Instagram Video Caption Download

Turn a 60-second Instagram Reel with spoken dialogue into 1080p captioned video files just by typing what you need. Whether it's downloading captions from In...

Security Scan

The skill's runtime instructions largely match its stated purpose (upload a Reel, run server-side captioning, return a rendered file), but there are small inconsistencies and missing provenance (metadata mismatch, unknown source/homepage) and it will send user videos to a third-party API — review before use.

Purpose & Capability

The skill describes extracting captions and rendering captioned video via a remote GPU service and only requests a single API token (NEMO_TOKEN), which is consistent with the described functionality. However, the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) while the registry metadata reported no required config paths — this mismatch is unexplained and worth verifying.

Instruction Scope

The instructions are detailed and remain within the stated purpose: they instruct the agent to use NEMO_TOKEN (or obtain an anonymous token), create a session, upload media, drive SSE chat/editing, poll export endpoints, and return download URLs. This requires transmitting user videos and metadata to https://mega-api-prod.nemovideo.ai, which is expected for a cloud-rendering service but is a privacy/consent concern (user media leaves the local machine). No instructions appear to read unrelated system files or extra environment variables.

Install Mechanism

Instruction-only skill with no install spec or downloaded code — lowest installation risk. Nothing is written to disk by the skill itself.

Credentials

Only NEMO_TOKEN is required (declared as primary), which fits the purpose. The SKILL.md also suggests a config path in its metadata (~/.config/nemovideo/), which would grant access to local config if used — that was not declared in the registry fields and is inconsistent. The skill also instructs to obtain an anonymous token via a network call if no token is present, which is reasonable but means the agent will perform external network requests automatically.

Persistence & Privilege

The skill is not always-enabled and does not request elevated platform privileges. It does not attempt to modify other skills or system-wide settings in its instructions.

What to consider before installing

This skill appears to do what it says (upload a short Instagram video to a remote service to extract captions and return a rendered file), but review the following before installing or running it: - Source and provenance: the skill has no listed homepage or source repo. That makes it harder to verify the remote service (nemovideo.ai) and the operator. Prefer skills from known publishers or with a public repo. - Data exfiltration/privacy: using the skill uploads your video and audio to https://mega-api-prod.nemovideo.ai. Do not use it with private/sensitive content unless you trust that service and its retention/privacy policies. - Token handling: the skill expects NEMO_TOKEN (or will request an anonymous token by POSTing to the service). Be cautious about supplying long-lived tokens; if you provide one, ensure it has only the needed scope. If you let it acquire an anonymous token, know that agent-initiated network calls will occur automatically. - Metadata mismatch: the SKILL.md frontmatter references a local config path (~/.config/nemovideo/) that is not declared in the registry metadata — ask the publisher to clarify whether the skill reads or writes local config. If you want to proceed: ask the publisher for a homepage or repo, confirm the service's privacy/retention policy, and prefer using ephemeral anonymous tokens rather than permanent credentials. If you have very sensitive videos, do not use this skill.

Getting Started

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

Try saying:

• "extract a 60-second Instagram Reel with spoken dialogue into a 1080p MP4"
• "extract and download the captions from this Instagram video as a text or SRT file"
• "downloading captions from Instagram videos for reuse or editing for Instagram 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.

Instagram Video Caption Download — Extract and Download Video Captions

Send me your Instagram video and describe the result you want. The caption extraction download runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 60-second Instagram Reel with spoken dialogue, type "extract and download the captions from this Instagram video as a text or SRT file", and you'll get a 1080p MP4 back in roughly 20-40 seconds. All rendering happens server-side.

Worth noting: shorter clips under 60 seconds process and export captions faster.

Matching Input to Actions

User prompts referencing instagram video caption download, 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	instagram-video-caption-download
X-Skill-Version	frontmatter version
X-Skill-Platform	auto-detect: clawhub / cursor / unknown from install path

Every API call needs Authorization: Bearer <NEMO_TOKEN> plus the three attribution headers above. If any header is missing, exports return 402.

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)

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 → "extract and download the captions from this Instagram video as a text or SRT file" → 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 "extract and download the captions from this Instagram video as a text or SRT file" — 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 Instagram and other platforms.