Caption Generator From Photo

Skip the learning curve of professional editing software. Describe what you want — generate a caption for this photo and overlay it as a short video — and ge...

Security Scan

The skill's requirements and runtime instructions are consistent with a cloud-based caption/video rendering service: it needs a single service token and the SKILL.md only instructs calls to that backend and upload of user images.

Purpose & Capability

Name/description (generate captions and overlay on photos to produce short videos) align with the declared primary credential (NEMO_TOKEN) and the SKILL.md endpoints (nemovideo API). One minor inconsistency: the registry metadata reported no required config paths, but the SKILL.md frontmatter mentions ~/.config/nemovideo/ in metadata; this is likely a documentation mismatch but worth noting.

Instruction Scope

Instructions stay within the stated purpose: establish a session with the nemovideo API, upload user-provided media, stream render events, and poll for exports. The SKILL.md does not instruct reading arbitrary local files or unrelated environment variables. A small note: the doc says X-Skill-Platform is 'detected from the install path' (examples like ~/.clawhub/ or ~/.cursor/skills/); it's not explicit whether the agent must read those paths to build the header — if implemented, that could require reading the agent's install location, so confirm implementation does not attempt to read unrelated user files.

Install Mechanism

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

Credentials

Only one credential is requested (NEMO_TOKEN) and it's clearly used for authorization to the described backend. The SKILL.md documents a fallback anonymous-token call when NEMO_TOKEN is absent, which is consistent with the service. The earlier mismatch about configPaths appearing in frontmatter but not in registry metadata is noted but does not by itself indicate extraneous credential requests.

Persistence & Privilege

No always:true, no persistent installs or modifications to other skills. The skill manages short-lived sessions with the remote renderer; that behavior is expected for this functionality.

Assessment

This skill looks coherent for a cloud caption/video rendering integration and only needs a NEMO_TOKEN (or it will obtain a short-lived anonymous token from the listed domain). Before installing or using it, consider: 1) Confirm you trust https://mega-api-prod.nemovideo.ai and review their privacy/retention policy for uploaded images (you are uploading media to a third party). 2) Prefer providing a scoped service token rather than a long-lived credential. 3) Ask the implementer whether the agent will read local install paths to produce the X-Skill-Platform header — if so, request they limit file reads to the minimum required. 4) Note the small metadata mismatch (configPaths present in SKILL.md but not in registry metadata); ask the publisher to clarify. If any of these are unresolved, treat the skill as higher risk.

Getting Started

Got photos or images to work with? Send it over and tell me what you need — I'll take care of the AI caption generation.

Try saying:

• "generate a single product photo or portrait image into a 1080p MP4"
• "generate a caption for this photo and overlay it as a short video"
• "turning photos into short captioned videos for social media for social media 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 From Photo — Turn Photos Into Captioned Videos

Send me your photos or images 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 single product photo or portrait image, type "generate a caption for this photo and overlay it as a short video", and you'll get a 1080p MP4 back in roughly 20-40 seconds. All rendering happens server-side.

Worth noting: high-contrast images produce cleaner caption overlays with better readability.

Matching Input to Actions

User prompts referencing caption generator from photo, 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.

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

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

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 a caption for this photo and overlay it as a short video" — concrete instructions get better results.

Max file size is 200MB. Stick to JPG, PNG, WEBP, HEIC for the smoothest experience.

Export as MP4 for widest compatibility across social platforms.

Common Workflows

Quick edit: Upload → "generate a caption for this photo and overlay it as a short 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.