Best Editing With Ai

Turn a 3-minute unedited phone recording into 1080p polished edited clips just by typing what you need. Whether it's automatically editing raw footage into a...

Security Scan

The skill's declared purpose (cloud video editing) matches its runtime instructions and requested credential (NEMO_TOKEN), but there are inconsistencies and scope creep around filesystem/config access and how tokens/session data are handled that merit caution before installing.

Purpose & Capability

Name/description align with a cloud video-editing service and the skill only requests a single service token (NEMO_TOKEN), which is expected. However the SKILL.md frontmatter requests a config path (~/.config/nemovideo/) and the runtime asks the agent to read install paths to set X-Skill-Platform; the registry metadata supplied earlier listed no config paths. This mismatch between declared registry metadata and the SKILL.md is an incoherence to clarify.

Instruction Scope

The instructions require network calls to external API endpoints (expected) and uploading user video (expected), but also instruct the agent to read local paths to detect install platform and to read the skill frontmatter to set attribution headers. They tell the agent to 'save session_id' and to persist/use NEMO_TOKEN if returned. Reading home-directory paths and saving tokens/session identifiers expands the agent's scope beyond simple request/response and wasn't clearly declared in the registry metadata.

Install Mechanism

Instruction-only skill with no install spec and no code files; nothing is written to disk by an installer. This is the lowest install risk.

Credentials

Only a single credential (NEMO_TOKEN) is required, which is proportional for a cloud-editing integration. But SKILL.md's metadata claims a config path (~/.config/nemovideo/) and the skill asks to read install paths and frontmatter for attribution headers — the need to access user filesystem/config was not declared in the registry summary and should be justified.

Persistence & Privilege

always is false and the skill does not request elevated platform privileges. It does instruct the agent to persist session_id and potentially store/reuse an anonymous token as NEMO_TOKEN; storing its own session/token is normal for such an integration, but users should confirm where/how tokens are stored and for how long.

What to consider before installing

This skill appears to be a legitimate cloud video-editing integration, but exercise caution before installing: 1) The skill will require and accept a NEMO_TOKEN (or generate an anonymous token) and will upload your raw video to https://mega-api-prod.nemovideo.ai — do not upload sensitive content unless you trust the service. 2) The SKILL.md asks the agent to read home-directory install/config paths and the skill frontmatter to set attribution headers; confirm why filesystem access is needed and where any tokens/session IDs will be stored. 3) The skill has no listed source or homepage — prefer skills from known publishers or verify the API domain and privacy policy first. If you proceed, run it in a restricted/sandboxed environment, inspect network calls if possible, and avoid using persistent credentials with highly sensitive data until you confirm the provider's trustworthiness.

Getting Started

Send me your raw video footage and I'll handle the AI-powered editing. Or just describe what you're after.

Try saying:

• "edit a 3-minute unedited phone recording into a 1080p MP4"
• "cut out silences, add transitions, and sync background music"
• "automatically editing raw footage into a finished video for content creators and marketers"

Automatic Setup

On first interaction, connect to the processing API before doing anything else. Show a brief status like "Setting things up...".

Token: If NEMO_TOKEN environment variable is already set, use it and skip to Session below.

Free token: Generate a UUID as client identifier, then POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id: <uuid>. The response field data.token becomes your NEMO_TOKEN (100 credits, 7-day expiry).

Session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Save session_id from the response.

Confirm to the user you're connected and ready. Don't print tokens or raw JSON.

Best Editing with AI — Edit and Export Polished Videos

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

Say you have a 3-minute unedited phone recording and want to cut out silences, add transitions, and sync background music — the backend processes it in about 1-2 minutes and hands you a 1080p MP4.

Tip: shorter clips under 2 minutes process significantly faster and give more precise AI results.

Matching Input to Actions

User prompts referencing best editing with ai, 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.

All calls go to https://mega-api-prod.nemovideo.ai. The main endpoints:

1. Session — POST /api/tasks/me/with-session/nemo_agent with {"task_name":"project","language":"<lang>"}. Gives you a session_id.
2. Chat (SSE) — POST /run_sse with session_id and your message in new_message.parts[0].text. Set Accept: text/event-stream. Up to 15 min.
3. Upload — POST /api/upload-video/nemo_agent/me/<sid> — multipart file or JSON with URLs.
4. Credits — GET /api/credits/balance/simple — returns available, frozen, total.
5. State — GET /api/state/nemo_agent/me/<sid>/latest — current draft and media info.
6. Export — POST /api/render/proxy/lambda with render ID and draft JSON. Poll GET /api/render/proxy/lambda/<id> every 30s for completed status and download URL.

Formats: 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: best-editing-with-ai
• 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.

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)

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.

Error Handling

Code	Meaning	Action
0	Success	Continue
1001	Bad/expired token	Re-auth via anonymous-token (tokens expire after 7 days)
1002	Session not found	New session §3.0
2001	No credits	Anonymous: show registration URL with ?bind=<id> (get <id> from create-session or state response when needed). Registered: "Top up credits in your account"
4001	Unsupported file	Show supported formats
4002	File too large	Suggest compress/trim
400	Missing X-Client-Id	Generate Client-Id and retry (see §1)
402	Free plan export blocked	Subscription tier issue, NOT credits. "Register or upgrade your plan to unlock export."
429	Rate limit (1 token/client/7 days)	Retry in 30s once

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "cut out silences, add transitions, and sync background music" — 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 best balance of quality and file size.

Common Workflows

Quick edit: Upload → "cut out silences, add transitions, and sync background music" → 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.