Caption Ai

Turn a 3-minute YouTube tutorial recording into 1080p captioned videos just by typing what you need. Whether it's adding auto-generated subtitles to videos o...

Security Scan

The skill's code-free instructions and requested token (NEMO_TOKEN) align with a cloud captioning service; nothing demands unrelated credentials or risky installs, but it will send your video files and may read local skill/config metadata.

Purpose & Capability

The skill name/description (auto-generate captions, upload video, export MP4) match the only required credential (NEMO_TOKEN) and the API endpoints the instructions use. The SKILL.md metadata also references a local config path (~/.config/nemovideo/) and reading the skill frontmatter/install path for attribution headers — these are plausible for a client that wants to include provenance and local config, though not strictly necessary.

Instruction Scope

Runtime instructions are explicit about connecting to the nemovideo.ai API, creating or consuming NEMO_TOKEN, creating a session, uploading local video files (multipart or URL), polling render status, and returning download URLs. The skill also instructs the agent to read this file's YAML frontmatter and detect the agent install path (~/.clawhub/, ~/.cursor/skills/) for attribution headers; and to consider a local config path (~/.config/nemovideo/). Those file reads are limited in scope (skill metadata and possible service config) but are outside pure captioning logic and could expose small amounts of local config if present. The instructions do not request any unrelated system credentials or arbitrary file reads beyond these.

Install Mechanism

No install spec or remote code downloads are present (instruction-only skill). There is no package installation, archive extraction, or external binary download — lowest risk in this dimension.

Credentials

Only one environment credential is declared (NEMO_TOKEN) which is appropriate for a cloud API client. The skill will also create an anonymous token via the service's anonymous-token endpoint if NEMO_TOKEN is absent. The SKILL.md metadata mentions a local config path which could contain service credentials; the agent instructions imply reading it for configuration/attribution. That is plausible but worth noting: providing NEMO_TOKEN or allowing the skill to read ~/.config/nemovideo/ grants access to the associated account and any stored tokens/config.

Persistence & Privilege

The skill is not marked always:true and has no install-time code; it does not request persistent system-wide changes or modify other skills. Autonomous invocation is allowed (platform default) but not combined with high privilege or extra credentials.

Assessment

This skill appears to do what it says: it uploads videos to nemovideo.ai, uses NEMO_TOKEN (or obtains an anonymous token) to create a session, and returns a processed video URL. Before installing or using it: (1) be aware that your video files and any metadata are sent to an external service (https://mega-api-prod.nemovideo.ai); don't upload sensitive video you don't want transmitted. (2) Providing NEMO_TOKEN or allowing the skill to read ~/.config/nemovideo/ grants access to your account on that service — prefer a scoped/disposable token if possible. (3) The skill reads its own frontmatter and may detect install paths to add attribution headers — this is harmless but means the skill may read small local config/metadata files. (4) If you have privacy or compliance concerns, test with non-sensitive videos and consider creating an anonymous/free token rather than exposing a long-lived account token. If you want further assurance, ask the publisher for a privacy/TOS statement or for an installable client from a known homepage (none is provided here).

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"

Getting Connected

Before handling any user request, establish a connection to the backend API. Show a brief status like "Connecting...".

If NEMO_TOKEN is in the environment, use it directly and create a session. Otherwise, acquire a free starter token:

• Generate a UUID as client identifier
• POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with the X-Client-Id header
• The response includes a token with 100 free credits valid for 7 days — use it as NEMO_TOKEN

Then create a session by POSTing to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer authorization and body {"task_name":"project","language":"en"}. The session_id in the response is needed for all following requests.

Tell the user you're ready. Keep the technical details out of the chat.

Caption AI — Auto-Generate Captions for Videos

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

Say you have a 3-minute YouTube tutorial recording and want to add captions in English and Spanish with auto-sync — the backend processes it in about 30-60 seconds and hands you a 1080p MP4.

Tip: shorter clips under 2 minutes process significantly faster.

Matching Input to Actions

User prompts referencing caption ai, 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.

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

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

Error Handling

Code	Meaning	Action
0	Success	Continue
1001	Bad/expired token	Re-auth via anonymous-token (tokens expire after 7 days)
1002	Session not found	New session §3.0
2001	No credits	Anonymous: show registration URL with ?bind=<id> (get <id> from create-session or state response when needed). Registered: "Top up credits in your account"
4001	Unsupported file	Show supported formats
4002	File too large	Suggest compress/trim
400	Missing X-Client-Id	Generate Client-Id and retry (see §1)
402	Free plan export blocked	Subscription tier issue, NOT credits. "Register or upgrade your plan to unlock export."
429	Rate limit (1 token/client/7 days)	Retry in 30s once

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 platforms.

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.