Subtitle Generator Green Screen

Turn a 2-minute green screen presentation clip into 1080p captioned green screen videos just by typing what you need. Whether it's adding subtitles to green...

Security Scan

The skill's stated purpose (cloud subtitle/green-screen processing) largely matches its instructions, but there are small incoherences and behavior you should verify before installing—notably automatic anonymous token creation/storage and an inconsistent claim about config-path requirements.

Purpose & Capability

The skill claims to add subtitles and export composited green-screen videos and only requires a NEMO_TOKEN to talk to a nemo video backend—this is coherent. However, the SKILL.md YAML declares a required config path (~/.config/nemovideo/) while the registry metadata shown earlier listed no required config paths. That mismatch is an internal inconsistency worth confirming.

Instruction Scope

The runtime instructions are explicit about creating a session, uploading user video files to https://mega-api-prod.nemovideo.ai, streaming SSE responses, and polling render status. These actions are expected for a cloud render/subtitle service. Two things to notice: (1) if NEMO_TOKEN is not present the skill will automatically POST to an anonymous-token endpoint and treat the returned token as NEMO_TOKEN (i.e., it will acquire credentials on the user's behalf); (2) the doc says 'Don't display raw API responses or token values to the user,' which is reasonable for hiding secrets but also reduces transparency—ask how and where tokens/session IDs are stored and for what retention period. The instructions also derive platform headers by inspecting install paths (~/.clawhub/, ~/.cursor/skills/), which implies the agent will read its environment/paths to compute headers.

Install Mechanism

No install spec and no code files — this is instruction-only. That is low risk from an installation standpoint because nothing arbitrary will be downloaded or written by an installer step described here.

Credentials

Only NEMO_TOKEN is declared as a required environment variable, which is proportionate to a cloud API integration. Caveats: the skill will create an anonymous token if none is present (it expects to store that token and session_id for subsequent requests). Also the SKILL.md metadata references a local config path (~/.config/nemovideo/) which suggests the skill may read/write a config file in the user's home directory—this should be verified and justified.

Persistence & Privilege

always:false (normal). The instructions instruct the agent to persist an anonymous token and session_id for subsequent requests and reference a potential config path. Persisting tokens/sessions and writing a config under ~/.config/nemovideo/ are legitimate for a client that resumes jobs, but this is additional persistence and should be disclosed. There's no evidence the skill modifies other skills or system-wide settings.

What to consider before installing

Before installing or enabling this skill: 1) Confirm the domain (mega-api-prod.nemovideo.ai) is the official service you expect and check their privacy/retention policy—your video files are uploaded to that domain. 2) Ask where the skill will store the anonymous token and session_id (in-memory only vs. written to ~/.config/nemovideo/) and how long those credentials are kept. 3) Decide whether you want the skill to auto-create anonymous tokens on your behalf; if not, pre-provision NEMO_TOKEN and deny auto-creation. 4) Be aware the instructions intentionally hide raw API responses and tokens from the user—request transparency (logs, job IDs) if you need auditability. 5) If you have sensitive content, avoid uploading it until you confirm the vendor, storage/retention, and access controls.

Getting Started

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

Try saying:

• "generate my video footage"
• "export 1080p MP4"
• "generate subtitles and export with a"

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.

Subtitle Generator Green Screen — Add Captions to Green Screen Videos

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

Say you have a 2-minute green screen presentation clip and want to generate subtitles and export with a transparent or replaced background — the backend processes it in about 30-60 seconds and hands you a 1080p MP4.

Tip: keep your green screen well-lit before uploading so the AI processes the subject more accurately.

Matching Input to Actions

User prompts referencing subtitle generator green screen, 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.

Base URL: https://mega-api-prod.nemovideo.ai

Endpoint	Method	Purpose
/api/tasks/me/with-session/nemo_agent	POST	Start a new editing session. Body: {"task_name":"project","language":"<lang>"}. Returns session_id.
/run_sse	POST	Send a user message. Body includes app_name, session_id, new_message. Stream response with Accept: text/event-stream. Timeout: 15 min.
/api/upload-video/nemo_agent/me/<sid>	POST	Upload a file (multipart) or URL.
/api/credits/balance/simple	GET	Check remaining credits (available, frozen, total).
/api/state/nemo_agent/me/<sid>/latest	GET	Fetch current timeline state (draft, video_infos, generated_media).
/api/render/proxy/lambda	POST	Start export. Body: {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll status every 30s.

Accepted file types: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is subtitle-generator-green-screen, X-Skill-Version comes from the version field, and X-Skill-Platform is detected from the install path (~/.clawhub/ = clawhub, ~/.cursor/skills/ = cursor, otherwise unknown).

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

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

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.

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

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 subtitles and export with a transparent or replaced background" — 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 when compositing in other editors.

Common Workflows

Quick edit: Upload → "generate subtitles and export with a transparent or replaced background" → 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.