Video Capcut

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

Security Scan

The skill mostly matches a cloud video-editing service (it legitimately needs a NEMO_TOKEN and network access), but there are unexplained metadata/instruction mismatches (a declared config path and an instruction to auto-detect install paths) and it will upload user videos to a third-party API — you should confirm privacy, token scope, and why the skill needs access to any config/install path before installing.

Purpose & Capability

The name/description (cloud AI video editing) aligns with the runtime instructions and required NEMO_TOKEN credential and the listed API endpoints. However the SKILL.md frontmatter lists a configPaths value (~/.config/nemovideo/) while the registry metadata reported no required config paths — this discrepancy is unexplained and worth asking the publisher about.

Instruction Scope

Instructions direct the agent to use NEMO_TOKEN or obtain an anonymous token and to upload user media to https://mega-api-prod.nemovideo.ai (expected for remote editing). But the skill also requires adding attribution headers that include an 'auto-detect' X-Skill-Platform value (which implies reading install path or environment to detect platform) and the metadata mentions a config path; the SKILL.md does not clearly justify reading local config/install locations. The instructions also explicitly tell the agent to hide technical details from the user, which reduces transparency. These points broaden the agent's read/sensing scope beyond simply sending files to the API.

Install Mechanism

No install spec and no code files — this is instruction-only, which is lower risk since nothing is downloaded or written by the skill itself. All runtime actions are network calls to the external API described in the doc.

Credentials

Requesting a single API credential (NEMO_TOKEN) is proportional for a cloud editing service. The unexplained inclusion of a config path (~/.config/nemovideo/) in the SKILL.md metadata is disproportionate unless the skill truly needs to read a local token or cached session — the registry listing did not declare any required config paths, so this is inconsistent and should be clarified.

Persistence & Privilege

The skill is not always-enabled and does not request elevated platform privileges. It appears to operate interactively and does not include instructions to modify other skills or global settings.

What to consider before installing

This skill will upload your videos and audio to an external service (mega-api-prod.nemovideo.ai) and requires an API token (NEMO_TOKEN) or will create a short-term anonymous token. Before installing: 1) Confirm the privacy policy and data retention rules of nemovideo.ai — any uploaded media will be sent off-device. 2) Verify where NEMO_TOKEN comes from and the token's permissions; prefer an account with minimal rights or an ephemeral anonymous token if you want limited exposure. 3) Ask the publisher to explain the config path (~/.config/nemovideo/) and the 'auto-detect X-Skill-Platform' behavior — clarify whether the skill will read local files or the install path. 4) If you cannot verify those points or you need strict data control, do not enable the skill for sensitive content. 5) Because this is instruction-only, there is no local install, but you should monitor network calls and token usage (rotate/delete tokens if you stop using the skill).

Getting Started

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

Try saying:

• "edit a 60-second vertical phone recording into a 1080p MP4"
• "trim the clip, add text overlays, and sync cuts to the beat"
• "editing short-form videos for TikTok and Reels for TikTok 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 CapCut — Edit and Export Video Clips

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

Say you have a 60-second vertical phone recording and want to trim the clip, add text overlays, and sync cuts to the beat — the backend processes it in about 30-60 seconds and hands you a 1080p MP4.

Tip: shorter clips under 60 seconds process significantly faster.

Matching Input to Actions

User prompts referencing video capcut, 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.

Base URL: https://mega-api-prod.nemovideo.ai

Endpoint	Method	Purpose
/api/tasks/me/with-session/nemo_agent	POST	Start a new editing session. Body: {"task_name":"project","language":"<lang>"}. Returns session_id.
/run_sse	POST	Send a user message. Body includes app_name, session_id, new_message. Stream response with Accept: text/event-stream. Timeout: 15 min.
/api/upload-video/nemo_agent/me/<sid>	POST	Upload a file (multipart) or URL.
/api/credits/balance/simple	GET	Check remaining credits (available, frozen, total).
/api/state/nemo_agent/me/<sid>/latest	GET	Fetch current timeline state (draft, video_infos, generated_media).
/api/render/proxy/lambda	POST	Start export. Body: {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll status every 30s.

Accepted file types: 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-capcut
X-Skill-Version	frontmatter version
X-Skill-Platform	auto-detect: clawhub / cursor / unknown from install path

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.

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

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)

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "trim the clip, add text overlays, and sync cuts to the beat" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across social platforms.

Common Workflows

Quick edit: Upload → "trim the clip, add text overlays, and sync cuts to the beat" → Download MP4. Takes 30-60 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.