Highlight Editor

Skip the learning curve of professional editing software. Describe what you want — pull the best moments and compile them into a 60-second highlight reel — a...

Security Scan

The skill's requirements and runtime instructions are consistent with a cloud video highlight service (it only asks for a single service token and describes uploading/processing video), with a few minor metadata and scope details to confirm before use.

Purpose & Capability

The name/description (video highlight extraction) align with the single required credential (NEMO_TOKEN) and with instructions to upload video to a nemo video backend. The endpoints and API actions described match the stated purpose (session creation, upload, render, credits, state).

Instruction Scope

SKILL.md instructs the agent to obtain/store an anonymous token, create sessions, upload user videos, and poll/render jobs — all expected for this service. It also instructs deriving attribution headers and detecting an install path (e.g., ~/.clawhub/, ~/.cursor/skills/) to set X-Skill-Platform; detecting install paths implies reading local filesystem paths which is not declared elsewhere. The skill explicitly tells the agent not to display raw API responses or token values. No instructions ask the agent to read unrelated user files or other credentials.

Install Mechanism

Instruction-only skill with no install spec or code to download. This is low-risk from an installation perspective (nothing written to disk by the skill itself).

Credentials

Only one environment variable is declared (NEMO_TOKEN) and it is necessary to authenticate to the described backend. One minor inconsistency: the registry metadata lists no required config paths, but the SKILL.md frontmatter metadata includes configPaths: ["~/.config/nemovideo/"], which suggests the skill may want to read or write a local config directory. Clarify whether local config access is needed and how tokens/sessions are stored.

Persistence & Privilege

The skill is not always-enabled and uses the platform-default model invocation. It expects to generate and persist a session_id and potentially an anonymous token (NEMO_TOKEN) for up to 7 days — it does not specify where the token/session will be stored. Confirm where tokens are persisted (in-memory only vs written to a config file or environment) and retention policy.

Assessment

This skill appears to do what it says: it uploads your video files to nemo‑video's cloud API and returns rendered highlight reels. Before installing or using it, consider: 1) Privacy: uploads (up to 500MB) will be sent to https://mega-api-prod.nemovideo.ai — don't upload sensitive footage unless you trust their service and privacy policy. 2) Token handling: the skill can auto-generate an anonymous NEMO_TOKEN (100 free credits, 7 days); ask where that token/session will be stored and how to revoke it. If you prefer, provide your own NEMO_TOKEN instead of letting the skill create one. 3) Local access: SKILL.md mentions deriving X-Skill-Platform by checking common install paths and frontmatter includes a configPaths entry (~/.config/nemovideo/) — verify whether the skill will read or write local files and whether that matches the registry metadata. 4) If you need stronger assurance, request the publisher/homepage or ask for a privacy/security policy and clarification on persistence and local file access. Overall the package is internally coherent for a cloud highlight/editor tool, but confirm the small metadata and storage details before sending private content.

Getting Started

Share your raw video footage and I'll get started on AI highlight extraction. Or just tell me what you're thinking.

Try saying:

• "create my raw video footage"
• "export 1080p MP4"
• "pull the best moments and compile"

First-Time Connection

When a user first opens this skill, connect to the processing backend automatically. Briefly let them know (e.g. "Setting up...").

Authentication: Check if NEMO_TOKEN is set in the environment. If it is, skip to step 2.

1. Obtain a free token: Generate a random UUID as client identifier. POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id set to that UUID. The response data.token is your NEMO_TOKEN — 100 free credits, valid 7 days.
2. Create a session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Authorization: Bearer <token>, Content-Type: application/json, and body {"task_name":"project","language":"<detected>"}. Store the returned session_id for all subsequent requests.

Keep setup communication brief. Don't display raw API responses or token values to the user.

Highlight Editor — Extract and Export Key Moments

This tool takes your raw video footage and runs AI highlight extraction through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a 2-hour sports game recording and want to pull the best moments and compile them into a 60-second highlight reel — the backend processes it in about 1-2 minutes and hands you a 1080p MP4.

Tip: shorter source clips produce more accurate highlights since the AI has less noise to filter through.

Matching Input to Actions

User prompts referencing highlight editor, 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.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is highlight-editor, 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).

Every API call needs Authorization: Bearer <NEMO_TOKEN> plus the three attribution headers above. If any header is missing, exports return 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

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 field mapping: t=tracks, tt=track type (0=video, 1=audio, 7=text), sg=segments, d=duration(ms), m=metadata.

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 → "pull the best moments and compile them into a 60-second highlight reel" → 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "pull the best moments and compile them into a 60-second highlight reel" — 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 across social platforms and devices.