Services Video

Skip the learning curve of professional editing software. Describe what you want — trim pauses, add branded intro, and export for our services page — and get...

Security Scan

The skill's requests and runtime instructions are generally consistent with a cloud video-editing service: it needs a single service token, it uploads user media to a third‑party API, and its steps match that purpose, but a small metadata mismatch and implicit filesystem probing are worth double-checking before use.

Purpose & Capability

Name/description (cloud AI video editing) aligns with the declared primary credential (NEMO_TOKEN) and the API endpoints and upload flows described in SKILL.md. Requiring a service token and session state is expected for a remote render service.

Instruction Scope

SKILL.md instructs the agent to upload user-supplied video files to https://mega-api-prod.nemovideo.ai, create sessions, poll render status, and stream SSE responses — all normal for a remote-rendering skill. It also instructs deriving an X-Skill-Platform value by inspecting install paths (e.g., ~/.clawhub/, ~/.cursor/skills/) and references a config path (~/.config/nemovideo/) in its frontmatter; this implies the agent may read filesystem paths to detect environment, which is plausible but broader than simply sending files and could leak local context if mishandled.

Install Mechanism

No install spec or code files are present; the skill is instruction-only. This is low-risk from an installation standpoint because nothing new is written to disk by an installer.

Credentials

Only one credential (NEMO_TOKEN) is declared and used. The skill additionally describes a flow to fetch an anonymous token if none is set — reasonable for anonymous access. No unrelated secrets or multiple external credentials are requested.

Persistence & Privilege

The skill does not request always:true and has no install-time persistence mechanisms declared. It instructs storing a session_id for the runtime session (expected for API use).

Assessment

This skill forwards uploaded videos and edit instructions to a third-party service (mega-api-prod.nemovideo.ai). Before installing or using it, confirm you are comfortable sending your media to that external provider and review their privacy/retention policy. Note the skill will (if no NEMO_TOKEN is set) obtain an anonymous token on your behalf and store a session_id for the active session — tokens are short‑lived per the docs but avoid using this with sensitive footage. The SKILL.md also references reading install/config paths to derive headers (e.g., ~/.config/nemovideo/ and detection of install paths), which could expose local environment details; if you prefer, run the skill in an isolated environment or ask the maintainer for a version that does not probe filesystem paths. Finally, the registry metadata shown to you omitted configPaths while the SKILL.md includes them — if provenance matters, request the full source or a verified homepage and verify the owner before trusting this skill with confidential media.

Getting Started

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

Try saying:

• "edit my raw video footage"
• "export 1080p MP4"
• "trim pauses, add branded intro, and"

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.

Services Video — Edit and Export Service Videos

Send me your raw video footage and describe the result you want. The AI video processing runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 2-minute service walkthrough recording, type "trim pauses, add branded intro, and export for our services page", and you'll get a 1080p MP4 back in roughly 1-2 minutes. All rendering happens server-side.

Worth noting: keep service demos under 90 seconds for best viewer retention.

Matching Input to Actions

User prompts referencing services 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.

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 services-video, 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 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

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.

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)

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "trim pauses, add branded intro, and export for our services page" — 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 websites and social platforms.

Common Workflows

Quick edit: Upload → "trim pauses, add branded intro, and export for our services page" → 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.