Blackbox Ai

analyze raw video footage into AI-processed video with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. content creators and developers use it f...

Security Scan

The skill is broadly consistent with a cloud video-processing connector, but there are mismatches and privacy/behavioral surprises (automatic anonymous token creation, instructions to hide token values, and metadata inconsistencies) that merit caution before installing.

Purpose & Capability

The claimed purpose (AI video analysis / export) aligns with the API endpoints and workflow described (upload, render, export). Requesting a single service token (NEMO_TOKEN) is proportionate to the stated purpose. However, the SKILL.md describes auto-generating an anonymous token if NEMO_TOKEN is not present, while the registry lists NEMO_TOKEN as required — that inconsistency should be resolved.

Instruction Scope

Instructions direct the agent to: generate UUIDs, POST credentials to a third-party domain (mega-api-prod.nemovideo.ai), upload user video files, store session IDs, and detect install paths to set attribution headers. Those actions are expected for a remote video-processing skill, but two instructions stand out as concerning: (1) 'Don't display raw API responses or token values to the user' — this explicitly instructs hiding tokens/response content from users; (2) detecting install path and reading frontmatter to set X-Skill-Platform/X-Skill-Version requires reading local paths and the skill file. Together these grant the agent discretion over token generation/storage and some filesystem inspection outside purely user-file handling.

Install Mechanism

No install spec or code files — instruction-only skill. This is the lowest install risk: nothing is downloaded or written by an installer step.

Credentials

Only one credential (NEMO_TOKEN) is declared and it is appropriate for the external service. However, the SKILL.md will create an anonymous token when NEMO_TOKEN is absent; the registry metadata and SKILL.md frontmatter also differ regarding required config paths (~/.config/nemovideo/ appears in the frontmatter but the registry shows no required config paths). These mismatches weaken the declared environment/credential guarantees.

Persistence & Privilege

always is false and the skill does not request elevated platform privileges. It will store session_id and tokens for ongoing API use per its instructions (normal for a remote-service skill). There is no indication it modifies other skills or system-wide settings.

What to consider before installing

This skill appears to be a normal connector to a third-party video-processing API, but proceed with caution. Before installing or using it: - Confirm the privacy policy and data-retention practices of mega-api-prod.nemovideo.ai; your videos will be uploaded to that external service. Do not upload sensitive or private footage until you’ve verified retention and deletion policies. - Consider supplying your own NEMO_TOKEN (from your account) rather than allowing the skill to auto-generate anonymous tokens. The skill will create a token automatically if none is present and is instructed to hide token values from users — ask the maintainer why token values should be hidden and where tokens/sessions are stored. - Ask the author/registry to fix metadata mismatches: the frontmatter references a config path (~/.config/nemovideo/) and declares NEMO_TOKEN as required but the registry shows different requirements. Clear these inconsistencies before trusting the skill. - If you need an audit trail, request the exact behavior for token storage (where session_id / token are saved, how long they persist) and whether the skill sends any data outside the documented nemovideo API domain. If any of the above answers are unsatisfactory, avoid installing or allow the skill only in a sandboxed environment.

Getting Started

Ready when you are. Drop your raw video footage here or describe what you want to make.

Try saying:

• "analyze a 2-minute screen recording or tutorial clip into a 1080p MP4"
• "analyze this video and automatically cut dead air, add captions, and highlight key moments"
• "automatically editing and enhancing videos using AI without manual effort for content creators and developers"

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.

Blackbox AI — AI Video Analysis and Export

This tool takes your raw video footage and runs AI-powered video analysis through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a 2-minute screen recording or tutorial clip and want to analyze this video and automatically cut dead air, add captions, and highlight key moments — the backend processes it in about 1-2 minutes and hands you a 1080p MP4.

Tip: shorter clips under 60 seconds yield faster and more accurate AI analysis results.

Matching Input to Actions

User prompts referencing blackbox ai, 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 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.

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

• X-Skill-Source: blackbox-ai
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

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.

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

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.

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)

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "analyze this video and automatically cut dead air, add captions, and highlight key moments" — concrete instructions get better results.

Max file size is 500MB. Stick to MP4, MOV, AVI, WebM for the smoothest experience.

Export as MP4 with H.264 codec for the best balance of quality and file size.

Common Workflows

Quick edit: Upload → "analyze this video and automatically cut dead air, add captions, and highlight key moments" → 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.