Rtk Compressor Online

Turn a 500MB MP4 recording from a dashcam or drone into 1080p compressed MP4 files just by typing what you need. Whether it's reducing large RTK or drone vid...

Security Scan

The skill's declared purpose (cloud video compression) mostly matches the actions it instructs, but there are small inconsistencies and privacy surface concerns (reading install paths, frontmatter vs registry mismatch, automatic anonymous-token acquisition) that you should understand before installing.

Purpose & Capability

Name/description align with a cloud video-compression service and the skill only asks for a single service credential (NEMO_TOKEN) used to call nemovideo.ai endpoints — that is proportionate. However, the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) while the registry metadata listed no required config paths, which is an inconsistency.

Instruction Scope

Instructions direct the agent to upload local video files (multipart file POSTs), create sessions, stream SSEs, poll renders, and include attribution headers. Uploading files is expected for this purpose, but the skill also instructs the agent to detect install paths (~/.clawhub/, ~/.cursor/skills/) and to read this file's YAML frontmatter at runtime — actions that touch user filesystem metadata and could reveal presence of other tools. The skill will also generate an anonymous token by POSTing to the backend if NEMO_TOKEN is absent; this automatically grants the backend a token tied to the agent. These behaviors are plausible for the stated purpose but increase privacy/telemetry surface and should be understood.

Install Mechanism

Instruction-only skill with no install spec and no code files — low risk from install artifacts. Nothing is downloaded or written by an installer step.

Credentials

Only NEMO_TOKEN is requested as a primary credential, which is appropriate for a hosted compression service. But the SKILL.md also describes creating and using an anonymous token when NEMO_TOKEN is missing (calling an external endpoint to obtain a token), and the frontmatter mentions a config path not declared elsewhere — these are mismatches the user should be aware of. No unrelated credentials are requested.

Persistence & Privilege

always:false and no install steps — the skill does not request permanent presence or system-level changes. It does ask the agent to remember session_id during a run, which is normal for session-based APIs.

What to consider before installing

This skill appears to do what it says (upload a video to nemovideo.ai, request a render, and return a download link), but review these points before installing or using it: - Privacy: uploaded videos are sent to mega-api-prod.nemovideo.ai. Only upload content you are comfortable sharing with that service. - Token behavior: the skill expects a NEMO_TOKEN; if none is present it will call the anonymous-token endpoint to obtain a token for you. That implies the backend will receive an agent-scoped token (100 free credits / 7-day expiry). If you prefer control, provide your own token instead of relying on auto-generation. - Filesystem checks: the runtime instructions say to detect install paths (~/.clawhub, ~/.cursor) and reference a config directory (~/.config/nemovideo/). If you are concerned about revealing which tools or config exist on your machine, avoid giving the agent access to your home directory or run in an isolated environment. - Inconsistency: registry metadata and the SKILL.md frontmatter disagree about required config paths. That could be an oversight, but you may want to ask the publisher to clarify. If you proceed, only share files you control, consider supplying your own NEMO_TOKEN, and use an isolated environment (or limit the agent's filesystem access) if you have privacy concerns.

Getting Started

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

Try saying:

• "compress my video files"
• "export 1080p MP4"
• "compress this RTK video file to"

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.

RTK Compressor Online — Compress RTK Videos to MP4

This tool takes your video files and runs AI video compression through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a 500MB MP4 recording from a dashcam or drone and want to compress this RTK video file to reduce size without losing quality — the backend processes it in about 30-90 seconds and hands you a 1080p MP4.

Tip: shorter clips compress faster — split long recordings before uploading.

Matching Input to Actions

User prompts referencing rtk compressor online, 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.

Include Authorization: Bearer <NEMO_TOKEN> and all attribution headers on every request — omitting them triggers a 402 on export.

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

• X-Skill-Source: rtk-compressor-online
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

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.

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

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.

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)

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "compress this RTK video file to reduce size without losing quality" — concrete instructions get better results.

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

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

Common Workflows

Quick edit: Upload → "compress this RTK video file to reduce size without losing quality" → Download MP4. Takes 30-90 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.