Best Video Frames

extract video footage into top quality frames with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. content creators use it for pulling the clea...

Security Scan

The skill's requirements and instructions are consistent with a cloud video-processing connector that uploads user video to a backend and uses a single API token; nothing in the package suggests it is trying to do unrelated or hidden things, but there are a few minor inconsistencies and privacy considerations you should note before installing.

Purpose & Capability

The skill claims to extract high-quality frames via a cloud backend and it requires a single API token (NEMO_TOKEN) and network calls to a nemo video API — this aligns with the described purpose. Minor inconsistency: the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) and asks to detect install path for attribution, but the registry metadata earlier reported no required config paths; this is a small mismatch in metadata but not a functional red flag.

Instruction Scope

The runtime instructions direct the agent to perform HTTP requests (auth, session creation, SSE, upload, export polling) and to upload any user-provided video to the third-party backend — all expected for this skill. The instructions also tell the agent to read the skill's YAML frontmatter and detect install paths (e.g., ~/.clawhub/, ~/.cursor/skills/) to set an X-Skill-Platform header; reading those filesystem locations is slightly invasive relative to pure video processing but appears limited to attribution detection. No instructions ask the agent to read unrelated files, system credentials, or to exfiltrate extra data beyond uploads to the stated API.

Install Mechanism

This is an instruction-only skill with no install spec and no code files — low risk from installation artifacts. There is no package download or archive extraction to inspect.

Credentials

Only one credential (NEMO_TOKEN) is declared as required and is the primary credential; that is proportionate for a cloud-processing service. The skill will optionally obtain an anonymous token by calling the provider's anonymous-token endpoint if NEMO_TOKEN is not present — acceptable but worth noting (token has limited credits/expiry). The metadata/frontmatter mentions a config path (~/.config/nemovideo/) and install-path detection; these are not sensitive by themselves but represent additional filesystem access that the registry did not list as required.

Persistence & Privilege

The skill is not always-enabled and does not request any elevated platform privileges. It will keep a session_id in memory for operations and may reuse an anonymous token for up to 7 days per the backend, but it does not declare writing system-wide configuration or modifying other skills.

Assessment

This skill uploads your video files to an external service (mega-api-prod.nemovideo.ai) and requires a NEMO_TOKEN (or it will request a temporary anonymous token on your behalf). Before installing: (1) verify you trust the nemo video domain and are comfortable with your videos leaving your device, (2) be aware the skill may read install/config paths in your home directory for attribution purposes, (3) do not supply sensitive or confidential footage unless you confirm the provider's privacy/security posture, and (4) note that anonymous tokens are short-lived and the skill will create them automatically if none are provided. The package appears coherent with its stated purpose, but review the service's terms/privacy before use.

Getting Started

Share your video footage and I'll get started on AI frame extraction. Or just tell me what you're thinking.

Try saying:

• "extract my video footage"
• "export 1080p MP4"
• "extract the sharpest and most visually"

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.

Best Video Frames — Extract top frames from video

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

Here's a typical use: you send a a 2-minute interview recording, ask for extract the sharpest and most visually clear frames from my video, 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 — shorter clips yield faster and more precise frame detection results.

Matching Input to Actions

User prompts referencing best 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.

Skill attribution — read from this file's YAML frontmatter at runtime:

• X-Skill-Source: best-video-frames
• 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.

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.

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.

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

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)

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 "extract the sharpest and most visually clear frames from my video" — 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 the sharpest and most visually clear frames from my video" → 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.