Video Finder

find search query into matched video results with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. content creators use it for searching a video...

Security Scan

The skill mostly does what its description says (search and render videos via a cloud API) but there are small metadata inconsistencies and it will upload user videos and call an external API — review data/privacy and the config-path mismatch before installing.

Purpose & Capability

The name/description match the runtime instructions: the SKILL.md explains uploading videos, running searches, streaming SSE, and requesting cloud renders via https://mega-api-prod.nemovideo.ai. Requesting a single API credential (NEMO_TOKEN) is proportionate to that purpose. However, the frontmatter metadata includes a required config path (~/.config/nemovideo/) while the registry metadata earlier listed no config paths — this mismatch is unexplained.

Instruction Scope

The instructions direct the agent to: obtain or generate a token (POST to the external auth endpoint), open a session, upload video files, stream SSE, poll render state, and return download URLs. These behaviors are consistent with a cloud-rendering video search service, but they also mean user video files and metadata will be transmitted to an external third party. The SKILL.md also instructs the agent to detect an install path to set X-Skill-Platform (which implies reading filesystem/install paths). The doc says not to print tokens/raw JSON, but it does not explicitly instruct how long to persist session tokens or where to store them.

Install Mechanism

Instruction-only skill with no install spec and no code files — lowest install risk. There is no downloading or unpacking of third-party code indicated.

Credentials

Only one credential is declared (NEMO_TOKEN), which fits the API usage. The SKILL.md also offers generating an anonymous token via the service's auth endpoint if NEMO_TOKEN is not set (this is reasonable for anonymous use). The unexplained metadata configPath (~/.config/nemovideo/) and the requirement to detect install path for attribution headers are proportionally suspicious because they suggest possible filesystem access beyond just reading an env var; the SKILL.md does not justify reading local config files.

Persistence & Privilege

The skill does not request always:true and does not include an install script. It asks the agent to save a session_id during the session (expected). There is no instruction to modify other skills or system-wide settings.

What to consider before installing

This skill is mostly coherent with its stated purpose (it uploads videos and uses a cloud rendering/search API), but you should be cautious: installing/using it will send your video files and metadata to the nemovideo backend (https://mega-api-prod.nemovideo.ai). Verify the service's privacy and terms before sending sensitive content. Also note a metadata mismatch: the SKILL.md references a config path (~/.config/nemovideo/) and detecting an install path for attribution headers — ask the publisher why the skill needs filesystem/install-path access and where session tokens are stored. If you don't want uploads or external processing of private videos, do not enable this skill.

Getting Started

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

Try saying:

• "find my search query"
• "export 1080p MP4"
• "find me videos of ocean waves"

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.

Video Finder — Search and Locate Videos Fast

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

Say you have a keyword or topic like 'sunset timelapse' and want to find me videos of ocean waves at sunset under 2 minutes — the backend processes it in about under 10 seconds and hands you a 1080p MP4.

Tip: more specific search terms return more accurate matches.

Matching Input to Actions

User prompts referencing video finder, 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.

Base URL: https://mega-api-prod.nemovideo.ai

Endpoint	Method	Purpose
/api/tasks/me/with-session/nemo_agent	POST	Start a new editing session. Body: {"task_name":"project","language":"<lang>"}. Returns session_id.
/run_sse	POST	Send a user message. Body includes app_name, session_id, new_message. Stream response with Accept: text/event-stream. Timeout: 15 min.
/api/upload-video/nemo_agent/me/<sid>	POST	Upload a file (multipart) or URL.
/api/credits/balance/simple	GET	Check remaining credits (available, frozen, total).
/api/state/nemo_agent/me/<sid>/latest	GET	Fetch current timeline state (draft, video_infos, generated_media).
/api/render/proxy/lambda	POST	Start export. Body: {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll status every 30s.

Accepted file types: 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: video-finder
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

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

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

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)

Common Workflows

Quick edit: Upload → "find me videos of ocean waves at sunset under 2 minutes" → Download MP4. Takes under 10 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "find me videos of ocean waves at sunset under 2 minutes" — 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.