Subtitle Analysis

Get analyzed subtitle report ready to post, without touching a single slider. Upload your video with subtitles (MP4, MOV, AVI, WebM, up to 500MB), say someth...

Security Scan

The skill's requirements and runtime instructions are coherent with a cloud-based subtitle analysis service, but verify the token use and a small metadata mismatch before installing or sending sensitive videos.

Purpose & Capability

Name/description (subtitle analysis, upload & export) match the declared requirement for a NEMO_TOKEN and the API endpoints in the instructions. Requesting a service token and upload capability is proportionate to the stated purpose.

Instruction Scope

SKILL.md instructs the agent to create/use a bearer token, upload user video files to https://mega-api-prod.nemovideo.ai, open SSE chat streams, poll render status, and return download URLs. These actions are expected for a cloud render/analysis workflow but do involve transmitting user media and transcripts to an external service — users should be aware of privacy/data-retention implications.

Install Mechanism

This is an instruction-only skill with no install spec and no code files — minimal local installation risk.

Credentials

The only required credential is NEMO_TOKEN, which is appropriate. However, SKILL.md frontmatter includes a configPaths entry (~/.config/nemovideo/) while the registry metadata reported no required config paths — this mismatch should be clarified. Also note: if a NEMO_TOKEN exists in the agent environment, the skill will use it directly (so ensure that token's scope/owner is intended to be used).

Persistence & Privilege

always:false (default) and no install hooks; the skill does not request persistent/privileged platform presence or attempt to modify other skills or system configs.

Assessment

This skill appears to do what it says: it will upload user-provided videos/subtitles to a nemo-video backend and return analyzed reports and rendered MP4s. Before installing or using it: (1) confirm you trust the endpoint domain (mega-api-prod.nemovideo.ai) and review its privacy/retention policy for uploaded videos and transcripts; (2) ensure any NEMO_TOKEN in your environment is intended to be used by this skill (it will be used directly if present); (3) if you prefer not to send sensitive video content to a third party, do not upload such files through the skill; (4) ask the publisher to clarify the small metadata mismatch about config path requirements and provide a homepage/source for verifiability.

Getting Started

Share your video with subtitles and I'll get started on AI subtitle analysis. Or just tell me what you're thinking.

Try saying:

• "analyze my video with subtitles"
• "export 1080p MP4"
• "analyze the subtitles in this 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 Analysis — Analyze and Extract Subtitle Insights

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

Here's a typical use: you send a a 3-minute YouTube video with embedded or SRT subtitles, ask for analyze the subtitles in this video and summarize the key topics discussed, 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 — videos with clean, accurate subtitles produce more reliable analysis results.

Matching Input to Actions

User prompts referencing subtitle analysis, 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.

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

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

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

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "analyze the subtitles in this video and summarize the key topics discussed" — concrete instructions get better results.

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

MP4 with embedded subtitles or an accompanying SRT file gives the best analysis accuracy.

Common Workflows

Quick edit: Upload → "analyze the subtitles in this video and summarize the key topics discussed" → 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.