Ai Video Editor Long Form

Turn a 45-minute interview recording into 1080p polished long-form video just by typing what you need. Whether it's editing long recordings like interviews,...

Security Scan

The skill's actions (uploading footage to a nemo video backend and using a NEMO_TOKEN) are consistent with its stated purpose; there is a small metadata inconsistency to check but nothing that obviously deviates from the described video-editing functionality.

Purpose & Capability

Name and description describe cloud-based long-form video editing and the skill only requires a NEMO_TOKEN and talks to nemovideo.ai endpoints for session creation, upload, SSE editing, and export — this is coherent with the stated purpose.

Instruction Scope

Runtime instructions direct the agent to check for NEMO_TOKEN (or obtain an anonymous token via an API call), create a session, upload user video files, drive edits via SSE, and poll/export results. These actions are within the editing scope, but the instructions also reference reading install/config paths (e.g., to derive X-Skill-Platform and a frontmatter configPaths entry ~/.config/nemovideo/) which implies touching user home config paths; that's reasonable for attribution but worth noting.

Install Mechanism

No install spec or code files are included (instruction-only), so nothing is written to disk by an installer. This is the lowest-risk install model.

Credentials

The skill only requires one credential, NEMO_TOKEN, which is proportionate for a cloud service that requires an API token. However, the SKILL.md frontmatter references a config path (~/.config/nemovideo/) that suggests the skill may look for stored config/credentials there; the registry metadata provided earlier listed no required config paths, so there is a minor inconsistency to verify.

Persistence & Privilege

The skill does not request always:true and does not ask to modify other skills or global agent settings. Autonomous invocation is allowed (default) but not in itself a problem here.

Assessment

This skill uploads your video files to mega-api-prod.nemovideo.ai and uses a NEMO_TOKEN (or will request an anonymous token if none is present). Before installing or using it: 1) Confirm you trust nemovideo.ai to process and store your footage (privacy, retention, and terms). 2) Decide whether you want the skill to obtain/store an anonymous token automatically (it creates a token via an API call if NEMO_TOKEN is absent). 3) Check the small metadata mismatch: SKILL.md frontmatter references ~/.config/nemovideo/ while the registry metadata showed no required config paths — if you care about what local files the skill reads, ask the publisher or inspect the environment where the skill runs. 4) Avoid sending sensitive PII or confidential footage until you verify the service's policies. If you want higher assurance, request publisher identity/homepage or an explicit privacy/billing statement for the nemovideo.ai backend before use.

Getting Started

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

Try saying:

• "edit a 45-minute interview recording into a 1080p MP4"
• "cut the filler words, add chapter titles, and smooth the transitions throughout"
• "editing long recordings like interviews, webinars, or documentaries into clean final cuts for YouTubers, podcasters, documentary 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.

AI Video Editor Long Form — Edit and Export Long Videos

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

Here's a typical use: you send a a 45-minute interview recording, ask for cut the filler words, add chapter titles, and smooth the transitions throughout, and about 2-4 minutes later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — splitting very long videos into segments before uploading can speed up processing significantly.

Matching Input to Actions

User prompts referencing ai video editor long form, 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.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is ai-video-editor-long-form, X-Skill-Version comes from the version field, and X-Skill-Platform is detected from the install path (~/.clawhub/ = clawhub, ~/.cursor/skills/ = cursor, otherwise 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.

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)

Error Codes

• 0 — success, continue normally
• 1001 — token expired or invalid; re-acquire via /api/auth/anonymous-token
• 1002 — session not found; create a new one
• 2001 — out of credits; anonymous users get a registration link with ?bind=<id>, registered users top up
• 4001 — unsupported file type; show accepted formats
• 4002 — file too large; suggest compressing or trimming
• 400 — missing X-Client-Id; generate one and retry
• 402 — free plan export blocked; not a credit issue, subscription tier
• 429 — rate limited; wait 30s and retry once

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "cut the filler words, add chapter titles, and smooth the transitions throughout" — concrete instructions get better results.

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

Export as MP4 with H.264 codec for the best balance of quality and file size across platforms.

Common Workflows

Quick edit: Upload → "cut the filler words, add chapter titles, and smooth the transitions throughout" → Download MP4. Takes 2-4 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.