Subtitle Extension

Skip the learning curve of professional editing software. Describe what you want — extend subtitle display time so each line stays on screen longer — and get...

Security Scan

The skill's behavior mostly matches its subtitle-rendering purpose, but there are inconsistent metadata and minor scope concerns (implicit config-path access and required headers) that merit caution before installing or granting credentials.

Purpose & Capability

The declared purpose (extend subtitle duration on uploaded videos) aligns with the runtime instructions (upload endpoints, render/export workflow, credits/status endpoints). Requesting a single service token (NEMO_TOKEN) is proportionate to a cloud-rendering service. However, the SKILL.md frontmatter advertises access to a local config path (~/.config/nemovideo/) while the registry metadata lists no required config paths — this discrepancy is unexpected and should be clarified.

Instruction Scope

The SKILL.md gives concrete API calls only related to authentication, session creation, uploading videos, SSE messaging, and export polling — all within the stated domain. The instructions do ask agents to 'auto-detect' platform from install path (which implies reading the agent's install path) and to include three attribution headers that must match the frontmatter; both expand what the agent will inspect/send beyond just the NEMO_TOKEN. Uploading user video files to the remote service is explicit and expected, but users should be aware their media is transmitted off-device.

Install Mechanism

No install spec or code files — instruction-only skill. This is the lowest-risk install posture: nothing is written to disk by the skill itself.

Credentials

The skill declares a single required env var (NEMO_TOKEN), which is appropriate. But the frontmatter inside SKILL.md also requests a config path (~/.config/nemovideo/) that the registry metadata does not list; if honored, that would give the skill access to local config files. Also, the instructions expect the agent to read NEMO_TOKEN from the environment and to generate/use anonymous tokens when absent. Requesting a persistent account token as an env var is reasonable, but users should avoid placing long-lived secrets in global environment variables unless they trust the service. The discrepancy about configPaths raises proportionality concerns.

Persistence & Privilege

The skill is not marked always:true and uses the default autonomous invocation setting. It does not request system-wide persistence or modifications to other skills. Autonomous invocation is normal here and, standing alone, is not a reason to block the skill.

What to consider before installing

This skill appears to do what it says (upload videos and return rendered files), but take these precautions before installing: - Clarify the metadata mismatch: SKILL.md frontmatter references ~/.config/nemovideo/ while the registry shows no required config paths. Ask the publisher whether the skill will read local config files and why. If it will, review what lives in that folder. - Only provide an NEMO_TOKEN you control and are willing to share with an external service. Prefer short-lived or limited-scope tokens (or use the anonymous-token flow) rather than placing a personal/production token in a global environment variable. - Be aware all uploaded media will be sent to https://mega-api-prod.nemovideo.ai — confirm you trust the operator before uploading sensitive videos. - The skill will include attribution headers and may inspect the agent install path to set X-Skill-Platform; if you do not want local path information exposed, ask the publisher to avoid requiring install-path detection. - Because the skill owner and homepage are unknown, consider testing with non-sensitive sample media and a throwaway token first. If the owner provides a homepage or privacy/terms, review them before using for real content.

Getting Started

Send me your video with subtitles and I'll handle the subtitle duration extension. Or just describe what you're after.

Try saying:

• "extend a 2-minute tutorial video with short subtitle lines into a 1080p MP4"
• "extend subtitle display time so each line stays on screen longer"
• "extending subtitle display duration for easier reading for content creators"

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 Extension — Extend Subtitle Duration in Videos

Send me your video with subtitles and describe the result you want. The subtitle duration extension runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 2-minute tutorial video with short subtitle lines, type "extend subtitle display time so each line stays on screen longer", and you'll get a 1080p MP4 back in roughly 20-40 seconds. All rendering happens server-side.

Worth noting: shorter subtitle segments are easier to time-extend without overlapping adjacent lines.

Matching Input to Actions

User prompts referencing subtitle extension, 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.

Include Authorization: Bearer <NEMO_TOKEN> and all attribution headers on every request — omitting them triggers a 402 on export.

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

Header	Value
X-Skill-Source	subtitle-extension
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 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

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)

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "extend subtitle display time so each line stays on screen longer" — 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.

Common Workflows

Quick edit: Upload → "extend subtitle display time so each line stays on screen longer" → 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.