Video Editing With Hindi

Cloud-based video-editing-with-hindi tool that handles adding Hindi subtitles to videos for Indian audiences. Upload MP4, MOV, AVI, WebM files (up to 500MB),...

Security Scan

The skill's requested credential, network calls, and actions align with a cloud video‑editing/subtitling service; nothing obviously unrelated or excessive is requested, but there are a few minor inconsistencies and privacy considerations to be aware of.

Purpose & Capability

The skill's name and description (Hindi subtitle generation and cloud video rendering) match the runtime instructions: it calls a remote video-rendering API, uploads video files, handles SSE events, polls render status, and returns download URLs. The single required credential (NEMO_TOKEN) is consistent with an upstream API token.

Instruction Scope

Instructions stay within the editing/subtitling domain: session creation, uploading videos, SSE for progress, state polling, and export. The skill does instruct the agent to upload user videos to https://mega-api-prod.nemovideo.ai and to persist a session_id/token for subsequent calls. It does not instruct reading unrelated system files or other environment variables, but it does reference install/config paths for attribution headers which implies the agent may check certain filesystem locations.

Install Mechanism

No install spec or code files are present (instruction-only), so nothing is written to disk by an installer. This is the lowest-risk install model.

Credentials

The skill asks only for NEMO_TOKEN (primaryEnv), which is appropriate for a cloud API. One minor inconsistency: the top-level registry metadata listed no required config paths, but the SKILL.md frontmatter includes a configPaths value (~/.config/nemovideo/). That suggests the skill may read or write a local config directory for session/token persistence — plausible but worth confirming.

Persistence & Privilege

always:false (normal). The instructions tell the agent to store the returned session_id (and implicitly to keep/use NEMO_TOKEN). Persisting session state or tokens locally is reasonable for this workflow, but users should be aware tokens and uploaded videos will be handled by the remote service and may be stored server‑side.

Assessment

This skill appears to do what it claims: it uploads videos to a third‑party rendering API and uses a NEMO_TOKEN for authentication. Before installing or using it, consider: (1) you will be uploading potentially sensitive videos to https://mega-api-prod.nemovideo.ai — review that service's privacy/retention policy if possible; (2) the skill may persist a session_id and/or token locally (frontmatter references ~/.config/nemovideo/) — confirm where data is stored if you care about local persistence; (3) the skill can auto-obtain an anonymous token from the API if NEMO_TOKEN isn't provided — this is convenient but means the service may create short‑lived credentials on your behalf; (4) there is a small metadata inconsistency about config paths in the SKILL.md vs registry metadata — if you need stricter guarantees, ask the publisher where (and whether) files or tokens are written on disk and whether uploads are retained or shared. If you are okay with cloud uploads and short‑lived API tokens, the skill is coherent with its stated purpose.

Getting Started

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

Try saying:

• "add my raw video footage"
• "export 1080p MP4"
• "add Hindi subtitles and captions to"

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.

Video Editing With Hindi — Edit Videos With Hindi Captions

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

Here's a typical use: you send a a 3-minute vlog recorded on a smartphone, ask for add Hindi subtitles and captions to my video, and about 1-2 minutes later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — shorter clips under 5 minutes generate Hindi captions most accurately.

Matching Input to Actions

User prompts referencing video editing with hindi, 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.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is video-editing-with-hindi, 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).

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

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.

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)

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

Common Workflows

Quick edit: Upload → "add Hindi subtitles and captions to my video" → Download MP4. Takes 1-2 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "add Hindi subtitles and captions 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 Hindi video platforms.