Free Rtk Compressor

Skip the learning curve of professional editing software. Describe what you want — compress this RTK video file to under 500MB without losing quality — and g...

Security Scan

The skill's high-level purpose (cloud video compression) matches its network calls, but there are inconsistencies between declared requirements and the runtime instructions (credential handling and config-path use) and some instructions ask the agent to read environment/install paths — raise caution before installing.

Purpose & Capability

The skill claims to compress/upload video via a cloud backend and all described API endpoints and actions align with that purpose. Requesting a NEMO_TOKEN to authenticate with the backend is appropriate. However, the frontmatter and registry metadata mismatch: the SKILL.md includes a configPaths entry (~/.config/nemovideo/) but the registry metadata earlier listed no required config paths; this inconsistency should be clarified.

Instruction Scope

Instructions are mainly limited to interacting with the remote nemovideo.ai API (session creation, SSE chat, upload, export) which is in-scope. They also instruct: (1) creating an anonymous token if NEMO_TOKEN isn't present, (2) including attribution headers and detecting the agent install path (~/.clawhub/, ~/.cursor/skills/) to set X-Skill-Platform, and (3) reading YAML frontmatter for version. Reading the agent install path and frontmatter is benign but expands scope beyond pure upload/encode actions and could reveal local environment details; the skill doesn't explicitly say whether it will persist tokens or write to ~/.config/nemovideo/.

Install Mechanism

This is an instruction-only skill with no install spec or added binaries, so there is no download/extract risk. That lowers disk-write and supply-chain risk.

Credentials

The registry lists NEMO_TOKEN as a required env var and the frontmatter marks it as primaryEnv, which is proportional for a cloud video service. However, SKILL.md also instructs the agent to automatically request an anonymous token if NEMO_TOKEN is not found (and the frontmatter includes a configPaths entry). This is a mismatch: the skill both requires an env var and contains logic to generate one. It's unclear whether the generated anonymous token is stored locally (e.g., under ~/.config/nemovideo/) or kept only in memory; persistent storage would increase risk. Also the skill will read install paths to set attribution headers — that reveals filesystem layout.

Persistence & Privilege

always is false and the skill does not request elevated persistent privileges. However, the presence of configPaths in the frontmatter suggests it may write/read under ~/.config/nemovideo/ (not declared elsewhere); clarify whether the skill will store tokens or state on disk. Autonomous invocation is allowed (normal) and not a standalone concern here.

What to consider before installing

This skill appears to do what it says (upload video to a cloud compressor) but has a few inconsistencies you should clear up before installing: 1) The registry declares NEMO_TOKEN as required, but the instructions also generate an anonymous NEMO_TOKEN if none is present — ask whether the skill will persist that token to disk (e.g., ~/.config/nemovideo/) or keep it only in memory. Persistent storage would increase risk. 2) The skill will read the agent's install path and YAML frontmatter to set X-Skill-Platform/version headers — this reveals some local environment details; confirm exactly which paths are read. 3) All uploads go to a third-party domain (mega-api-prod.nemovideo.ai); verify you trust that service and its privacy policy because uploaded video content may include sensitive data. Recommendations before use: do not set any high-privilege credentials as NEMO_TOKEN, test the skill in a sandboxed environment with non-sensitive videos first, ask the author to clarify the configPath usage and token persistence behavior, and if possible review network traffic or logs to confirm tokens are not exfiltrated to unexpected endpoints. If the author confirms no tokens are stored on disk and configPaths are unused, and the only credential is a limited anonymous token, the inconsistencies become less concerning.

Getting Started

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

Try saying:

• "compress my raw 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.

Free RTK Compressor — Compress and Export RTK Videos

This tool takes your raw 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 2GB MP4 gameplay recording and want to compress this RTK video file to under 500MB without losing quality — the backend processes it in about 1-3 minutes and hands you a 1080p MP4.

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

Matching Input to Actions

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

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

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)

Backend Response Translation

The backend assumes a GUI exists. Translate these into API actions:

Backend says	You do
"click [button]" / "点击"	Execute via API
"open [panel]" / "打开"	Query session state
"drag/drop" / "拖拽"	Send edit via SSE
"preview in timeline"	Show track summary
"Export button" / "导出"	Execute export workflow

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.

Error Handling

Code	Meaning	Action
0	Success	Continue
1001	Bad/expired token	Re-auth via anonymous-token (tokens expire after 7 days)
1002	Session not found	New session §3.0
2001	No credits	Anonymous: show registration URL with ?bind=<id> (get <id> from create-session or state response when needed). Registered: "Top up credits in your account"
4001	Unsupported file	Show supported formats
4002	File too large	Suggest compress/trim
400	Missing X-Client-Id	Generate Client-Id and retry (see §1)
402	Free plan export blocked	Subscription tier issue, NOT credits. "Register or upgrade your plan to unlock export."
429	Rate limit (1 token/client/7 days)	Retry in 30s once

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "compress this RTK video file to under 500MB without losing quality" — concrete instructions get better results.

Max file size is 2GB. 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 under 500MB without losing quality" → Download MP4. Takes 1-3 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.