Subtitle To Video

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

Security Scan

The skill's behavior mostly matches a subtitle-embedding service, but there are inconsistencies and a couple of runtime instructions (reading install paths / config locations, and a mismatched configPaths declaration) that warrant caution before installing.

Purpose & Capability

The skill's stated purpose (embed subtitles into videos) matches the runtime instructions (upload video + subtitle files, render on cloud GPUs, return MP4). Requesting a NEMO_TOKEN credential is coherent for a hosted rendering service. However, the SKILL.md frontmatter declares a configPath (~/.config/nemovideo/) even though the registry metadata reported no required config paths — this mismatch is unexplained.

Instruction Scope

Runtime instructions are explicit about connecting to https://mega-api-prod.nemovideo.ai, creating sessions, uploading files, using SSE, and polling render status — all expected for a cloud rendering service. The instructions also ask the agent to detect install path patterns to set X-Skill-Platform and to read this file's YAML frontmatter at runtime to set attribution headers. Those filesystem reads (detecting install path, reading frontmatter) are not strictly required to embed subtitles and expand the skill's scope modestly; they should be justified by the developer.

Install Mechanism

No install spec and no code files — instruction-only skill. That is lower risk because nothing is written to disk by an installer. All network activity comes from runtime API calls described in SKILL.md.

Credentials

The skill only declares one required env var (NEMO_TOKEN), which is proportionate to a hosted API. The instructions also provide a fallback workflow to obtain an anonymous token by POSTing to the service if NEMO_TOKEN is absent; this is reasonable but means the agent may reach out and create/use ephemeral credentials automatically. The mismatch between the registry's 'no config paths' and the frontmatter that lists ~/.config/nemovideo/ is unexplained and should be clarified.

Persistence & Privilege

No 'always: true' or other elevated persistence flags. The skill is user-invocable and allows autonomous invocation (the platform default) but does not request system-wide modifications or persistent elevated privileges in its manifest.

What to consider before installing

This skill appears to be a client for a cloud subtitle-rendering service and will upload the video/subtitle files you provide to https://mega-api-prod.nemovideo.ai and use a NEMO_TOKEN for authorization. Before installing or running it: 1) Confirm you trust the nemovideo.ai domain and are comfortable uploading the videos (they will leave your machine). 2) Prefer providing your own NEMO_TOKEN from a known account rather than relying on the skill's anonymous-token flow if you need auditability. 3) Ask the publisher to explain the config path in the frontmatter (~/.config/nemovideo/) and why the registry listed no config paths — that mismatch is unexplained. 4) If you have sensitive videos, verify the service's privacy/retention policy and, if possible, test with non-sensitive content first. Additional information that would raise confidence: a homepage or documented service owner, code or network logs showing only the described endpoints, and a clear justification for reading install paths and the YAML frontmatter.

Getting Started

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

Try saying:

• "add my subtitle files, video"
• "export 1080p MP4"
• "burn these subtitles into my video"

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.

Subtitle to Video — Embed Subtitles Into Videos

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

A quick example: upload a 3-minute tutorial video with an SRT file, type "burn these subtitles into my video so they show on all players", and you'll get a 1080p MP4 back in roughly 20-40 seconds. All rendering happens server-side.

Worth noting: shorter clips process faster, so split long videos before uploading.

Matching Input to Actions

User prompts referencing subtitle to video, 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 calls go to https://mega-api-prod.nemovideo.ai. The main endpoints:

1. Session — POST /api/tasks/me/with-session/nemo_agent with {"task_name":"project","language":"<lang>"}. Gives you a session_id.
2. Chat (SSE) — POST /run_sse with session_id and your message in new_message.parts[0].text. Set Accept: text/event-stream. Up to 15 min.
3. Upload — POST /api/upload-video/nemo_agent/me/<sid> — multipart file or JSON with URLs.
4. Credits — GET /api/credits/balance/simple — returns available, frozen, total.
5. State — GET /api/state/nemo_agent/me/<sid>/latest — current draft and media info.
6. Export — POST /api/render/proxy/lambda with render ID and draft JSON. Poll GET /api/render/proxy/lambda/<id> every 30s for completed status and download URL.

Formats: 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: subtitle-to-video
• 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.

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)

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

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.

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

Common Workflows

Quick edit: Upload → "burn these subtitles into my video so they show on all players" → 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 "burn these subtitles into my video so they show on all players" — 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 and devices.