Caption Generator Downfall

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

Security Scan

The skill's requirements and instructions generally match its stated purpose (calling a nemo video API with a NEMO_TOKEN), but there are small metadata inconsistencies and privacy/credential considerations you should review before use.

Purpose & Capability

The skill is described as a cloud caption-removal tool and its instructions call nemo-video endpoints and require a NEMO_TOKEN — this is coherent. However, the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) while the registry metadata showed none; that mismatch is unexplained but not obviously malicious.

Instruction Scope

Runtime instructions stay within the expected scope (connect to the nemo API, create a session, upload video files, poll export). The skill provides a fallback anonymous-token flow if NEMO_TOKEN is absent. It also asks to include attribution headers derived from an install path (e.g., ~/.clawhub/) which implies reading/detecting install context; the SKILL.md does not instruct reading unrelated system files, but the install-path header derivation is a small scope expansion worth noting.

Install Mechanism

Instruction-only skill with no install spec and no code files. No binaries or downloads are requested, which minimizes install-time risk.

Credentials

Only one credential (NEMO_TOKEN) is declared as required, which is reasonable for a cloud API. The instructions also allow obtaining an anonymous temporary token. Still, NEMO_TOKEN grants access to upload and render operations and possibly credits, so using a primary account token without checking provider policies is a privacy/credential risk. Also note the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) that isn't reflected elsewhere.

Persistence & Privilege

The skill is not force-included (always:false) and does not request elevated system persistence. It uses standard session tokens for server-side jobs; no instructions to modify other skills or system-wide configuration were found.

Assessment

This skill appears to do what it says: it uploads videos to nemovideo.ai, edits/removes captions on cloud GPUs, and returns a downloadable MP4, and it only needs a NEMO_TOKEN. Before installing, verify you trust the nemo service (uploads contain your media), avoid supplying a primary or highly-privileged account token — use a throwaway or anonymous token to test, and review the provider's privacy and retention policies. Note the small inconsistencies: SKILL.md frontmatter references a config path (~/.config/nemovideo/) and install-path-derived attribution headers; ask the publisher to clarify why those are needed if you’re uncomfortable. If you want higher assurance, request source/origin information (homepage or repository) and a privacy/data-retention policy from the skill author before using with sensitive content.

Getting Started

Ready when you are. Drop your video clips here or describe what you want to make.

Try saying:

• "remove a 2-minute YouTube video with burned-in captions into a 1080p MP4"
• "remove or disable the auto-generated captions from this video"
• "removing unwanted captions from existing videos for content 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 Downfall — Remove or Fix Video Captions

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

Here's a typical use: you send a a 2-minute YouTube video with burned-in captions, ask for remove or disable the auto-generated captions from this video, and about 30-60 seconds later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — if captions are burned in rather than a separate track, re-export from source without the subtitle layer for cleaner results.

Matching Input to Actions

User prompts referencing caption generator downfall, 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.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is caption-generator-downfall, 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).

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)

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

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 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

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "remove or disable the auto-generated captions from this video" — concrete instructions get better results.

Max file size is 500MB. Stick to MP4, MOV, AVI, WebM for the smoothest experience.

Export as MP4 with H.264 codec for widest platform compatibility.

Common Workflows

Quick edit: Upload → "remove or disable the auto-generated captions from this video" → 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.