Clip Skill

Turn a 2-minute raw video recording into 1080p edited video clips just by typing what you need. Whether it's trimming and refining short video clips for soci...

Security Scan

The skill's runtime instructions largely match a cloud video-editing purpose, but there is an inconsistency about config-path access (the SKILL.md asks for ~/.config/nemovideo/ while the registry lists no required config paths) which could expand what the agent reads from your machine; review before installing.

Purpose & Capability

Name/description, endpoints, and required credential (NEMO_TOKEN) all align with a cloud video-editing service that uploads media and returns rendered clips. The skill also auto-provisions an anonymous NEMO_TOKEN if none is present, which fits a consumer-friendly flow.

Instruction Scope

The SKILL.md instructs the agent to upload user video files and call various backend endpoints (session, upload, render, state, credits). That is expected for this purpose. However the SKILL.md metadata lists a config path (~/.config/nemovideo/) which implies the agent may look in a user config directory; the registry metadata reported no required config paths. This mismatch is an incoherence — if the agent reads that directory it might access credentials or other files beyond the single declared env var.

Install Mechanism

No install spec and no code files — instruction-only. That minimizes filesystem persistence and installation-time risk.

Credentials

Only one env var is declared (NEMO_TOKEN), which is proportionate for an API-backed video editor. The skill will auto-request an anonymous token from the service if NEMO_TOKEN is absent. The main concern is the SKILL.md metadata's configPaths entry (see instruction_scope) which would broaden access beyond the single env var if honored.

Persistence & Privilege

always:false and no install spec. The skill does network I/O and can be invoked autonomously (platform default) but it does not request elevated system persistence.

What to consider before installing

This skill behaves like a cloud video editor: it uploads your video files to a remote API (mega-api-prod.nemovideo.ai) and returns rendered clips. That behavior is expected, but before you install or use it consider: (1) Do you want your video content sent to that external service? (2) The skill will accept or create a NEMO_TOKEN (anonymous tokens are temporary); avoid providing a long-lived secret unless you trust the service. (3) SKILL.md metadata references a local config path (~/.config/nemovideo/) even though the registry said no config paths — ask the author whether the agent will read that directory (it could contain other credentials or personal data). (4) Request the privacy/retention policy and confirm where uploaded media and generated tokens are stored and for how long. If you need stronger guarantees, do not supply a persistent NEMO_TOKEN and verify the agent is not reading arbitrary config directories before using sensitive media.

Getting Started

Got video clips to work with? Send it over and tell me what you need — I'll take care of the AI clip editing.

Try saying:

• "edit a 2-minute raw video recording into a 1080p MP4"
• "trim this clip, remove silences, and cut it down to 30 seconds"
• "trimming and refining short video clips for social media for content creators"

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.

Clip Skill — Edit and Export Video Clips

Send me your video clips and describe the result you want. The AI clip editing runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 2-minute raw video recording, type "trim this clip, remove silences, and cut it down to 30 seconds", and you'll get a 1080p MP4 back in roughly 20-45 seconds. All rendering happens server-side.

Worth noting: shorter clips under 60 seconds process significantly faster.

Matching Input to Actions

User prompts referencing clip skill, 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.

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

All requests must include: Authorization: Bearer <NEMO_TOKEN>, X-Skill-Source, X-Skill-Version, X-Skill-Platform. Missing attribution headers will cause export to fail with 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)

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 "trim this clip, remove silences, and cut it down 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.

Common Workflows

Quick edit: Upload → "trim this clip, remove silences, and cut it down to 30 seconds" → Download MP4. Takes 20-45 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.