Photographer Video

Turn 20 wedding or portrait photos in JPEG format into 1080p photo slideshow video just by typing what you need. Whether it's turning photo shoots into share...

Security Scan

The skill's declared need for a single NEMO_TOKEN mostly fits its purpose, but inconsistent metadata and a few instructions that probe the local environment and call an external, unvetted API make the package worth caution.

Purpose & Capability

The skill's stated purpose (turn JPEG photos into 1080p slideshow videos) matches the runtime instructions (upload files, create session, render, download). Requesting a NEMO_TOKEN as the primary credential is proportionate for a cloud rendering service. However, the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) that is not listed in the registry 'Required config paths'—an inconsistency worth flagging.

Instruction Scope

Instructions tell the agent to read the NEMO_TOKEN environment variable (declared) and to POST to an external API to obtain an anonymous token if none exists (reasonable). They also instruct the agent to detect the install path to set an X-Skill-Platform header (inspecting ~/.clawhub/, ~/.cursor/skills/, etc.). That implies the agent may probe the local filesystem or environment to determine install location — a small scope creep beyond pure upload/HTTP behavior. The instructions also tell the agent to include attribution headers and to hide technical details from the user; hiding implementation details is not malicious by itself but reduces transparency.

Install Mechanism

No install spec or code files are included (instruction-only). That reduces surface area because nothing will be written to disk by an installer. There is no download-from-URL or package install behavior to evaluate.

Credentials

Only one environment variable (NEMO_TOKEN) is declared and used, which is proportionate. The SKILL.md also references a config path in its metadata, which conflicts with registry metadata that lists no required config paths; this discrepancy could indicate either stale metadata or an undeclared requirement to access ~/.config/nemovideo/. The skill will also generate a UUID and call the anonymous-token endpoint if no token exists — this behavior will result in temporary tokens being stored in-memory but the spec doesn't say whether the agent will persist them to disk.

Persistence & Privilege

always:false and normal autonomous invocation settings. The skill does not request permanent presence or elevated platform-wide privileges. There is no instruction to modify other skills or global agent configuration.

What to consider before installing

This skill mostly does what its name promises, but proceed with caution. It will upload your photos to an external backend (mega-api-prod.nemovideo.ai) and either use a NEMO_TOKEN you provide or obtain a short-lived anonymous token for you — make sure you trust that service before sending private images. Ask the publisher to clarify the metadata mismatch (SKILL.md lists ~/.config/nemovideo/ but the registry shows no required config paths) and whether any tokens are persisted to disk. If you want to test safely: (1) try with non-sensitive sample images, (2) do not provide long-lived credentials — use a throwaway/limited token if possible, and (3) verify the service's privacy policy and where media are stored. If you need high assurance, request the skill author to remove the file-system install-path detection or explain why it's necessary.

Getting Started

Got photo collections to work with? Send it over and tell me what you need — I'll take care of the AI slideshow creation.

Try saying:

• "turn 20 wedding or portrait photos in JPEG format into a 1080p MP4"
• "turn my portrait photos into a cinematic video with music and transitions"
• "turning photo shoots into shareable video reels for photographers"

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.

Photographer Video — Turn Photos Into Shareable Videos

This tool takes your photo collections and runs AI slideshow creation through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have 20 wedding or portrait photos in JPEG format and want to turn my portrait photos into a cinematic video with music and transitions — the backend processes it in about 30-60 seconds and hands you a 1080p MP4.

Tip: grouping photos by scene or lighting makes transitions look more natural.

Matching Input to Actions

User prompts referencing photographer video, 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 photographer-video, 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).

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

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

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.

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 JSON uses short keys: t for tracks, tt for track type (0=video, 1=audio, 7=text), sg for segments, d for duration in ms, m for metadata.

Example timeline summary:

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 "turn my portrait photos into a cinematic video with music and transitions" — concrete instructions get better results.

Max file size is 500MB. Stick to JPG, PNG, HEIC, RAW for the smoothest experience.

Export as MP4 for widest compatibility across social and client delivery platforms.

Common Workflows

Quick edit: Upload → "turn my portrait photos into a cinematic video with music and transitions" → Download MP4. Takes 30-60 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.