Video Caption Remover

Skip the learning curve of professional editing software. Describe what you want — remove the hardcoded captions from the bottom of this video — and get clea...

Security Scan

The skill's requirements and runtime instructions largely match its stated purpose (calling a remote video-processing API using a token), but there are a few minor metadata inconsistencies and privacy trade-offs to be aware of.

Purpose & Capability

The skill claims to remove burned-in captions via a remote service and only requires a single token (NEMO_TOKEN) for that API — this is proportionate. However, the SKILL.md frontmatter includes a configPaths entry (~/.config/nemovideo/) that is not reflected in the registry metadata; that suggests the skill may expect local config access even though the registry did not declare it.

Instruction Scope

The instructions are focused on establishing a session, uploading video files or URLs, handling SSE streams, and polling render status — all consistent with a cloud-render workflow. The skill explicitly instructs obtaining an anonymous token if no NEMO_TOKEN is present (i.e., contacting the vendor to mint a token). The agent will upload user videos to an external server (expected for this service) — note this transmits potentially sensitive media off-device.

Install Mechanism

No install spec and no code files — instruction-only. This minimizes filesystem/installation risk.

Credentials

Only one environment credential (NEMO_TOKEN) is required which aligns with contacting the remote API. The SKILL.md frontmatter also indicates a config path (~/.config/nemovideo/) which was not declared in the registry; it's unclear whether the skill will try to read local config files. The agent will also generate/obtain an anonymous token if none is provided (expected behavior but worth noting).

Persistence & Privilege

The skill is not always-enabled and does not request elevated or persistent platform privileges. There is no install that modifies other skills or system-wide settings.

Assessment

This skill appears to do what it says: it uploads videos to a remote rendering API and returns processed files. Before using it, consider: 1) Privacy: your videos are uploaded to https://mega-api-prod.nemovideo.ai — do not send sensitive or private footage unless you trust the service and reviewed its terms/privacy policy. 2) Credentials: the skill uses a single token (NEMO_TOKEN); only provide a token you control and trust. If you don't set one, the skill will request an anonymous token from the vendor automatically (100 free credits). 3) Metadata mismatch: SKILL.md mentions a local config path (~/.config/nemovideo/) but the registry did not declare this — ask the author whether the agent will read local config files. 4) No install is required, so no files are written to your agent by the skill itself. If you need higher assurance, verify the service domain, review the vendor's docs or privacy policy, and avoid uploading content you cannot share.

Getting Started

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

Try saying:

• "remove a 2-minute YouTube video with burned-in subtitles into a 1080p MP4"
• "remove the hardcoded captions from the bottom of this video"
• "removing hardcoded subtitles from existing videos for content creators and video editors"

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.

Video Caption Remover — Remove Hardcoded Captions from Videos

Send me your captioned video files and describe the result you want. The AI caption removal runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 2-minute YouTube video with burned-in subtitles, type "remove the hardcoded captions from the bottom of this video", and you'll get a 1080p MP4 back in roughly 30-90 seconds. All rendering happens server-side.

Worth noting: videos with high contrast between caption text and background produce the cleanest results.

Matching Input to Actions

User prompts referencing video caption remover, 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.

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

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

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.

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.

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

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)

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 the hardcoded captions from the bottom of 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 for widest compatibility.

Common Workflows

Quick edit: Upload → "remove the hardcoded captions from the bottom of this video" → Download MP4. Takes 30-90 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.