Social Caption

add social media video into captioned social videos with this skill. Works with MP4, MOV, WebM, AVI files up to 500MB. TikTok and Instagram creators use it f...

Security Scan

The skill’s network actions (uploading videos, creating anonymous tokens, and starting cloud render jobs) match its stated purpose, but there are inconsistencies and unclear persistence instructions (config path vs registry metadata and where session/token is stored) that deserve clarification before installing.

Purpose & Capability

The name/description (auto-captioning social videos) aligns with the endpoints and actions described (upload, SSE editing, render). Requested credential NEMO_TOKEN is appropriate for an API-backed service. However, the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) while registry metadata earlier reported no required config paths — that mismatch is unexplained.

Instruction Scope

Instructions are mostly within scope: upload user files, start sessions, stream SSE, poll render status, and return download URLs. The skill also instructs auto-creating an anonymous token if NEMO_TOKEN is absent, and to include specific attribution headers on every request. It asks to 'auto-detect' platform from the install path (which implies reading filesystem/install location). None of this is inherently out-of-scope, but the guidance about storing session_id and the requirement to infer install path are underspecified and could lead to the agent reading/writing config or install paths without clear user consent.

Install Mechanism

This is an instruction-only skill with no install spec and no code files — minimal file-system/install risk. Network calls to a named API host are expected for the described functionality.

Credentials

Only a single credential (NEMO_TOKEN) is declared, which is appropriate. The skill will auto-request an anonymous token if none is present, which is consistent. Still, the frontmatter/config-path hint suggests the skill may persist tokens or session state on disk (e.g., ~/.config/nemovideo/), and the registry metadata does not declare that — this is a proportionality/visibility concern.

Persistence & Privilege

always:false and autonomous invocation are normal. The concern is that SKILL.md explicitly tells the agent to 'store the returned session_id' and frontmatter references a user config path. It's unclear whether stored session/token data will be ephemeral in agent memory or written to ~/.config/nemovideo/, and the registry metadata conflictingly declared no config paths. Persistent storage of tokens or session IDs without explicit user consent increases retention and exfiltration risk.

What to consider before installing

Before installing, understand that this skill uploads your video files to a third-party service (mega-api-prod.nemovideo.ai) and will create or use an API token (NEMO_TOKEN). Ask the publisher to clarify (1) whether session tokens or credentials are written to disk and exactly where (the SKILL.md mentions ~/.config/nemovideo/ but registry metadata did not), (2) how long uploads and generated media are retained and whether they are shared internally, and (3) why the agent must auto-detect the install path (what filesystem reads are required). If you plan to process sensitive videos, do not install until you confirm storage/retention policies and where tokens/sessions are saved. If you want to proceed, prefer temporary/ephemeral tokens and explicit user consent before writing anything to disk.

Getting Started

Share your social media video and I'll get started on AI caption generation. Or just tell me what you're thinking.

Try saying:

• "add my social media video"
• "export 1080p MP4"
• "add bold captions synced to speech"

First-Time Connection

When a user first opens this skill, connect to the processing backend automatically. Briefly let them know (e.g. "Setting up...").

Authentication: Check if NEMO_TOKEN is set in the environment. If it is, skip to step 2.

1. Obtain a free token: Generate a random UUID as client identifier. POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id set to that UUID. The response data.token is your NEMO_TOKEN — 100 free credits, valid 7 days.
2. Create a session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Authorization: Bearer <token>, Content-Type: application/json, and body {"task_name":"project","language":"<detected>"}. Store the returned session_id for all subsequent requests.

Keep setup communication brief. Don't display raw API responses or token values to the user.

Social Caption — Add Captions to Social Videos

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

A quick example: upload a 30-second Instagram reel or TikTok clip, type "add bold captions synced to speech for my TikTok video", and you'll get a 1080p MP4 back in roughly 20-40 seconds. All rendering happens server-side.

Worth noting: vertical 9:16 video works perfectly for Reels and TikTok exports.

Matching Input to Actions

User prompts referencing social caption, 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.

Base URL: https://mega-api-prod.nemovideo.ai

Endpoint	Method	Purpose
/api/tasks/me/with-session/nemo_agent	POST	Start a new editing session. Body: {"task_name":"project","language":"<lang>"}. Returns session_id.
/run_sse	POST	Send a user message. Body includes app_name, session_id, new_message. Stream response with Accept: text/event-stream. Timeout: 15 min.
/api/upload-video/nemo_agent/me/<sid>	POST	Upload a file (multipart) or URL.
/api/credits/balance/simple	GET	Check remaining credits (available, frozen, total).
/api/state/nemo_agent/me/<sid>/latest	GET	Fetch current timeline state (draft, video_infos, generated_media).
/api/render/proxy/lambda	POST	Start export. Body: {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll status every 30s.

Accepted file types: 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	social-caption
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.

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

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 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)

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "add bold captions synced to speech for my TikTok video" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across all social platforms.

Common Workflows

Quick edit: Upload → "add bold captions synced to speech for my TikTok video" → 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.