Caption Generator Meme

generate images or video into captioned meme videos with this skill. Works with MP4, MOV, GIF, WebM files up to 200MB. TikTok creators use it for adding AI-g...

Security Scan

The skill's declared purpose (adding meme captions to videos) matches its runtime instructions, but there are small inconsistencies and trust decisions (unknown external service, mismatched metadata, implicit filesystem detection) you should understand before installing.

Purpose & Capability

Name/description match the endpoints and actions described: uploading media, creating a session, streaming SSE edits, and starting cloud renders. Requesting a single service token (NEMO_TOKEN) is coherent for a cloud video-processing API.

Instruction Scope

SKILL.md instructs the agent to obtain or use NEMO_TOKEN, create sessions, upload files, stream SSE, poll state, and include attribution headers. These are appropriate for the stated purpose. Two items to note: (1) the skill asks callers to "auto-detect" an install path to set X-Skill-Platform which implies reading the agent's install location or filesystem (not explicitly declared), and (2) it instructs saving session_id and using tokens — ensure token/session handling matches your privacy policies.

Install Mechanism

No install spec and no code files: instruction-only skill — nothing is written to disk by an installer. This is the lowest-risk install mechanism.

Credentials

Only one credential is requested (NEMO_TOKEN), which is appropriate. However SKILL.md frontmatter metadata includes a config path (~/.config/nemovideo/) while the registry manifest reported no required config paths — that's an inconsistency. Also the skill will call an external domain (mega-api-prod.nemovideo.ai) and will POST/stream user media and session tokens there; ensure you trust that service before sending media or tokens.

Persistence & Privilege

always:false and no install-time persistence; agent may store a session_id during a session which is normal. The skill does not request elevated or cross-skill config changes.

What to consider before installing

This skill appears to do what it says (upload media, create a session, return a captioned video) and only asks for one token, but review these before installing: - Trust the remote service: the API host (mega-api-prod.nemovideo.ai) and the skill have no public source or homepage listed. If you will upload private videos, verify the service's privacy policy and provenance. - Metadata mismatch: the SKILL.md metadata lists a config path (~/.config/nemovideo/) though the registry manifest did not — ask the publisher whether the skill will read that directory and why. - Filesystem access: the instruction to "auto-detect" platform from an install path likely requires reading agent/install paths. If you want to limit exposure, run the skill in a sandboxed environment or deny filesystem access. - Token handling: the skill can request an anonymous token on first use; do not paste or log tokens. Make sure NEMO_TOKEN is scoped only to this service and not reused for other services. If you need higher assurance, ask the publisher for source code or an official homepage and for explicit confirmation of what local paths the skill reads. If you proceed, avoid sending sensitive videos until you're comfortable with the remote service.

Getting Started

Send me your images or video and I'll handle the AI meme caption generation. Or just describe what you're after.

Try saying:

• "generate a 10-second video clip of a cat sliding off a table into a 1080p MP4"
• "generate funny meme captions and overlay them on my video automatically"
• "adding AI-generated meme captions to funny video clips for TikTok creators"

Automatic Setup

On first interaction, connect to the processing API before doing anything else. Show a brief status like "Setting things up...".

Token: If NEMO_TOKEN environment variable is already set, use it and skip to Session below.

Free token: Generate a UUID as client identifier, then POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id: <uuid>. The response field data.token becomes your NEMO_TOKEN (100 credits, 7-day expiry).

Session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Save session_id from the response.

Confirm to the user you're connected and ready. Don't print tokens or raw JSON.

Caption Generator Meme — Add Meme Captions to Videos

This tool takes your images or video and runs AI meme caption generation through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a 10-second video clip of a cat sliding off a table and want to generate funny meme captions and overlay them on my video automatically — the backend processes it in about 20-40 seconds and hands you a 1080p MP4.

Tip: shorter clips under 15 seconds produce the most on-point meme captions.

Matching Input to Actions

User prompts referencing caption generator meme, 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	caption-generator-meme
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 "generate funny meme captions and overlay them on my video automatically" — concrete instructions get better results.

Max file size is 200MB. Stick to MP4, MOV, GIF, WebM for the smoothest experience.

Export as MP4 for widest compatibility across social platforms.

Common Workflows

Quick edit: Upload → "generate funny meme captions and overlay them on my video automatically" → 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.