Caption Video

Get captioned videos ready to post, without touching a single slider. Upload your video clips (MP4, MOV, AVI, WebM, up to 500MB), say something like "add cap...

Security Scan

The skill's requests and runtime instructions are consistent with a cloud captioning service: it needs a single service token, uploads user video to a remote API, and does not install local code — but there are a few small inconsistencies and privacy/handling details you should review before trusting it with sensitive content.

Purpose & Capability

The skill claims to perform captioning/rendering and requires a single service credential (NEMO_TOKEN) and session management with the nemovideo API — that aligns with its stated purpose. Minor inconsistency: the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) while the registry metadata lists no required config paths; it's unclear whether the skill expects to read or write that directory.

Instruction Scope

Runtime instructions stay within captioning functionality: obtain (or use) a token, create a session, upload media, stream SSE events, and start renders. Notable instructions: automatically POST to an external auth endpoint to get an anonymous token if NEMO_TOKEN is not present, store session_id and token for subsequent requests, and 'do not display raw API responses or token values to the user'. The skill also instructs deriving X-Skill-Platform from install paths (e.g. reading ~/.clawhub/ or ~/.cursor/skills/) which implies the agent may need to inspect filesystem paths or agent install metadata. There are no instructions to access unrelated system files or other credentials.

Install Mechanism

Instruction-only skill with no install spec and no code files — minimal install risk because nothing is downloaded or written by an installer.

Credentials

Only one credential (NEMO_TOKEN) is declared as required, which is appropriate for a hosted captioning API. The skill explicitly supports auto-generating a short-lived anonymous token via the provider's auth endpoint (100 free credits, 7 days). The earlier-mentioned metadata/config-path mismatch is the only proportionality oddity to clarify.

Persistence & Privilege

The skill does not request always:true and does not declare system-wide privileges. It instructs storing a session_id and token for repeated calls; it's not explicit where (in memory vs on disk) these are persisted. There is no indication it modifies other skills or global agent settings.

Assessment

What to consider before installing or using this skill: - Trust and privacy: the service's base URL is mega-api-prod.nemovideo.ai (not a well-known vendor). Check the service's privacy policy and data retention terms before uploading sensitive videos. - Token handling: the skill will auto-request an anonymous NEMO_TOKEN if you don't provide one. Ask or confirm where the token/session_id are stored (in-memory vs written to ~/.config/nemovideo/ or another file). If written to disk, you may want the ability to revoke or delete it. - Exposure of local path info: the skill asks agents to set X-Skill-Platform based on install paths (~/.clawhub or ~/.cursor). That could reveal parts of your home path or environment — verify whether the agent exposes any extra metadata you don't want sent. - Test safely: try the skill first with a short, non-sensitive clip to observe behavior, headers, and returned URLs. If possible, supply your own NEMO_TOKEN rather than letting the skill generate one, so you control its lifecycle. - No code installed: because this is instruction-only, there is no package download risk; the primary risk is remote data handling by the external service. If you want higher assurance, ask the skill author to clarify (1) whether any tokens/sessions are persisted to disk and where, (2) the exact data retention / deletion policy for uploaded media, and (3) why the frontmatter lists a config path that registry metadata omitted.

Getting Started

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

Try saying:

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

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.

Caption Video — Add Subtitles to Any Video

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

A quick example: upload a 3-minute YouTube tutorial video, type "add captions in English and Spanish", 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 process significantly faster.

Matching Input to Actions

User prompts referencing caption video, 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 caption-video, 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).

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.

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)

Common Workflows

Quick edit: Upload → "add captions in English and Spanish" → 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" — 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.