Subtitle Download

Turn a 10-minute YouTube tutorial video into 1080p downloadable subtitle files just by typing what you need. Whether it's downloading subtitles from videos a...

Security Scan

The skill will upload user videos and use/obtain a NEMO_TOKEN to talk to an external backend — the instructions include broader rendering/export behavior than the name implies and reference local config paths that aren't needed, so review privacy and token use before installing.

Purpose & Capability

The skill is named and marketed as a 'Subtitle Download' helper, but the runtime instructions describe a full cloud video render/export pipeline (compositing, 1080p renders, many media formats, export endpoints). That scope is broader than the short description and could surprise users expecting only subtitle extraction.

Instruction Scope

SKILL.md instructs the agent to upload user video files (multipart or URL) to an external API (mega-api-prod.nemovideo.ai), create sessions, use SSE, poll renders, and return download URLs. It will perform outbound network calls to obtain anonymous tokens if NEMO_TOKEN is absent. All of that is consistent with a cloud-based service but means user media is transmitted to an unknown third-party domain — a privacy/PII risk that users should understand.

Install Mechanism

No install spec and no code files (instruction-only). This is lower risk from an installation standpoint because nothing is downloaded or written to disk by an installer.

Credentials

The skill requires a single env var (NEMO_TOKEN), which is appropriate for authenticating to the described API. However, metadata also lists a local config path (~/.config/nemovideo/) that the instructions never actually read — this is an unexplained request for local config access. The skill also instructs creating and using an anonymous token if none is provided, which will cause outbound token acquisition automatically.

Persistence & Privilege

always:false and no install steps that modify other skills or system-wide settings. The skill will create short-lived sessions on the remote service but does not request permanent platform privileges.

What to consider before installing

This skill will upload whatever video you drop into the chat to an external service at mega-api-prod.nemovideo.ai and will use a NEMO_TOKEN (or automatically fetch an anonymous token) to do so. Before installing or using it: (1) Confirm you trust that remote service and its privacy policy — don't upload private, proprietary, or sensitive audio/video. (2) Avoid supplying long-lived or highly privileged tokens; prefer temporary/anonymous tokens. (3) Note the mismatch between the skill name ('Subtitle Download') and the runtime behavior (full video rendering/export), and the unexplained reference to a local config path — ask the publisher to clarify why local config access is needed. If you need stronger assurance, request the skill author to provide a verified homepage, source, or privacy/terms links for the backend API.

Getting Started

Share your video with audio and I'll get started on subtitle extraction download. Or just tell me what you're thinking.

Try saying:

• "generate my video with audio"
• "export 1080p MP4"
• "generate and download subtitles for my"

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.

Subtitle Download — Extract and Download Video Subtitles

Drop your video with audio in the chat and tell me what you need. I'll handle the subtitle extraction download on cloud GPUs — you don't need anything installed locally.

Here's a typical use: you send a a 10-minute YouTube tutorial video, ask for generate and download subtitles for my video as an SRT file, 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 — clear audio with minimal background noise produces the most accurate subtitles.

Matching Input to Actions

User prompts referencing subtitle download, 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.

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

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

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 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

Translating GUI Instructions

The backend responds as if there's a visual interface. Map its instructions to API calls:

• "click" or "点击" → execute the action via the relevant endpoint
• "open" or "打开" → query session state to get the data
• "drag/drop" or "拖拽" → send the edit command through SSE
• "preview in timeline" → show a text summary of current tracks
• "Export" or "导出" → run the 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)

Common Workflows

Quick edit: Upload → "generate and download subtitles for my video as an SRT file" → 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "generate and download subtitles for my video as an SRT file" — 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.