Caption Generator Canva

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

Security Scan

The skill's instructions, endpoints, and credential request are broadly coherent for a cloud captioning integration, but missing provenance (unknown source/homepage), a small metadata inconsistency, and the fact that user videos are uploaded to an external service without clear trust signals are reasons to be cautious.

Purpose & Capability

Name, description, and runtime instructions consistently describe a cloud-based captioning/render pipeline (session creation, upload, SSE, render/export). Requiring a NEMO_TOKEN is proportionate for a third‑party API.

Instruction Scope

Instructions describe uploading user video files and streaming SSE from mega-api-prod.nemovideo.ai and include logic for anonymous token acquisition. They also instruct deriving an X-Skill-Platform header by probing install paths (~/.clawhub/, ~/.cursor/skills/) — that implicitly requires checking the user's filesystem for those paths, which is unnecessary for functionality and a potential privacy surface.

Install Mechanism

This is an instruction-only skill with no install spec and no code files, so nothing is written to disk by the skill package itself (lowest install risk).

Credentials

Only NEMO_TOKEN is declared as required; that's appropriate for this API. The SKILL.md also mentions a config path (~/.config/nemovideo/) in its frontmatter metadata while the registry summary listed no required config paths — a minor inconsistency. The skill will fallback to requesting/generating an anonymous token if NEMO_TOKEN is absent, which means it will still upload user data to the remote service even without user-provided credentials.

Persistence & Privilege

always is false and there's no install-time persistence or cross-skill configuration changes. The skill can be invoked autonomously by the agent (platform default), which increases blast radius only insofar as the service it contacts is trusted.

What to consider before installing

This skill appears to do what it says (cloud captioning) and only needs a single API token, but there are three things to consider before installing: (1) Source trust: the skill has no homepage or known publisher — verify who runs mega-api-prod.nemovideo.ai before sending private videos. (2) Data flow: your uploaded videos and audio will be sent to that external service (even if you don't supply a NEMO_TOKEN, the skill can obtain an anonymous token to proceed). Don't use it for sensitive/personal content unless you trust the provider and understand retention/processing policies. (3) Minor metadata inconsistency: SKILL.md mentions a config path and install-path probing for X-Skill-Platform headers, which implies the agent may check your home directories; if you want to avoid that, ask the skill maintainer to remove filesystem probing and accept 'unknown' as the platform. If you decide to proceed, prefer using a limited-scope token, review the provider's privacy/terms, and test with non-sensitive sample media first.

Getting Started

Got video clips to work with? Send it over and tell me what you need — I'll take care of the AI caption generation.

Try saying:

• "add a 60-second product demo video into a 1080p MP4"
• "add captions to my video in Canva style with bold text"
• "adding styled captions to videos for social media for social media creators"

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 Generator Canva — Auto-Generate Captions for Videos

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

Here's a typical use: you send a a 60-second product demo video, ask for add captions to my video in Canva style with bold text, and about 20-40 seconds 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 2 minutes generate captions noticeably faster.

Matching Input to Actions

User prompts referencing caption generator canva, 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 caption-generator-canva, 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.

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.

Reading the SSE Stream

Text events go straight to the user (after GUI translation). Tool calls stay internal. Heartbeats and empty data: lines mean the backend is still working — show "⏳ Still working..." every 2 minutes.

About 30% of edit operations close the stream without any text. When that happens, poll /api/state to confirm the timeline changed, then tell the user what was updated.

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 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 captions to my video in Canva style with bold text" → Download MP4. Takes 20-40 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 to my video in Canva style with bold text" — 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 social platforms.