Trimmer Linux

Turn a 10-minute screen recording from a Linux session into 1080p trimmed video clips just by typing what you need. Whether it's trimming and cutting video f...

Security Scan

The skill's stated purpose (cloud video trimming) is plausible and most requirements match that purpose, but there are inconsistencies and instructions that ask the agent to probe the user's filesystem and supply attribution headers that are unnecessary for basic operation — these are scope and packaging concerns you should understand before installing.

Purpose & Capability

The skill claims to perform cloud-based video trimming and its network endpoints, auth flow, and file upload instructions align with that purpose. Requesting a NEMO_TOKEN (or creating an anonymous token) is proportionate for a cloud service. However, the frontmatter embedded in SKILL.md also lists configPaths ("~/.config/nemovideo/") even though the registry metadata earlier reported no required config paths — this mismatch suggests sloppy packaging or undocumented filesystem access.

Instruction Scope

The runtime instructions explicitly tell the agent to: generate tokens, POST uploads and SSE messages to an external API (expected), and also to read this file's YAML frontmatter and detect install path strings (e.g., checking ~/.clawhub/ or ~/.cursor/skills/) to set an X-Skill-Platform header. Detecting install path implies probing user filesystem locations, which is not necessary to trim videos and expands the skill's scope into user-host environment inspection. The instructions also require storing session_id and using attribution headers on every API call; both are operationally plausible but the install-path detection is unnecessary and privacy-sensitive.

Install Mechanism

There is no install spec and no code files — the skill is instruction-only. That minimizes supply-chain risk because nothing is downloaded or written by an installer. Network calls to the service are the main runtime surface.

Credentials

The only declared required env var is NEMO_TOKEN (primary credential), which is appropriate for a cloud video service. The instructions further provide an anonymous-token fallback (requests a UUID and exchanges it at the service) so a pre-set NEMO_TOKEN is optional. That is sensible, but you should treat any token (anonymous or not) as allowing uploads of your videos to a third-party; confirm the token's scope, retention, and privacy rules before use. Also note the SKILL.md metadata lists a config path that was not declared in the registry metadata — another inconsistency.

Persistence & Privilege

The skill does not request 'always: true' and is user-invocable only. It instructs the agent to create and save a session_id for a short-lived editing session (expected). There is no request to modify other skills or global agent settings. The main privilege is network access to upload potentially sensitive video files to the external API.

What to consider before installing

This skill generally behaves like a normal cloud-based video editor: it uploads files to mega-api-prod.nemovideo.ai and uses a NEMO_TOKEN (or an anonymous token it can generate) to authenticate. Before installing: (1) Confirm you trust the nemovideo.ai domain and review its privacy/retention policy for uploaded videos; (2) avoid supplying a privileged/production token — use an anonymous or limited token for testing; (3) be aware the skill's instructions ask the agent to detect install paths on your system (e.g., ~/.clawhub/, ~/.cursor/skills/) and to read the SKILL.md frontmatter — this filesystem probing is unnecessary for trimming and may leak information about your environment; (4) the SKILL.md lists a config path (~/.config/nemovideo/) even though registry metadata did not — ask the publisher why and whether the skill will access that directory; (5) test first with non-sensitive, short sample videos to confirm exactly what is uploaded and returned. If you are uncomfortable with filesystem probing or uploading sensitive recordings, do not enable the skill until the developer clarifies these points.

Getting Started

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

Try saying:

• "trim a 10-minute screen recording from a Linux session into a 1080p MP4"
• "trim the first 30 seconds and cut out the pauses in the middle"
• "trimming and cutting video files on Linux systems for Linux users and developers"

Automatic Setup

On first interaction, connect to the processing API before doing anything else. Show a brief status like "Setting things up...".

Token: If NEMO_TOKEN environment variable is already set, use it and skip to Session below.

Free token: Generate a UUID as client identifier, then POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id: <uuid>. The response field data.token becomes your NEMO_TOKEN (100 credits, 7-day expiry).

Session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Save session_id from the response.

Confirm to the user you're connected and ready. Don't print tokens or raw JSON.

Trimmer for Linux — Trim and Export Video Clips

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

Here's a typical use: you send a a 10-minute screen recording from a Linux session, ask for trim the first 30 seconds and cut out the pauses in the middle, 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 — browser-based trimming means no installation needed — works on any Linux distro.

Matching Input to Actions

User prompts referencing trimmer 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.

Base URL: https://mega-api-prod.nemovideo.ai

Endpoint	Method	Purpose
/api/tasks/me/with-session/nemo_agent	POST	Start a new editing session. Body: {"task_name":"project","language":"<lang>"}. Returns session_id.
/run_sse	POST	Send a user message. Body includes app_name, session_id, new_message. Stream response with Accept: text/event-stream. Timeout: 15 min.
/api/upload-video/nemo_agent/me/<sid>	POST	Upload a file (multipart) or URL.
/api/credits/balance/simple	GET	Check remaining credits (available, frozen, total).
/api/state/nemo_agent/me/<sid>/latest	GET	Fetch current timeline state (draft, video_infos, generated_media).
/api/render/proxy/lambda	POST	Start export. Body: {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll status every 30s.

Accepted file types: 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: trimmer-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.

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

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 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)

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "trim the first 30 seconds and cut out the pauses in the middle" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across Linux media players and platforms.

Common Workflows

Quick edit: Upload → "trim the first 30 seconds and cut out the pauses in the middle" → 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.