Ai Subtitle Editor

Turn a 3-minute YouTube tutorial recording into 1080p captioned video files just by typing what you need. Whether it's adding subtitles to YouTube and social...

Security Scan

The skill's behavior is largely coherent with a cloud subtitle/renderer service, but packaging inconsistencies (metadata vs registry), an unknown upstream domain, and a runtime instruction to probe install paths/filesystem make me cautious.

Purpose & Capability

The name/description (AI Subtitle Editor) match the instructions that call a remote rendering API and upload video files. Requesting a single service token (NEMO_TOKEN) is proportionate. However, the SKILL.md metadata lists a config path (~/.config/nemovideo/) while the registry summary earlier said 'Required config paths: none' — an internal inconsistency in the bundle.

Instruction Scope

Runtime instructions focus on connecting to mega-api-prod.nemovideo.ai: creating anonymous tokens, creating sessions, uploading videos, SSE streaming, and polling renders — all expected for this purpose. The instructions also tell the agent to read the SKILL.md YAML frontmatter and to detect install path (~/.clawhub/ or ~/.cursor/skills/) to set X-Skill-Platform; reading those install paths and the skill file is somewhat intrusive (reveals presence of other tooling and local paths) and is unnecessary for basic upload/render operations.

Install Mechanism

Instruction-only skill with no install spec or code files — lowest install risk. Nothing is downloaded or written by an installer step according to the manifest.

Credentials

Only one required env var (NEMO_TOKEN) is declared and used as bearer auth; that's appropriate. The SKILL.md also describes generating an anonymous token and using it as NEMO_TOKEN when the env var is absent — reasonable but it means the skill will perform network auth on the user's behalf. The mismatch between top-level 'no config paths' and SKILL.md's metadata listing ~/.config/nemovideo/ is unexplained.

Persistence & Privilege

The skill is not always-enabled and uses default autonomous invocation. It does not request system-wide privileges or permanent presence beyond using the token/session; no evidence it modifies other skills or global agent configs.

What to consider before installing

This skill appears to do what it claims (upload video, create a session, render on a remote GPU service) and only asks for one token (NEMO_TOKEN). However: - The skill will contact an external domain (mega-api-prod.nemovideo.ai). If you don't recognize this service, verify the vendor/site before sending private videos. - It may probe install paths (~/.clawhub, ~/.cursor/skills) and read its own SKILL.md frontmatter; that can reveal tool installation details — consider if you’re comfortable with that metadata being accessed. - There's a packaging inconsistency: the registry said no config paths, but the SKILL.md lists ~/.config/nemovideo/; ask the author which is correct. - Prefer using ephemeral/anonymous tokens for uploads if you don't want to store a persistent NEMO_TOKEN; avoid placing tokens in global environment variables unless you trust the service. If you want higher confidence before installing: ask the publisher for a homepage/source repo, a privacy policy for uploaded content, and an explanation for the configPath/install-path checks. If the service is unfamiliar, avoid uploading sensitive videos until you confirm ownership and retention/processing guarantees.

Getting Started

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

Try saying:

• "add my video files"
• "export 1080p MP4"
• "add captions in English and Spanish"

Automatic Setup

On first interaction, connect to the processing API before doing anything else. Show a brief status like "Setting things up...".

Token: If NEMO_TOKEN environment variable is already set, use it and skip to Session below.

Free token: Generate a UUID as client identifier, then POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id: <uuid>. The response field data.token becomes your NEMO_TOKEN (100 credits, 7-day expiry).

Session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Save session_id from the response.

Confirm to the user you're connected and ready. Don't print tokens or raw JSON.

AI Subtitle Editor — Add Captions and Export Videos

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

A quick example: upload a 3-minute YouTube tutorial recording, type "add captions in English and Spanish with auto-sync", and you'll get a 1080p MP4 back in roughly 30-60 seconds. All rendering happens server-side.

Worth noting: shorter clips under 5 minutes generate subtitles significantly faster.

Matching Input to Actions

User prompts referencing ai subtitle editor, 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 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.

Skill attribution — read from this file's YAML frontmatter at runtime:

• X-Skill-Source: ai-subtitle-editor
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

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 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

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

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 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)

Common Workflows

Quick edit: Upload → "add captions in English and Spanish with auto-sync" → 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "add captions in English and Spanish with auto-sync" — 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 all platforms.