Ai Screen Record

educators, developers, and content creators edit screen recordings into polished screen recordings using this skill. Accepts MP4, MOV, AVI, WebM up to 500MB,...

Security Scan

The skill's requests and runtime instructions largely match its stated purpose (cloud-based video editing) but there are a few small mismatches and privacy/operational considerations you should review before using it.

Purpose & Capability

The skill is an instruction-only cloud video editing integration and it only asks for a NEMO_TOKEN and (in frontmatter) a nemovideo config path, which is consistent with calling the described nemo-video backend. However, the registry metadata listed earlier reported no required config paths while the skill frontmatter references ~/.config/nemovideo/ — a minor inconsistency to clarify.

Instruction Scope

SKILL.md stays within the edit/export domain: it describes authenticating, creating a session, uploading media, streaming SSE edits, polling export status, and returning download URLs. Two points to note: (1) it instructs the agent to automatically obtain an anonymous token if NEMO_TOKEN is absent (POST to the external endpoint) and (2) it instructs not to display raw API responses or token values to users. Both can be legitimate, but you should confirm where session tokens and session_id are stored and for how long.

Install Mechanism

No install spec and no downloaded code; instruction-only skills are lower-risk for code injection. Nothing is written to disk by an installer here (though the skill may read/write a session/token in runtime state).

Credentials

Only NEMO_TOKEN is requested as the primary credential, which fits a cloud editing service. The automatic anonymous-token flow makes the token optional, but that means the skill will call an external auth endpoint and obtain credentials on your behalf — acceptable for this purpose but worth awareness. The frontmatter's config path reference should be reconciled with registry metadata.

Persistence & Privilege

always is false and autonomous invocation is permitted (platform default). The skill requires storing a session_id and using an auth token for subsequent calls, which is typical for a remote service; it does not request elevated agent-wide privileges or persistent system-wide changes.

Assessment

This skill appears to do what it says (cloud-based video editing) and only needs a NEMO_TOKEN, but check these before installing: 1) Privacy & content: using the skill uploads your videos (up to 500MB) to https://mega-api-prod.nemovideo.ai — do not upload sensitive or confidential recordings unless you trust the service and its privacy policy. 2) Token handling: the skill can auto-create anonymous tokens if NEMO_TOKEN is not set; ask where tokens/session IDs are stored and how long they persist. 3) Config path mismatch: the SKILL.md references ~/.config/nemovideo/, but registry metadata said no config paths — ask the publisher to clarify. 4) Billing/credits: anonymous tokens have limited credits and exports may require topping up; verify cost/limits before large jobs. If you need stronger assurance, request the publisher's homepage, a privacy policy, or source code to confirm storage and deletion behavior.

Getting Started

Share your screen recordings and I'll get started on AI screen capture editing. Or just tell me what you're thinking.

Try saying:

• "edit my screen recordings"
• "export 1080p MP4"
• "remove filler pauses, add zoom-ins on"

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.

AI Screen Record — Edit and Export Screen Recordings

Send me your screen recordings and describe the result you want. The AI screen capture editing runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 3-minute screen recording of a software tutorial, type "remove filler pauses, add zoom-ins on clicks, and add captions", and you'll get a 1080p MP4 back in roughly 1-2 minutes. All rendering happens server-side.

Worth noting: trim dead air before uploading to speed up processing and get tighter results.

Matching Input to Actions

User prompts referencing ai screen record, 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: ai-screen-record
• 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

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.

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 "remove filler pauses, add zoom-ins on clicks, and add captions" — 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 → "remove filler pauses, add zoom-ins on clicks, and add captions" → Download MP4. Takes 1-2 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.