Online Subtitle

Turn a 3-minute YouTube tutorial video into 1080p captioned video files just by typing what you need. Whether it's adding subtitles to videos online without...

Security Scan

The skill's runtime instructions largely match a cloud subtitle service, but mismatches between the registry metadata and the SKILL.md (required config paths vs none, required env var vs SKILL.md auto-obtaining a token), lack of a public source/homepage, and runtime calls to an unverified backend make the package incoherent enough to warrant caution.

Purpose & Capability

The declared purpose (add subtitles via a cloud backend) aligns with the API calls and token usage in SKILL.md. However, the registry metadata says no config paths while the SKILL.md frontmatter declares a config path (~/.config/nemovideo/). Also the registry marks NEMO_TOKEN as required, but SKILL.md describes an anonymous-token flow to obtain NEMO_TOKEN if it's not present. Those inconsistencies suggest sloppy packaging or mismatched declarations.

Instruction Scope

SKILL.md instructs the agent to create sessions, upload video files, poll SSE endpoints, and POST to specific API endpoints on mega-api-prod.nemovideo.ai — all coherent with the stated feature set. It also requires adding attribution headers and asks the agent to auto-acquire an anonymous token if NEMO_TOKEN is missing. The instructions are fairly specific but include vague items (auto-detecting 'install path' to set X-Skill-Platform) and rely on an external domain with no published homepage or source for verification.

Install Mechanism

This is an instruction-only skill with no install spec and no code files, so it does not write code to disk or fetch archives at install time. That minimizes install-time risk.

Credentials

Only NEMO_TOKEN is declared as a required credential, which is appropriate for a cloud API-backed subtitle service. But SKILL.md will generate an anonymous token itself if NEMO_TOKEN is missing, so marking the env var as strictly required in registry metadata is inconsistent. The frontmatter's implied config path (~/.config/nemovideo/) could imply reading or writing local configuration, but the registry metadata did not declare that; this discrepancy is concerning and should be clarified.

Persistence & Privilege

The skill does not request always:true and does not include an install script. It keeps session_id in-memory per-session per instructions; there is no explicit instruction to persist tokens or modify other skills or system settings. The only minor concern is the frontmatter-configPath mention (which could permit reading ~/.config/nemovideo/) — that capability is not declared elsewhere, creating ambiguity.

What to consider before installing

This skill mostly behaves like a thin client for an external subtitle-rendering API, but there are metadata mismatches and no public source/homepage to verify the backend. Before installing or enabling it: 1) Ask the publisher for a public repo or homepage and a privacy/security statement about how they store tokens and uploaded video. 2) Clarify whether NEMO_TOKEN is required or optional (SKILL.md says it can obtain an anonymous token). 3) Confirm whether the skill will read or write ~/.config/nemovideo/ and whether tokens are persisted to disk. 4) Limit exposure: do not feed it high-sensitivity videos or system-level secrets (don’t reuse system API keys). 5) If you decide to try it, run it in an isolated environment (sandbox/container) and monitor network requests to the listed domain (mega-api-prod.nemovideo.ai). If the publisher can't provide verifiable details about the service and token handling, avoid granting broad credentials or using it for sensitive content.

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 Japanese"

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.

Online Subtitle — Add Subtitles to Videos Online

This tool takes your video files and runs subtitle generation through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a 3-minute YouTube tutorial video and want to add subtitles in English and Japanese to my video — the backend processes it in about 30-60 seconds and hands you a 1080p MP4.

Tip: shorter clips under 5 minutes generate subtitles significantly faster.

Matching Input to Actions

User prompts referencing online 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.

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	online-subtitle
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)

Backend Response Translation

The backend assumes a GUI exists. Translate these into API actions:

Backend says	You do
"click [button]" / "点击"	Execute via API
"open [panel]" / "打开"	Query session state
"drag/drop" / "拖拽"	Send edit via SSE
"preview in timeline"	Show track summary
"Export button" / "导出"	Execute 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 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

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "add subtitles in English and Japanese to my video" — 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.

Common Workflows

Quick edit: Upload → "add subtitles in English and Japanese to my video" → Download MP4. Takes 30-60 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.