Simple Video Editing With

content creators and social media users edit raw video clips into polished edited clips using this skill. Accepts MP4, MOV, AVI, WebM up to 500MB, renders on...

Security Scan

The skill broadly matches a cloud video-editing purpose, but there are inconsistencies and a few behaviours that are disproportionate or under-specified (reading local install/config paths, auto-creating/hiding tokens, and metadata mismatch).

Purpose & Capability

The skill's declared purpose (cloud video editing) aligns with the API endpoints and workflows in SKILL.md (upload, render, export). Requesting a single service token (NEMO_TOKEN) is expected. However, the runtime metadata and instructions ask the agent to read local install paths (~/.clawhub, ~/.cursor/skills) and a config path (~/.config/nemovideo/), which are not necessary for basic editing and are not declared in the registry metadata (registry said 'Required config paths: none'). This is an inconsistency and expands local access beyond the minimal need to call a remote API.

Instruction Scope

The SKILL.md instructs the agent to automatically obtain an anonymous token if NEMO_TOKEN is not set and to 'Keep setup communication brief' and 'Don't display raw API responses or token values to the user.' That instruction to hide token/API responses is unusual and removes transparency from the user. The skill also asks the agent to read the file's YAML frontmatter for attribution and to detect install paths to set X-Skill-Platform — these require reading local filesystem locations. The instructions do not explicitly describe where or how tokens/sessions are persisted (env, memory, disk), leaving storage semantics unclear.

Install Mechanism

No install spec and no code files (instruction-only) — low on-disk footprint and lower installer risk. All network interactions happen at runtime via the remote API.

Credentials

Only one credential (NEMO_TOKEN) is declared as required, which is proportional for a cloud service. However the skill will generate an anonymous token on behalf of the user if none is present; it also instructs not to surface that token to the user. That behaviour is plausible but should be explicit: users should be told if tokens or session identifiers are stored locally or reused across invocations. Also registry metadata did not list the config path that the SKILL.md expects (~/.config/nemovideo/), creating a transparency gap about where secrets/config could be read or written.

Persistence & Privilege

always:false and default model invocation are present (normal). The skill does create short-lived sessions/tokens on the backend, but it does not request permanent platform-wide privileges or ask to modify other skills. The only persistence signalled is storing session_id for the session; where/how that is stored is unspecified.

What to consider before installing

This skill appears to do what it claims (cloud video editing), but there are a few things to ask or confirm before installing: - Why does it need to inspect your install directories (~/.clawhub, ~/.cursor/skills) and ~/.config/nemovideo/? Reading those paths is not required to edit a video and could reveal other environment details. - If NEMO_TOKEN isn't provided, the skill will automatically create an anonymous token and use it — ask where that token and the session_id are stored (in-memory vs written to disk) and whether it will be reused across sessions. - The SKILL.md explicitly says not to show raw API responses or token values to the user; request clarification on that policy and ask for explicit console/log options for transparency. - The skill will send your uploaded media to a remote host (mega-api-prod.nemovideo.ai). If you handle sensitive content, avoid uploading until you verify the service's privacy/data-retention policies. If you want to proceed, consider running the skill in an isolated environment, provide your own NEMO_TOKEN if you trust the service, and request the developer to remove or justify filesystem checks and to document token storage/expiration behavior.

Getting Started

Ready when you are. Drop your raw video clips here or describe what you want to make.

Try saying:

• "edit a 2-minute unedited screen recording into a 1080p MP4"
• "trim the pauses, add transitions, and export as a clean MP4"
• "quickly trimming and cleaning up raw footage without complex software for content creators and social media users"

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.

Simple Video Editing With AI — Edit and Export Polished Videos

Drop your raw video clips in the chat and tell me what you need. I'll handle the AI-assisted video editing on cloud GPUs — you don't need anything installed locally.

Here's a typical use: you send a a 2-minute unedited screen recording, ask for trim the pauses, add transitions, and export as a clean MP4, and about 30-90 seconds later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — shorter clips under 3 minutes process significantly faster and use fewer credits.

Matching Input to Actions

User prompts referencing simple video editing with, 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.

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

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

Include Authorization: Bearer <NEMO_TOKEN> and all attribution headers on every request — omitting them triggers a 402 on export.

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.

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 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)

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 "trim the pauses, add transitions, and export as a clean MP4" — concrete instructions get better results.

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

Export as MP4 with H.264 codec for the widest device and platform compatibility.

Common Workflows

Quick edit: Upload → "trim the pauses, add transitions, and export as a clean MP4" → Download MP4. Takes 30-90 seconds 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.