN and access to nemovideo.ai endpoints — these are proportional and expected. Minor oddity: the metadata declares a configPath (~/.config/nemovideo/) which matches the service, but the runtime instructions also instruct detecting other install paths (~/.clawhub/, ~/.cursor/skills/) to populate the X-Skill-Platform header. Probing those install locations is not necessary for core functionality and is unnecessary surface access.

Instruction Scope

SKILL.md stays within the stated purpose: creating sessions, uploading URLs/files, streaming SSE responses, polling render status, and returning a download URL. It includes instructions to upload local files (multipart form with files=@/path) and to poll session state; these are expected for a media upload pipeline. Two things to watch: (1) the skill instructs inferring platform by checking local install paths (reads user home paths), and (2) it instructs creating an anonymous token by POSTing to an external endpoint if NEMO_TOKEN is absent — both are within scope but increase what the agent will check/send.

Install Mechanism

No install specification and no code files — the skill is instruction-only. That minimizes on-disk risk (nothing is downloaded or executed by an installer).

Credentials

The skill requires a single primary credential, NEMO_TOKEN, which is directly used for authorizing API calls and is proportionate. However, the skill's runtime also instructs checking additional local paths (~/.clawhub/, ~/.cursor/skills/) for header population even though those aren't listed in declared configPaths, creating a mismatch between declared required paths (~/.config/nemovideo/) and the paths the instructions ask the agent to probe. Additionally, instructions to accept local file paths for upload mean the agent will read files you point it to — expected for uploads but a privacy consideration.

Persistence & Privilege

The skill does not request always:true and has no install step that writes persistent components. It can be invoked by the agent (default), which is normal; there is no evidence it modifies other skills or system-wide settings.

Assessment

This skill appears to do what it says: it uses a NEMO_TOKEN (or obtains a temporary anonymous token) to call nemovideo.ai endpoints to convert links or uploaded files into videos. Before installing/using: (1) only provide files you are comfortable uploading — uploads will be sent to the external service; (2) prefer using a low-privilege or time-limited token if possible rather than a long-lived secret; (3) be aware the skill may check for certain install/config paths in your home directory to populate an attribution header — if you don't want that, avoid installing or providing environment/config data; (4) verify the endpoint/domain (mega-api-prod.nemovideo.ai) against any official service you expect to use. If you want stronger assurance, ask the publisher for source code or a trustworthy homepage and a clear privacy/TOS statement before trusting sensitive content.

Getting Started

Got URL or link to work with? Send it over and tell me what you need — I'll take care of the AI video generation.

Try saying:

• "generate a YouTube or webpage URL into a 1080p MP4"
• "generate a video from this article link: https://example.com/blog-post"
• "creating videos from web links or online content for marketers, content creators, bloggers"

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.

Generator by Link — Create Videos from URLs

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

Say you have a YouTube or webpage URL and want to generate a video from this article link: https://example.com/blog-post — the backend processes it in about 1-2 minutes and hands you a 1080p MP4.

Tip: shorter articles or concise web pages produce more focused videos.

Matching Input to Actions

User prompts referencing generator by link, 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 generator-by-link, 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 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

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "generate a video from this article link: https://example.com/blog-post" — concrete instructions get better results.

Max file size is 500MB. Stick to MP4, MOV, WebM, AVI for the smoothest experience.

Export as MP4 for widest compatibility.

Common Workflows

Quick edit: Upload → "generate a video from this article link: https://example.com/blog-post" → Download MP4. Takes 1-2 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.