Video Editing With Davinci

Turn a 3-minute DaVinci Resolve project export into 4K polished edited clips just by typing what you need. Whether it's editing and refining video timelines...

Security Scan

The skill's functionality (remote video editing) is plausible and mostly coherent, but there are small inconsistencies and scope-creep (filesystem checks, a declared required env var that can be auto-created, and unnecessary config path metadata) that merit caution before installing or using it with sensitive footage or credentials.

Purpose & Capability

The skill claims to perform cloud-based DaVinci-style editing and asks only for a single token (NEMO_TOKEN), which fits the purpose. However the metadata also declares a config path (~/.config/nemovideo/) that isn't needed for basic upload/edit/export flows, and the SKILL.md documents generating an anonymous token when NEMO_TOKEN is absent despite NEMO_TOKEN being listed as required — this is an inconsistency between declared requirements and runtime behavior.

Instruction Scope

Instructions direct the agent to upload user video files to a third-party API (mega-api-prod.nemovideo.ai), open SSE streams, poll session/state endpoints, and include Authorization headers. Additionally, the runtime instructions tell the agent to detect install path by reading local filesystem locations (~/.clawhub/, ~/.cursor/skills/) to set an X-Skill-Platform header and to read this skill's YAML frontmatter at runtime. Those filesystem checks are outside the core editing task and expand the scope of what the agent will read from the user's environment.

Install Mechanism

Instruction-only skill with no install steps and no code files — nothing will be written to disk by an installer. This is lower-risk for arbitrary code installation.

Credentials

Only one credential (NEMO_TOKEN) is declared as required, which is proportional for a cloud editing service. However the SKILL.md will request an anonymous token from the backend if NEMO_TOKEN is not present (implying it does not strictly require pre-provisioned credentials), and the metadata's requested config path could expose local config data unnecessarily. The skill will upload user media to a third-party domain — this is expected but has privacy implications.

Persistence & Privilege

The skill is not always-enabled and does not request elevated or persistent system privileges. It uses session tokens for operations but does not appear to modify other skills or system-wide configuration.

What to consider before installing

This skill appears to do what it says (remote GPU-based video editing) but has a few red flags you should consider before using it with real or sensitive footage: - It will upload your raw videos to a third-party service at mega-api-prod.nemovideo.ai. Confirm you trust that service and understand its privacy/retention policy before uploading private content. - The skill declares NEMO_TOKEN as required but will create an anonymous token if none is present — it will contact the backend even if you don't provide credentials. - The runtime instructions ask the agent to check local paths (~/.clawhub/, ~/.cursor/skills/) to set an attribution header. That filesystem probing is outside the core editing need and may reveal information about your local setup. Recommendations: - Try with non-sensitive test footage first. - Do not provide high-privilege secrets or unrelated environment variables. Only set NEMO_TOKEN if you understand where it came from and what permissions it grants. - If you need a formal assurance, ask the publisher for a privacy policy, an official homepage, and documentation about retention and who can access uploaded media. If those are absent or the service is unfamiliar, avoid uploading confidential content. What would change this assessment: presence of code files or a reputable homepage/docs for the backend (which would allow verification of endpoints), or removal/justification of the filesystem checks and metadata config path would move this toward benign confidence.

Getting Started

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

Try saying:

• "edit a 3-minute DaVinci Resolve project export into a 4K MP4"
• "cut dead air, add color grading, and sync background music to transitions"
• "editing and refining video timelines with DaVinci-style tools for video editors and content creators"

Quick Start Setup

This skill connects to a cloud processing backend. On first use, set up the connection automatically and let the user know ("Connecting...").

Token check: Look for NEMO_TOKEN in the environment. If found, skip to session creation. Otherwise:

• Generate a UUID as client identifier
• POST https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with X-Client-Id header
• Extract data.token from the response — this is your NEMO_TOKEN (100 free credits, 7-day expiry)

Session: POST https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Keep the returned session_id for all operations.

Let the user know with a brief "Ready!" when setup is complete. Don't expose tokens or raw API output.

Video Editing with DaVinci — Edit and Export Polished Videos

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

A quick example: upload a 3-minute DaVinci Resolve project export, type "cut dead air, add color grading, and sync background music to transitions", and you'll get a 4K MP4 back in roughly 1-2 minutes. All rendering happens server-side.

Worth noting: shorter clips under 2 minutes process significantly faster and give cleaner AI results.

Matching Input to Actions

User prompts referencing video editing with davinci, 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: video-editing-with-davinci
• 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.

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.

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 JSON uses short keys: t for tracks, tt for track type (0=video, 1=audio, 7=text), sg for segments, d for duration in ms, m for metadata.

Example timeline summary:

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

The backend processes faster when you're specific. Instead of "make it look better", try "cut dead air, add color grading, and sync background music to transitions" — concrete instructions get better results.

Max file size is 500MB. Stick to MP4, MOV, AVI, DRM 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 dead air, add color grading, and sync background music to transitions" → 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.