Caption Ab

Skip the learning curve of professional editing software. Describe what you want — test two caption styles on my video and compare which performs better — an...

Security Scan

The skill's runtime instructions match its captioning purpose, but there are metadata inconsistencies and an unknown backend service with no homepage—check the service and config-path claims before trusting it with your videos or credentials.

Purpose & Capability

The skill's name/description (A/B caption testing) aligns with the API endpoints and upload/export workflow in SKILL.md. Requesting a single NEMO_TOKEN credential is proportionate. However, SKILL.md frontmatter declares a configPaths (~/.config/nemovideo/) while the registry metadata earlier reported no required config paths; the source/homepage are also not provided, making provenance unclear.

Instruction Scope

Instructions are specific and scoped to creating a session, uploading video files, submitting render jobs, and polling results on the external API (mega-api-prod.nemovideo.ai). The skill does not instruct reading unrelated local files or arbitrary environment variables. It does require uploading user video files to the service (privacy implication). It also asks the agent to auto-detect an install path to set a header value, which could require checking agent context.

Install Mechanism

No install spec or code is included (instruction-only). That minimizes on-disk risk; nothing is downloaded or extracted by the skill itself.

Credentials

Only NEMO_TOKEN is declared as required, which is appropriate for an API-backed service. But the SKILL.md frontmatter's inclusion of a config path (~/.config/nemovideo/) suggests possible access to local config that isn't explained elsewhere — a proportionality mismatch. The skill also offers to obtain an anonymous token for you (via the same backend), which is reasonable but means network calls can be made without a pre-provided token.

Persistence & Privilege

The skill is not force-included (always: false) and does not request elevated platform privileges or modifications to other skills. Autonomous invocation is allowed (platform default) but not combined with other high-risk requests.

What to consider before installing

This skill appears to implement the caption A/B testing workflow it describes, but proceed cautiously because (a) the backend domain has no published homepage or clear owner identity in the registry, and (b) there's an inconsistency about a config path (~/.config/nemovideo/) mentioned in the skill frontmatter. Before installing/use: 1) Prefer using the anonymous starter token (the skill offers to obtain one) for testing rather than giving any long-lived or privileged NEMO_TOKEN. 2) Test with non-sensitive, short video clips first to confirm behavior and retention. 3) Ask the publisher for a homepage, privacy/data-retention policy, and clarification about the claimed config path access. 4) If you must provide a personal NEMO_TOKEN, verify it only grants the minimum required permissions and rotate/revoke it after testing. 5) If you don't trust the unknown domain or cannot get provenance, do not upload sensitive videos.

Getting Started

Share your video clips and I'll get started on A/B caption testing. Or just tell me what you're thinking.

Try saying:

• "compare my video clips"
• "export 1080p MP4"
• "test two caption styles on my"

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 AB — Test and Compare Caption Variants

Drop your video clips in the chat and tell me what you need. I'll handle the A/B caption testing 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 test two caption styles on my video and compare which performs better, 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 — keep both caption variants short so differences are easy to spot in playback.

Matching Input to Actions

User prompts referencing caption ab, 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.

All calls go to https://mega-api-prod.nemovideo.ai. The main endpoints:

1. Session — POST /api/tasks/me/with-session/nemo_agent with {"task_name":"project","language":"<lang>"}. Gives you a session_id.
2. Chat (SSE) — POST /run_sse with session_id and your message in new_message.parts[0].text. Set Accept: text/event-stream. Up to 15 min.
3. Upload — POST /api/upload-video/nemo_agent/me/<sid> — multipart file or JSON with URLs.
4. Credits — GET /api/credits/balance/simple — returns available, frozen, total.
5. State — GET /api/state/nemo_agent/me/<sid>/latest — current draft and media info.
6. Export — POST /api/render/proxy/lambda with render ID and draft JSON. Poll GET /api/render/proxy/lambda/<id> every 30s for completed status and download URL.

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

Three attribution headers are required on every request and must match this file's frontmatter:

Header	Value
X-Skill-Source	caption-ab
X-Skill-Version	frontmatter version
X-Skill-Platform	auto-detect: clawhub / cursor / unknown from install path

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

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)

Backend Response Translation

The backend assumes a GUI exists. Translate these into API actions:

Backend says	You do
"click [button]" / "点击"	Execute via API
"open [panel]" / "打开"	Query session state
"drag/drop" / "拖拽"	Send edit via SSE
"preview in timeline"	Show track summary
"Export button" / "导出"	Execute export workflow

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.

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

Common Workflows

Quick edit: Upload → "test two caption styles on my video and compare which performs better" → 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 "test two caption styles on my video and compare which performs better" — 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.