Video Examples

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

Security Scan

The skill's requirements and runtime instructions are consistent with a cloud video-generation service: it only needs a service token, uploads user media to the stated backend, and has no install-time code or surprising machine-level privileges.

Purpose & Capability

Name/description (generate example videos) align with required env var NEMO_TOKEN and the declared config path (~/.config/nemovideo/). No unrelated credentials or binaries are requested.

Instruction Scope

SKILL.md instructs the agent to create sessions, upload media, stream SSE, poll job state, and include skill attribution headers. These actions are appropriate for the stated purpose. One minor scope note: it asks the agent to read the skill's frontmatter and detect install path (~/.clawhub, ~/.cursor/skills) to populate X-Skill-Platform — that requires checking filesystem paths beyond just using the provided token. This is explainable but worth being aware of.

Install Mechanism

There is no install spec and no code files (instruction-only), so nothing is written to disk or downloaded during installation.

Credentials

Only one credential (NEMO_TOKEN) is required and declared as the primary credential. The SKILL.md also documents an anonymous-token flow if NEMO_TOKEN is absent; this network flow is consistent with the skill's purpose.

Persistence & Privilege

Skill is user-invocable, not always-enabled, and does not request persistent system-wide privileges or modification of other skills. It creates ephemeral sessions with the backend as expected for cloud rendering.

Assessment

This skill will upload your media to mega-api-prod.nemovideo.ai and requires a NEMO_TOKEN (or will fetch an anonymous starter token). Before using: (1) avoid uploading sensitive/private footage because files leave your machine; (2) consider using an ephemeral or limited token if you have concerns about long-term access; (3) be aware the skill may inspect its own frontmatter and check common install directories to set an attribution header; (4) review the service's privacy/terms outside the skill if you need guarantees about retention or sharing; otherwise the skill appears coherent for its stated purpose.

Getting Started

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

Try saying:

• "generate a 2-minute tutorial recording into a 1080p MP4"
• "show me example videos made with this tool"
• "browsing sample outputs to understand what the tool can produce for marketers"

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 Examples — Browse and Preview Sample Videos

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

Say you have a 2-minute tutorial recording and want to show me example videos made with this tool — the backend processes it in about under a minute and hands you a 1080p MP4.

Tip: shorter example clips give you a clearer sense of quality before uploading your own footage.

Matching Input to Actions

User prompts referencing video examples, 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.

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

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

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

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.

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

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 → "show me example videos made with this tool" → Download MP4. Takes under a minute 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 "show me example videos made with this tool" — concrete instructions get better results.

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

Export as MP4 for widest compatibility.