Video Editing With Claude Code

Get code-edited videos ready to post, without touching a single slider. Upload your raw video footage (MP4, MOV, AVI, WebM, up to 500MB), say something like...

Security Scan

The skill's declared requirements and runtime instructions are generally consistent with a cloud-based video-editing service: it only needs a single NEMO_TOKEN and makes API calls to a remote rendering backend; no local installs or extra credentials are requested — but there are small metadata inconsistencies and an external API you should verify before uploading sensitive footage.

Purpose & Capability

Name/description (automated, server-side video editing) matches what the instructions do: upload video, create a session, run edits server-side, and return a rendered video. The only declared credential is NEMO_TOKEN, which is appropriate for a hosted service.

Instruction Scope

Runtime instructions are focused on the editing workflow (session creation, SSE chat, upload, render/export polling). They instruct generating an anonymous token if NEMO_TOKEN is absent and to hide technical details from the chat. Minor practicality concern: instructions require an X-Skill-Platform header 'auto-detect: from install path' — in an instruction-only skill there may be no reliable install path to auto-detect, so header population could be unclear or incorrectly implemented.

Install Mechanism

No install spec and no code files (instruction-only). This is the lowest install risk: nothing is downloaded or written by the skill itself.

Credentials

The skill only requires a single service token (NEMO_TOKEN) which is proportionate. However, the SKILL.md frontmatter also lists a config path (~/.config/nemovideo/) while the registry metadata showed no required config paths — this mismatch should be clarified (does the skill read local config files?). Aside from that, no unrelated credentials are requested.

Persistence & Privilege

always:false and no install-time persistence. The skill does not request system-wide privileges or to modify other skills. Normal autonomous invocation behavior is allowed (disable-model-invocation:false), which is expected for an agent skill.

Assessment

This skill appears coherent for a cloud video-editing service, but take these precautions before installing or using it: - Verify the backend domain (mega-api-prod.nemovideo.ai) and service legitimacy (homepage, privacy policy, or vendor) before uploading private footage. If you can't verify the provider, avoid sending sensitive videos. - NEMO_TOKEN is the only secret requested. Do not reuse sensitive tokens from other services as NEMO_TOKEN. If you don't have one, the skill will request an anonymous token from the API — that is expected behavior. - Clarify the config-path mismatch: SKILL.md frontmatter mentions ~/.config/nemovideo/ while registry metadata did not. Ask whether the skill will read local config files or write anything under that path. - The skill requires custom attribution headers on every request; ensure your agent/platform populates those correctly and that no other secrets are accidentally included in headers or logs. - If you proceed, test first with non-sensitive, short clips to validate behavior and download links, and monitor network traffic or audit logs where possible. If you want, I can draft the specific questions to ask the skill author (e.g., about config path usage, data retention, and token lifecycle) or produce a short checklist to validate the backend before trusting it with sensitive media.

Getting Started

Got raw video footage to work with? Send it over and tell me what you need — I'll take care of the AI-assisted code editing.

Try saying:

• "edit a 2-minute screen recording or phone clip into a 1080p MP4"
• "write a Claude script to trim silences, add text overlays, and export as MP4"
• "automating video edits using Claude-generated code scripts for developers and tech-savvy creators"

Getting Connected

Before handling any user request, establish a connection to the backend API. Show a brief status like "Connecting...".

If NEMO_TOKEN is in the environment, use it directly and create a session. Otherwise, acquire a free starter token:

• Generate a UUID as client identifier
• POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with the X-Client-Id header
• The response includes a token with 100 free credits valid for 7 days — use it as NEMO_TOKEN

Then create a session by POSTing to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer authorization and body {"task_name":"project","language":"en"}. The session_id in the response is needed for all following requests.

Tell the user you're ready. Keep the technical details out of the chat.

Video Editing with Claude Code — Automate and Export Edited Videos

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

A quick example: upload a 2-minute screen recording or phone clip, type "write a Claude script to trim silences, add text overlays, and export as MP4", and you'll get a 1080p MP4 back in roughly 1-2 minutes. All rendering happens server-side.

Worth noting: shorter clips under 60 seconds let Claude iterate and refine the edit script faster.

Matching Input to Actions

User prompts referencing video editing with claude code, 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.

Three attribution headers are required on every request and must match this file's frontmatter:

Header	Value
X-Skill-Source	video-editing-with-claude-code
X-Skill-Version	frontmatter version
X-Skill-Platform	auto-detect: clawhub / cursor / unknown from install path

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

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)

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

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 "write a Claude script to trim silences, add text overlays, and export as 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 playback compatibility.

Common Workflows

Quick edit: Upload → "write a Claude script to trim silences, add text overlays, and export as MP4" → 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.