Video Cli

Turn a 2-minute MP4 screen recording into 1080p edited video clips just by typing what you need. Whether it's running video edits via command-line commands o...

Security Scan

The skill's instructions and requirements are internally consistent with a cloud-based video editing service, with only minor documentation/inventory inconsistencies to be aware of.

Purpose & Capability

The skill claims to perform cloud-based video editing and its runtime instructions exclusively call a remote NemoVideo API for uploads, SSE editing, rendering and status—these are appropriate and expected for the stated purpose. The single declared credential (NEMO_TOKEN) is consistent with a remote API token requirement.

Instruction Scope

Instructions ask the agent to upload user-provided video files and interact with the remote rendering API via authenticated requests and SSE streams—which fits the purpose. The doc also instructs detecting the 'install path' to set an X-Skill-Platform header; that implies reading agent install-path information (filesystem/environment) for attribution, which is reasonable but outside pure video-editing logic and could leak environment info if you care about that.

Install Mechanism

No install steps or third-party downloads are specified (instruction-only skill). This minimizes on-disk risk.

Credentials

Only one credential (NEMO_TOKEN) is required, which is proportional. Minor inconsistency: the SKILL.md explains it will auto-provision an anonymous token by POSTing to the provider if NEMO_TOKEN is absent, so requiring the env var is not strictly mandatory in practice. The frontmatter in SKILL.md also references a config path (~/.config/nemovideo/) not declared in the registry metadata—this mismatch is likely a documentation/packaging oversight.

Persistence & Privilege

The skill does not request always:true or agent-global privileges, does not modify other skills, and only maintains per-session IDs for the remote service as part of normal operation.

Assessment

This skill sends any uploaded video and edit commands to a remote nemo video API and requires a NEMO_TOKEN (it can also request an anonymous token on first use). Before installing, consider: 1) Privacy: uploaded videos go to the provider—don't upload sensitive content unless you trust their policy. 2) Tokens: the skill will accept a provided NEMO_TOKEN or obtain a short-lived anonymous token (100 free credits, 7-day expiry) by calling the provider; if you prefer control, supply your own token. 3) Attribution headers: the skill will derive platform info from install paths (it may read path info for X-Skill-Platform). 4) Metadata mismatches: SKILL.md references a config path that the registry metadata does not list—this appears to be a packaging/documentation inconsistency but not by itself dangerous. If you need stronger assurance, ask the publisher for a provenance URL or privacy/terms link and avoid uploading sensitive videos until you verify the service and its data-retention policy.

Getting Started

Ready when you are. Drop your video clips here or describe what you want to make.

Try saying:

• "edit a 2-minute MP4 screen recording into a 1080p MP4"
• "trim the first 10 seconds, add a fade-in, and export at 1080p"
• "running video edits via command-line commands for developers and power users"

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.

Video CLI — Edit and Export Videos via CLI

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

Here's a typical use: you send a a 2-minute MP4 screen recording, ask for trim the first 10 seconds, add a fade-in, and export at 1080p, and about 20-40 seconds later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — shorter clips process faster and reduce command wait time.

Matching Input to Actions

User prompts referencing video cli, 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 video-cli, 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).

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.

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 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)

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 first 10 seconds, add a fade-in, and export at 1080p" → Download MP4. Takes 20-40 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "trim the first 10 seconds, add a fade-in, and export at 1080p" — 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.