Llm For Video Editing

Turn a 3-minute unedited interview recording into 1080p AI-edited videos just by typing what you need. Whether it's using natural language prompts to cut, tr...

Security Scan

The skill's requests and runtime instructions are consistent with a cloud-based video-editing integration: it needs a single NEMO_TOKEN, uploads user video files to an external rendering API, and has no install-time code—however it will transmit your videos and use an API token so treat uploaded footage and tokens as sensitive.

Purpose & Capability

Name and description match behaviour in SKILL.md: the skill routes uploads and edit requests to a remote nemovideo.ai rendering backend. The declared primary credential (NEMO_TOKEN) is appropriate for an API-driven service. Note: the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) while the registry metadata showed no required config paths — this is a minor metadata mismatch but consistent with a client that may also check local config.

Instruction Scope

Runtime instructions are scoped to starting sessions, uploading user-provided media, streaming SSE responses, polling render status, and exporting downloads. The skill explicitly posts files and metadata to nemovideo.ai endpoints and instructs reading its own frontmatter/install path to populate attribution headers. There are no instructions to read unrelated system files or secrets beyond NEMO_TOKEN.

Install Mechanism

Instruction-only skill with no install spec or downloaded code. This minimizes disk-write/remote-exec risk. All runtime actions are network calls to the documented API.

Credentials

Only one credential is required (NEMO_TOKEN), which is proportional to a cloud API. The SKILL.md also references a config path in its metadata (possible local config lookup) — acceptable but the registry metadata and SKILL.md disagree about config path requirements. Confirm whether the skill will read or write ~/.config/nemovideo/ if that matters for you.

Persistence & Privilege

Skill is not always-enabled and does not request elevated platform privileges. It may create ephemeral anonymous tokens via the API and keep session IDs in memory; there is no instruction to modify other skills or system-wide settings.

Assessment

This skill uploads whatever you send (video/audio) to nemovideo.ai and uses an API token (either one you provide as NEMO_TOKEN or a short-lived anonymous token it can obtain). Only upload footage you are comfortable sending to an external service. If privacy or billing matters, supply your own NEMO_TOKEN tied to an account you control rather than using anonymous tokens. Be aware of the minor metadata mismatch about a local config path (~/.config/nemovideo/) — ask the author whether the skill will read or write that directory if you are concerned about local files. Finally, review nemovideo.ai's privacy/retention policy before sending sensitive content.

Getting Started

Share your raw video footage and I'll get started on AI-assisted video editing. Or just tell me what you're thinking.

Try saying:

• "edit my raw video footage"
• "export 1080p MP4"
• "cut the filler words, add b-roll"

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.

LLM for Video Editing — Edit Videos With Text Prompts

Drop your raw video footage in the chat and tell me what you need. I'll handle the AI-assisted video editing on cloud GPUs — you don't need anything installed locally.

Here's a typical use: you send a a 3-minute unedited interview recording, ask for cut the filler words, add b-roll transitions, and write a short summary caption for each scene, and about 1-2 minutes later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — shorter, focused prompts like 'remove silences and add fade transitions' produce more accurate edits than vague requests.

Matching Input to Actions

User prompts referencing llm for video editing, 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.

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

• X-Skill-Source: llm-for-video-editing
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

Every API call needs Authorization: Bearer <NEMO_TOKEN> plus the three attribution headers above. If any header is missing, exports return 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.

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)

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "cut the filler words, add b-roll transitions, and write a short summary caption for each scene" — 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 the filler words, add b-roll transitions, and write a short summary caption for each scene" → 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.