Movie Subtitle

Turn a 2-hour movie file in MP4 format into 1080p subtitled video files just by typing what you need. Whether it's adding subtitles to movies and long-form v...

Security Scan

The skill's requests and runtime instructions are consistent with a remote subtitle-and-render service: it needs a single NEMO_TOKEN (or can obtain an anonymous token) and will upload videos to nemo's API for server-side processing.

Purpose & Capability

The name/description (generate and embed subtitles, render 1080p outputs) matches the actions the SKILL.md instructs (uploading video, SSE-based messaging, render/export endpoints). Requiring NEMO_TOKEN and session handling is appropriate for a hosted rendering service.

Instruction Scope

Instructions explicitly direct the agent to upload user video files and stream SSE to a remote API (mega-api-prod.nemovideo.ai). That data exfiltration is necessary for the described functionality but is material: user videos (potentially large and sensitive) will be sent to a third-party backend. The skill also instructs checking install path and reading the skill's YAML frontmatter to populate attribution headers; those are limited, explainable filesystem reads but worth noting.

Install Mechanism

No install spec and no code files — lowest risk for local persistence. All runtime behavior is instruction-only and performed via network calls to the remote API.

Credentials

Only NEMO_TOKEN is declared as required (primary credential), which is proportional to a hosted rendering API. The SKILL.md also documents an anonymous-token flow if NEMO_TOKEN is absent. The frontmatter mentions a config path (~/.config/nemovideo/) and the skill will try to detect install paths for X-Skill-Platform; the registry metadata shown earlier listed no config paths — this small mismatch should be noted but is explainable (the skill may optionally read local config for stored tokens).

Persistence & Privilege

always:false and no install scripts or cross-skill/system-wide modifications. The skill does not request permanent platform privileges beyond normal runtime network access.

Assessment

This skill will upload whatever video files you give it to mega-api-prod.nemovideo.ai for remote GPU subtitle generation and rendering. That is required for the feature, but it means your video content (and any embedded audio/metadata) will leave your device. If you have a private or sensitive video, avoid uploading it or confirm the service's privacy policy. The skill will use NEMO_TOKEN if present (so a provided token will be used for billing/credits); if no token exists it will request an anonymous token automatically. Note the small metadata mismatch: the skill's frontmatter references a local config path/install-path detection (used only to set a header) — this is plausible but be aware it may read those locations. If you trust nemo video's domain and are comfortable sending video data for processing, the skill appears coherent and proportional to its stated purpose.

Getting Started

Share your video files and I'll get started on subtitle generation. Or just tell me what you're thinking.

Try saying:

• "add my video files"
• "export 1080p MP4"
• "add subtitles in English and French"

Getting Connected

Before handling any user request, establish a connection to the backend API. Show a brief status like "Connecting...".

If NEMO_TOKEN is in the environment, use it directly and create a session. Otherwise, acquire a free starter token:

• Generate a UUID as client identifier
• POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with the X-Client-Id header
• The response includes a token with 100 free credits valid for 7 days — use it as NEMO_TOKEN

Then create a session by POSTing to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer authorization and body {"task_name":"project","language":"en"}. The session_id in the response is needed for all following requests.

Tell the user you're ready. Keep the technical details out of the chat.

Movie Subtitle — Generate and Embed Movie Subtitles

Send me your video files 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 2-hour movie file in MP4 format, type "add subtitles in English and French to my movie", and you'll get a 1080p MP4 back in roughly 1-3 minutes. All rendering happens server-side.

Worth noting: splitting long movies into scenes speeds up subtitle processing.

Matching Input to Actions

User prompts referencing movie subtitle, 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: movie-subtitle
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

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.

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.

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

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

Common Workflows

Quick edit: Upload → "add subtitles in English and French to my movie" → Download MP4. Takes 1-3 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "add subtitles in English and French to my movie" — concrete instructions get better results.

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

Export as MP4 with H.264 codec for widest device compatibility.