Free Video Frames

extract video clips into exported frame images with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. YouTubers, video editors, content creators...

Security Scan

The skill's API calls and single required credential (NEMO_TOKEN) match its stated purpose, but there are inconsistencies about storing credentials/config and no source/homepage to verify the service — review where tokens/files are stored and how uploads are handled before installing.

Purpose & Capability

Name and description (remote GPU-based frame extraction) align with the runtime instructions: all interactions target a video-processing API (mega-api-prod.nemovideo.ai) and the skill requests a single NEMO_TOKEN which is the expected credential for that service.

Instruction Scope

SKILL.md describes only API calls (session creation, upload, SSE chat, export polling) and uploading user videos to the stated domain — behavior fits the stated purpose. However, instructions also tell the agent to 'save session_id' and to make a generated anonymous token become your NEMO_TOKEN; that phrasing is ambiguous about where/ how credentials are persisted. The frontmatter also requires a config path (~/.config/nemovideo/) not shown in the registry metadata, which is a scope mismatch that should be clarified.

Install Mechanism

Instruction-only skill with no install spec and no code files — nothing is written to disk by an installer. This is the lower-risk pattern for skills, assuming runtime actions remain limited to the described API.

Credentials

Only one credential (NEMO_TOKEN) is declared as required and is appropriate for a remote API service. But the SKILL.md frontmatter references a config path (~/.config/nemovideo/) which would grant access to a user config directory; the registry metadata reported no required config paths. This inconsistency could mean the skill expects to read/write files on disk to persist tokens — a justified convenience but a privacy concern if not documented.

Persistence & Privilege

always:false and no install scripts reduce privilege. Still, the skill explicitly asks the agent to 'save session_id' and to set a generated token as NEMO_TOKEN; combined with the frontmatter config path, this implies potential persistence of credentials/session state on the host. The skill does not request elevated system privileges, but you should confirm where session/token data are stored and for how long.

What to consider before installing

Before installing or using this skill: (1) Verify the service domain and operator (there's no homepage or source repo listed). (2) Confirm how and where tokens/session IDs are stored — the SKILL.md suggests persisting tokens and the frontmatter references ~/.config/nemovideo/, but the registry metadata disagrees. If you prefer, use the anonymous-token flow rather than placing a long-lived token in your environment. (3) Understand privacy: videos must be uploaded to the provider — confirm retention, sharing, and deletion policies before uploading sensitive content. (4) Test with a harmless small clip first to see whether tokens or session files appear on disk. (5) If you need stronger assurance, ask the author for source code or documentation and for clarification about the config path and token persistence. If you cannot verify those points, avoid using this skill for confidential material.

Getting Started

Send me your video clips and I'll handle the frame extraction. Or just describe what you're after.

Try saying:

• "extract a 2-minute MP4 video clip into a 1080p MP4"
• "extract every 10th frame from my video as images"
• "pulling individual frames from videos for thumbnails or editing for YouTubers, video editors, content creators"

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.

Free Video Frames — Extract and Export Video Frames

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

A quick example: upload a 2-minute MP4 video clip, type "extract every 10th frame from my video as images", and you'll get a 1080p MP4 back in roughly 20-40 seconds. All rendering happens server-side.

Worth noting: shorter clips yield faster frame extraction and more precise results.

Matching Input to Actions

User prompts referencing free video frames, 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.

Three attribution headers are required on every request and must match this file's frontmatter:

Header	Value
X-Skill-Source	free-video-frames
X-Skill-Version	frontmatter version
X-Skill-Platform	auto-detect: clawhub / cursor / unknown from install path

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

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 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

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "extract every 10th frame from my video as images" — 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.

Common Workflows

Quick edit: Upload → "extract every 10th frame from my video as images" → 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.