Video Caption

add video clips into captioned videos with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. YouTubers and content creators use it for adding sub...

Security Scan

The skill's required credential, API endpoints, and runtime instructions are internally consistent with a cloud-based video-captioning service; no install or unrelated permissions are requested, but the skill will upload user videos to an external API and a few small inconsistencies and privacy considerations remain.

Purpose & Capability

Name/description match the behavior in SKILL.md: it uploads video files, requests a session token, and calls a remote render API. The required primary env var (NEMO_TOKEN) is appropriate for authenticating to the stated service.

Instruction Scope

Instructions direct the agent to POST to mega-api-prod.nemovideo.ai, create an anonymous token if NEMO_TOKEN is absent, upload local files via multipart form (files=@/path), and save session_id. Uploading local video files is expected for the feature, but users should understand videos and metadata will be transmitted to the external service. The SKILL.md also asks the agent to 'auto-detect' platform from an install path — that implies file-system/agent-path access which is out-of-band for a pure UI action and could be clarified.

Install Mechanism

This is an instruction-only skill with no install spec and no binaries to download, which minimizes installation risk.

Credentials

Only NEMO_TOKEN is declared as required, which aligns with the API auth model. The SKILL.md frontmatter also references a config path (~/.config/nemovideo/) that could be used to locate local config—this is not declared in the registry metadata and is a minor inconsistency to clarify. No unrelated secrets or broad system credentials are requested.

Persistence & Privilege

always is false and the skill does not request system-wide or cross-skill modifications. It does instruct the agent to 'save session_id' (presumably in memory/session), which is normal for API sessions; the storage location and lifetime are not specified and should be clarified.

Assessment

This skill appears to do what it says: it uploads video files to mega-api-prod.nemovideo.ai and uses a NEMO_TOKEN to authenticate (or obtains a short-lived anonymous token). Before installing/using: 1) Confirm you are comfortable uploading your video content to that external domain and review the provider's privacy/data-retention policy (no homepage was provided). 2) Prefer using a scoped token or the anonymous token flow for non-sensitive content rather than a long-lived secret in your environment. 3) Ask the publisher to clarify where session_id and tokens are stored (memory vs disk) and whether ~/.config/nemovideo/ is actually used (registry metadata omitted it). 4) Be aware the agent may read local file paths to attach uploads and may try to detect the install path—ensure the agent only accesses files you explicitly upload. If any of these points are unacceptable or unclear, request more details from the skill author before enabling it.

Getting Started

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

Try saying:

• "add a 3-minute tutorial video in MP4 format into a 1080p MP4"
• "add captions in English and Spanish with white text"
• "adding subtitles to YouTube or social media videos for YouTubers and 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.

Video Caption — Add Captions to Videos

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

A quick example: upload a 3-minute tutorial video in MP4 format, type "add captions in English and Spanish with white text", and you'll get a 1080p MP4 back in roughly 30-60 seconds. All rendering happens server-side.

Worth noting: shorter clips under 2 minutes process noticeably faster.

Matching Input to Actions

User prompts referencing video caption, 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.

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

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

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.

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.

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 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 "add captions in English and Spanish with white text" — 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.

Common Workflows

Quick edit: Upload → "add captions in English and Spanish with white text" → Download MP4. Takes 30-60 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.