Video Editing Ai Tools

Turn raw footage into polished, publish-ready content with AI-powered guidance built around video-editing-ai-tools workflows. Get instant recommendations on...

Security Scan

The skill's requested credential (NEMO_TOKEN) and API usage are plausible for a video-editing assistant, but there are inconsistencies and privacy-risk instructions (automatic anonymous token creation, guidance to hide tokens, and contradictory claims about uploading raw footage) that warrant caution.

Purpose & Capability

Name/description (AI video-editing assistant) align with needing an API token (NEMO_TOKEN) and a config path (~/.config/nemovideo/). Declared requirements (single service token) are proportional to the stated functionality. Minor inconsistency: frontmatter claims processing happens 'without pushing raw footage through the API' while the API reference includes a multipart file upload endpoint.

Instruction Scope

The SKILL.md instructs the agent to automatically obtain an anonymous token by POSTing to an external endpoint if NEMO_TOKEN isn't set, create and store sessions, and to avoid showing raw API responses or token values to the user. It also instructs reading the skill's YAML frontmatter and detecting install path to set attribution headers. These runtime instructions could lead to automatic network calls, storage of credentials/session IDs, and uploading local files (multipart upload example). The combination of 'hide token values' plus automatic token acquisition and session storage increases the risk that secrets or user data are handled without explicit user review. The upload endpoint and examples permit sending local files, contrary to the claim about not pushing raw footage.

Install Mechanism

Instruction-only skill with no install spec and no code files — lowest install risk; nothing will be written to disk by an installer. However, runtime behavior (network calls, optional storing of session_id / config under ~/.config/nemovideo/) is still possible via the agent's normal execution.

Credentials

Only a single credential (NEMO_TOKEN) is required, which is proportionate for a cloud-backed editing service. The skill's metadata also references a config path under ~/.config/nemovideo/ which may be used to persist tokens or session data; this is plausible but worth verifying. No unrelated secrets or broad environment access are requested.

Persistence & Privilege

always:false (normal). The skill expects to create and reuse a session_id and store it for subsequent requests—this is reasonable for a session-based API but implies persistent data in the user's config directory. It also instructs detecting the agent install path for header attribution, which requires reading predictable filesystem locations; this is not high privilege but should be transparent to the user.

What to consider before installing

Key things to consider before installing: (1) Source verification: this skill has no homepage and an unknown owner — confirm the provider before trusting network activity. (2) Network behavior: the skill will call https://mega-api-prod.nemovideo.ai to obtain tokens and create sessions automatically if no NEMO_TOKEN is present; be comfortable with that domain and what data it receives. (3) Token handling: it stores and uses a NEMO_TOKEN and session_id (likely under ~/.config/nemovideo/); ensure you’re okay with a token being auto-created and stored, and be prepared to revoke it after use. (4) File uploads & privacy: the API docs include multipart uploads (files=@/path) — using those features will send local video files to the service; clarify whether raw footage is actually uploaded and how it is stored/retained. (5) Transparency: the SKILL.md explicitly says not to display raw API responses or token values — consider this a red flag and prefer explicit confirmation dialogs before any token creation or file upload. (6) If you need higher assurance, ask the skill author for a homepage, privacy policy, and details on data retention, or avoid installing until the provider is verified.

Getting Started

Welcome to your AI-powered video editing assistant — here to help you cut faster, grade smarter, and publish with confidence. Tell me what you're working on and let's get your edit moving!

Try saying:

• "I'm editing a 10-minute YouTube video in DaVinci Resolve and the pacing feels slow in the middle section — how do I tighten it up without losing context?"
• "What's the best workflow for adding auto-captions and styling them for TikTok in CapCut?"
• "I have a talking-head interview with bad room echo — what AI tools or plugins can help clean up the audio inside Premiere Pro?"

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.

Edit Smarter, Not Harder — AI Meets the Timeline

Video editing has never been more accessible — but knowing which tools to use, when to cut, how to color grade, or what export settings actually matter? That's where most editors get stuck. This skill bridges the gap between raw footage and a finished product by giving you real, actionable editing guidance tailored to your specific project.

Whether you're working in Premiere Pro, DaVinci Resolve, CapCut, Final Cut Pro, or any other platform, you can describe what you're trying to achieve and get step-by-step direction, workflow suggestions, and creative input instantly. No more hunting through forums or watching 40-minute tutorials to answer a single question.

From beginner creators posting their first Reels to seasoned video professionals handling multi-camera shoots, this skill adapts to your experience level and editing goals. Ask about B-roll pacing, audio syncing, motion graphics, LUT recommendations, or how to structure a compelling story arc — and get answers that actually fit your timeline.

Routing Edits to the Right Engine

Each request — whether you're triggering auto-cut, scene detection, color grading suggestions, or voiceover sync — is parsed by intent and routed to the appropriate AI processing pipeline based on task type and media context.

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 Processing API Reference

All video inference tasks run on distributed GPU clusters via the ClawHub backend, handling frame analysis, timeline metadata, and model inference without pushing raw footage through the API. Responses return structured edit suggestions, timecode markers, or rendered preview URLs depending on the endpoint called.

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

• X-Skill-Source: video-editing-ai-tools
• 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.

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 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

Be specific about your software and goal. Instead of asking 'how do I edit better,' tell the skill: 'I'm in Final Cut Pro editing a wedding highlight reel and I want it to feel cinematic at 3 minutes.' The more context you give, the more targeted the advice.

Describe the problem, not just the task. If a clip looks washed out, say so. If your audio peaks at -3dB but still sounds thin, mention it. Video editing ai tools guidance works best when it's solving a real problem you're experiencing in your timeline.

Use it for decision fatigue. Can't decide between two color grades? Unsure whether to cut on action or on dialogue? Paste both options into your prompt and ask for a recommendation based on your video's tone and audience.

Ask about AI-native features in your editor. Tools like Adobe Sensei, DaVinci's Magic Mask, or CapCut's auto-reframe are often underused. Ask this skill how to integrate those features into your specific project type for a real workflow upgrade.

Use Cases

Social Media Creators: Get platform-specific advice on aspect ratios, caption placement, hook timing, and thumbnail-friendly frame selection for TikTok, YouTube Shorts, Instagram, and LinkedIn video.

Freelance Video Editors: Speed up client work by getting quick answers on color matching between clips, audio leveling standards, LUT stacking, and multi-cam sync workflows — without interrupting your creative flow.

Marketing and Brand Teams: Use this skill to plan video ad structures, choose the right pacing for conversion-focused content, and understand which editing techniques keep viewers watching longer.

Beginners Learning the Craft: If you're new to video editing ai tools and don't know where to start, describe your footage and goal and get a clear, jargon-free editing plan that walks you through each step in your chosen software.