Video Editing With Linux

edit raw video clips into edited MP4 clips with this skill. Works with MP4, MKV, AVI, WebM files up to 500MB. Linux users and open-source enthusiasts use it...

Security Scan

The skill's functionality (editing videos via a remote API) broadly matches its description, but there are inconsistencies in declared requirements and instructions that warrant caution before installing or using it.

Purpose & Capability

The skill's stated purpose (cloud video editing) aligns with the API endpoints and workflows described in SKILL.md. However, the registry metadata lists NEMO_TOKEN as a required environment variable and 'Required config paths: none', while the SKILL.md frontmatter and runtime instructions both reference configPaths (~/.config/nemovideo/) and also include logic to auto-generate a token if NEMO_TOKEN is not present. That mismatch (required env var vs. ability to obtain an anonymous token) is inconsistent and unexplained.

Instruction Scope

Instructions are largely limited to calls against the stated backend (mega-api-prod.nemovideo.ai) and describe expected APIs for session creation, SSE, upload, export, and polling. Concerns: (1) the skill instructs the agent to detect install path (e.g. ~/.clawhub, ~/.cursor/skills) to set X-Skill-Platform — this requires reading filesystem paths and is unrelated to core editing capability; (2) upload instructions include sending local file paths (multipart -F "files=@/path"), which is reasonable for uploads but implies the agent will access local files; (3) SKILL.md tells the agent to 'store the returned session_id for all subsequent requests' but doesn't specify where/how (ephemeral vs persistent). These behaviors expand the agent's access surface and should be clarified.

Install Mechanism

This is an instruction-only skill with no install spec and no code files. That minimizes installer risk (nothing is downloaded or written by an installer).

Credentials

Only one credential is declared (NEMO_TOKEN) and the APIs described legitimately require a bearer token. However, two issues: the registry declares NEMO_TOKEN required while the SKILL.md provides a flow to obtain an anonymous token automatically (making an env var optional in practice), and the SKILL.md frontmatter references a config path (~/.config/nemovideo/) not declared in the registry. Both are inconsistencies that affect how credential handling actually works. Confirm whether you must provide your own token or if the skill will auto-create/use anonymous tokens.

Persistence & Privilege

The skill does not request 'always: true' and has no install-time hooks. It does instruct the agent to keep session_id and tokens for the session; that is normal for an online editing workflow. There is no explicit instruction to modify other skills or system-wide config.

What to consider before installing

Before installing or invoking this skill: (1) Confirm the publisher and investigate the endpoint domain (mega-api-prod.nemovideo.ai) — only proceed if you trust that service. (2) Decide whether you want the skill to auto-create anonymous tokens (SKILL.md flow) or to require you to provide a NEMO_TOKEN; the registry and SKILL.md disagree. If you prefer explicit consent, do not put a long-lived token in your environment; use a disposable token. (3) Understand that the agent will upload your video files to a third-party service — do not send sensitive or private videos unless you accept that remote processing and storage. (4) Ask the publisher to clarify where session_id and any obtained tokens are stored and whether they persist beyond the browser session. (5) The skill attempts to detect install paths for attribution headers (reading ~/.clawhub, ~/.cursor/skills); if you are uncomfortable with filesystem probing, request that header be omitted or changed to a static value. (6) Because this is instruction-only with no source code provided, request source or further documentation if you need stronger assurance. If anything above is unclear or you cannot verify the backend/operator, treat this skill with caution.

Getting Started

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

Try saying:

• "edit my raw video clips"
• "export 1080p MP4"
• "trim the silent sections, add transitions,"

First-Time Connection

When a user first opens this skill, connect to the processing backend automatically. Briefly let them know (e.g. "Setting up...").

Authentication: Check if NEMO_TOKEN is set in the environment. If it is, skip to step 2.

1. Obtain a free token: Generate a random UUID as client identifier. POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id set to that UUID. The response data.token is your NEMO_TOKEN — 100 free credits, valid 7 days.
2. Create a session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Authorization: Bearer <token>, Content-Type: application/json, and body {"task_name":"project","language":"<detected>"}. Store the returned session_id for all subsequent requests.

Keep setup communication brief. Don't display raw API responses or token values to the user.

Video Editing with Linux — Edit and Export Videos Online

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

Here's a typical use: you send a a 2-minute screen recording made on Ubuntu, ask for trim the silent sections, add transitions, and export as MP4, 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 — since it runs in the browser, no Linux-specific software installation is needed.

Matching Input to Actions

User prompts referencing video editing with linux, 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-linux
• 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.

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 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

Common Workflows

Quick edit: Upload → "trim the silent sections, add transitions, 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "trim the silent sections, add transitions, and export as MP4" — concrete instructions get better results.

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

MP4 with H.264 codec gives the best compatibility across Linux media players.