Video Low

Turn a 2-minute 1080p interview recording into 720p compressed video files just by typing what you need. Whether it's reducing video file size for sharing or...

Security Scan

The skill's declared purpose (cloud video compression) lines up with its instructions, but there are notable inconsistencies about required credentials and config paths and it will upload your media to an external service — verify before use.

Purpose & Capability

Name/description match the runtime instructions: the skill routes uploads and render requests to a cloud video backend (nemovideo.ai). Requiring a NEMO_TOKEN and a session_id for cloud operations is expected for this purpose.

Instruction Scope

Instructions stay within the video-compression domain (create session, upload files, SSE for edits, export/poll for download). They also instruct the agent to check env for NEMO_TOKEN, or else obtain an anonymous token from the service; to add attribution headers derived from the file frontmatter and detect install path for X-Skill-Platform. These behaviors are relevant to the API but grant the skill the ability to: (a) contact an external service and upload user files, and (b) introspect install path metadata for headers. The instructions explicitly say not to expose tokens to users, but they do cause network activity and token acquisition on behalf of the user — that is expected for a cloud-based exporter but worth noting.

Install Mechanism

Instruction-only skill with no install steps or downloads. No code files and no packages are installed by the skill itself, minimizing disk-write risk.

Credentials

Registry metadata lists NEMO_TOKEN as required/primary, but the SKILL.md instructs the agent to obtain an anonymous NEMO_TOKEN if none is present. Additionally, the SKILL.md metadata lists a config path (~/.config/nemovideo/) while the registry metadata earlier reported no required config paths. These mismatches (declared required env vs. runtime fallback behavior, and inconsistent config path reporting) are incoherent and should be clarified. Functionally, the only secret used is NEMO_TOKEN; that is proportional to the claimed cloud service, but be aware providing your own NEMO_TOKEN grants the skill bearer access to your account/credits.

Persistence & Privilege

always:false and no install-time persistence. The skill keeps ephemeral session_id and tokens to operate, but it does not request elevated system privileges or modify other skills. Autonomous invocation is allowed (platform default) but not combined with other high-risk flags.

What to consider before installing

This skill appears to do what it says (upload your video to a cloud backend, compress on GPUs, and return a download link), but consider the following before installing or using it: - Privacy: Your videos are uploaded to https://mega-api-prod.nemovideo.ai. If clips contain sensitive content, do not upload them until you verify the service's privacy/security practices. - Credentials: The skill declares NEMO_TOKEN as required but will also generate an anonymous token if none is present — clarify whether you must provide a token (and what account/credits it uses). If you supply your own NEMO_TOKEN, the skill can act on your account/credits. Treat that token like a password. - Metadata/headers: The skill constructs X-Skill-* attribution headers and may inspect install path metadata to populate them — that file/path detection is minor but is inconsistent with registry metadata and should be resolved. - Test safely: Try with non-sensitive short clips first to confirm behavior, quotas, and that downloads work as documented. - Verify origin: The skill has no homepage and the owner is an opaque ID. If you need stronger assurance, request the skill's source or a vendor privacy/security statement and confirm the API domain and endpoints are legitimate. If you want me to, I can: (1) highlight the exact lines in SKILL.md that conflict with the registry metadata, (2) suggest a minimal set of questions to ask the skill author, or (3) draft a short test prompt and non-sensitive test clip workflow you can run safely.

Getting Started

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

Try saying:

• "compress my video clips"
• "export 720p MP4"
• "reduce the file size of this"

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 Low — Compress and Reduce Video Size

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

Here's a typical use: you send a a 2-minute 1080p interview recording, ask for reduce the file size of this video without losing too much quality, and about 30-60 seconds later you've got a MP4 file ready to download. The whole thing runs at 720p by default.

One thing worth knowing — shorter clips compress faster and give more predictable output sizes.

Matching Input to Actions

User prompts referencing video low, 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.

All calls go to https://mega-api-prod.nemovideo.ai. The main endpoints:

1. Session — POST /api/tasks/me/with-session/nemo_agent with {"task_name":"project","language":"<lang>"}. Gives you a session_id.
2. Chat (SSE) — POST /run_sse with session_id and your message in new_message.parts[0].text. Set Accept: text/event-stream. Up to 15 min.
3. Upload — POST /api/upload-video/nemo_agent/me/<sid> — multipart file or JSON with URLs.
4. Credits — GET /api/credits/balance/simple — returns available, frozen, total.
5. State — GET /api/state/nemo_agent/me/<sid>/latest — current draft and media info.
6. Export — POST /api/render/proxy/lambda with render ID and draft JSON. Poll GET /api/render/proxy/lambda/<id> every 30s for completed status and download URL.

Formats: 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: video-low
• 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.

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)

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

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.

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 "reduce the file size of this video without losing too much quality" — concrete instructions get better results.

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

H.264 codec gives the best balance of quality and size.

Common Workflows

Quick edit: Upload → "reduce the file size of this video without losing too much quality" → 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.