Ai Subtitle Jellyfin

generate video files into subtitled video files with this skill. Works with MP4, MKV, AVI, MOV files up to 500MB. Jellyfin media server users use it for addi...

Security Scan

The skill mostly matches its stated purpose (subtitling via an external Nemo service) but contains metadata/instruction inconsistencies and some data-exfiltration risks that deserve review before use.

Purpose & Capability

The skill's name and instructions describe a cloud-based subtitle/render pipeline and all runtime actions target a nemo-video backend — that aligns with the stated purpose. However the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) not reflected in the registry metadata, which is an internal inconsistency (see environment_proportionality).

Instruction Scope

The SKILL.md instructs the agent to obtain/store tokens, create sessions, upload video files (via multipart file paths or URLs), and repeatedly poll/push to the remote API. It explicitly shows multipart usage with local file paths (e.g., -F "files=@/path"), which implies the agent may read arbitrary filesystem paths if misapplied. It also directs inclusion of attribution headers and automatic anonymous-token acquisition when NEMO_TOKEN is missing — these behaviors broaden the agent's network activity and credential handling beyond simply calling a Jellyfin API.

Install Mechanism

No install spec and no code files: instruction-only skill. That minimizes disk-written code and reduces installer risk.

Credentials

Registry metadata lists NEMO_TOKEN as a required environment variable (primaryEnv), but the SKILL.md instructs the agent to auto-request an anonymous token if NEMO_TOKEN is not set. This is internally inconsistent (required vs. auto-provisioned). SKILL.md also lists a config path (~/.config/nemovideo/) in its frontmatter while the registry metadata said no config paths — another mismatch. Requesting a single third-party token is reasonable for a cloud rendering service, but these metadata/instruction contradictions and the lack of a public homepage or authoritative source for the backend (mega-api-prod.nemovideo.ai) raise provenance and credential-handling concerns.

Persistence & Privilege

The skill does not request always: true and has no install actions. It does instruct the agent to store session_id and tokens for continued requests (normal for a sessioned API) but does not attempt to modify other skills or system-wide configs.

What to consider before installing

This skill appears to call an external 'nemovideo' backend to render subtitles and requests a single token (NEMO_TOKEN). Before installing, verify the backend's trustworthiness and privacy policy (mega-api-prod.nemovideo.ai has no homepage listed here). Ask the publisher for a homepage/source code and confirm what data the backend logs/retains. Note the SKILL.md allows obtaining an anonymous token automatically if none is provided — decide whether you want anonymous uploads to that service. Be cautious about allowing the agent to upload large or private videos: the instructions permit using local file paths for uploads (which could be misused to read other files if the agent's file access is over-permissive). The registry metadata and SKILL.md disagree about required config paths and token handling — request clarification. If you must use it, supply a limited-scope/provisional token (or test with non-sensitive samples) and monitor network activity; do not grant broad filesystem access to the agent without additional safeguards.

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:

• "generate my video files"
• "export 1080p MP4"
• "generate English subtitles for my Jellyfin"

First-Time Connection

When a user first opens this skill, connect to the processing backend automatically. Briefly let them know (e.g. "Setting up...").

Authentication: Check if NEMO_TOKEN is set in the environment. If it is, skip to step 2.

1. Obtain a free token: Generate a random UUID as client identifier. POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id set to that UUID. The response data.token is your NEMO_TOKEN — 100 free credits, valid 7 days.
2. Create a session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Authorization: Bearer <token>, Content-Type: application/json, and body {"task_name":"project","language":"<detected>"}. Store the returned session_id for all subsequent requests.

Keep setup communication brief. Don't display raw API responses or token values to the user.

AI Subtitle Jellyfin — Generate Subtitles for Jellyfin Videos

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

Here's a typical use: you send a a 30-minute Jellyfin library movie file, ask for generate English subtitles for my Jellyfin video and export as SRT, and about 1-3 minutes later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — shorter video segments produce more accurate subtitle timing than full-length films.

Matching Input to Actions

User prompts referencing ai subtitle jellyfin, 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.

Every API call needs Authorization: Bearer <NEMO_TOKEN> plus the three attribution headers above. If any header is missing, exports return 402.

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

Header	Value
X-Skill-Source	ai-subtitle-jellyfin
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 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

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 "generate English subtitles for my Jellyfin video and export as SRT" — concrete instructions get better results.

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

MKV files support embedded subtitle tracks natively for Jellyfin playback.

Common Workflows

Quick edit: Upload → "generate English subtitles for my Jellyfin video and export as SRT" → Download MP4. Takes 1-3 minutes 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.