Video Cutter

trim video clips into trimmed video clips with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. content creators use it for cutting long videos...

Security Scan

The skill's functionality (uploading and cutting videos via a remote Nemovideo API) is coherent, but there are several mismatches and privacy/operational concerns you should understand before installing.

Purpose & Capability

The skill's name/description align with making API calls to a video-processing backend and therefore needing a NEMO_TOKEN. However the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) while the registry metadata lists no required config paths — this inconsistency in declared resource requirements is unexplained.

Instruction Scope

The runtime instructions direct the agent to: automatically obtain an anonymous token if none is present, create and store sessions, upload user files (multipart uploads or URLs), poll render jobs, and derive headers including a platform value by checking install paths (e.g., ~/.clawhub or ~/.cursor/skills/). Uploading user videos to an external service and auto-generating/storing auth tokens are expected for this type of skill but are privacy-sensitive. The SKILL.md explicitly instructs not to display raw API responses or token values, which reduces transparency and could hide sensitive actions. The instructions also mention writing/using a config path (in frontmatter) but don't specify where or how tokens/session IDs are persisted.

Install Mechanism

No install spec and no code files — this is an instruction-only skill. That is lower-risk from an installation/execution standpoint because nothing new is written to disk by an installer. The primary runtime risk is network activity described in SKILL.md, not a downloaded executable.

Credentials

Only one credential is requested (NEMO_TOKEN), which is proportionate for a third-party video processing API. However the skill proactively offers to obtain an anonymous token itself and instructs storing it; combined with the earlier mismatch about configPaths and the lack of a homepage/owner transparency, this raises questions about token storage duration, where tokens/session IDs are saved, and who can access them. The skill will send user files to an external domain (mega-api-prod.nemovideo.ai) — consider whether that is acceptable for your content.

Persistence & Privilege

The skill does not request 'always: true' and uses normal autonomous invocation. It does instruct creating a session_id and implies storing it (and possibly tokens) in a config location; but it does not request system-wide configuration changes or access to other skills' creds. Because autonomous invocation is allowed (platform default), the combination of automatic token acquisition + silent storage + external uploads increases the importance of verifying token handling and data retention policies.

What to consider before installing

Before installing or using this skill, consider the following: - This skill uploads your video files to an external service (mega-api-prod.nemovideo.ai). Do not upload sensitive or private footage unless you trust that service and understand its retention/deletion and privacy policies. - The SKILL.md will auto-generate and store an anonymous token if NEMO_TOKEN isn't provided. Ask where tokens and session IDs are written (the frontmatter references ~/.config/nemovideo/) and how long they persist; prefer manual provisioning of credentials if you want control. - There is an inconsistency: the registry metadata shows no required config paths but the SKILL.md frontmatter references a config directory. Ask the author to clarify what, if anything, will be written to disk. - The instructions say not to show raw API responses or token values to the user. That reduces transparency — ask for a clearer UI/UX policy and logs you can inspect. - There's no homepage or publisher info. If you need stronger assurance, request: a public project/homepage, documentation on data retention and security practices, and confirmation of exact file destinations for uploads. - If you accept using it, avoid uploading sensitive content, or run the agent in a sandboxed environment where you can control or inspect where tokens/configs are stored. If you want, I can draft specific questions to send to the skill owner requesting these clarifications (token storage, retention, config paths, and privacy policy).

Getting Started

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

Try saying:

• "trim a 10-minute interview recording into a 1080p MP4"
• "cut out the pauses and trim the intro to 30 seconds"
• "cutting long videos into shorter clips for content creators"

First-Time Connection

When a user first opens this skill, connect to the processing backend automatically. Briefly let them know (e.g. "Setting up...").

Authentication: Check if NEMO_TOKEN is set in the environment. If it is, skip to step 2.

1. Obtain a free token: Generate a random UUID as client identifier. POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id set to that UUID. The response data.token is your NEMO_TOKEN — 100 free credits, valid 7 days.
2. Create a session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Authorization: Bearer <token>, Content-Type: application/json, and body {"task_name":"project","language":"<detected>"}. Store the returned session_id for all subsequent requests.

Keep setup communication brief. Don't display raw API responses or token values to the user.

Video Cutter — Cut and Export Trimmed Videos

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

Say you have a 10-minute interview recording and want to cut out the pauses and trim the intro to 30 seconds — the backend processes it in about 20-40 seconds and hands you a 1080p MP4.

Tip: shorter source clips process faster and give more precise cut points.

Matching Input to Actions

User prompts referencing video cutter, 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.

Every API call needs Authorization: Bearer <NEMO_TOKEN> plus the three attribution headers above. If any header is missing, exports return 402.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is video-cutter, 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).

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

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

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 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 "cut out the pauses and trim the intro to 30 seconds" — 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 across platforms and devices.

Common Workflows

Quick edit: Upload → "cut out the pauses and trim the intro to 30 seconds" → 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.