Lapse Video

Turn 200 JPEG photos taken every 30 seconds into 1080p timelapse MP4 video just by typing what you need. Whether it's turning photo sequences into timelapse...

Security Scan

The skill's declared purpose (cloud timelapse rendering) matches what its instructions request (an API token, session creation, uploads, render calls), with no extra unrelated credentials or installs, though there are a few small inconsistencies worth noting.

Purpose & Capability

The skill converts photo sequences into timelapse videos via the nemovideo cloud API; requiring a NEMO_TOKEN and calling render/upload endpoints is coherent with that purpose. One minor mismatch: the registry metadata listed no config paths, but the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) — this is small but inconsistent.

Instruction Scope

SKILL.md provides concrete API flows: acquire or use NEMO_TOKEN, create session, upload files, use SSE, poll status, and include attribution headers. It also asks the agent to read the skill's YAML frontmatter and detect install path to set X-Skill-Platform; that requires local filesystem access to determine an install path and is out of the core 'upload/convert/download' happy-path but not disproportionate. The instructions telling the agent to 'keep technical details out of the chat' are operational guidance but not harmful.

Install Mechanism

Instruction-only skill with no install spec or code files — lowest-risk install surface. No downloads or package installs are requested.

Credentials

Only NEMO_TOKEN is declared as required (primary credential). The token is appropriate for a cloud rendering API. The skill will also generate an anonymous token if none is provided, which doesn't require extra secrets. No other unrelated secrets or keys are requested.

Persistence & Privilege

always:false and normal autonomous invocation defaults. The skill does not request persistent system-wide changes or elevated privileges. It does instruct session management and will hold short-lived session/render IDs, which is expected.

Assessment

This skill appears to do what it says: it uploads your images to a third‑party service (mega-api-prod.nemovideo.ai) and returns rendered MP4s. Before installing or using it, consider: (1) NEMO_TOKEN grants the skill access to your nemovideo account/credits—only provide a token if you trust that service; (2) images are uploaded to an external cloud service, so don't send sensitive photos you wouldn't want uploaded; (3) the skill may read its own SKILL.md frontmatter and attempt to detect install paths (filesystem access) to set attribution headers — ensure your agent runtime permissions are acceptable; (4) there is a small metadata inconsistency about a config path in SKILL.md vs the registry entry — not necessarily malicious but worth noting. If you need stronger assurance, ask the publisher for a homepage or official docs and confirm the API hostname and token scopes.

Getting Started

Share your sequential images and I'll get started on timelapse video creation. Or just tell me what you're thinking.

Try saying:

• "convert my sequential images"
• "export 1080p MP4"
• "combine these photos into a 30-second"

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.

Lapse Video — Convert Photos into Timelapse Videos

This tool takes your sequential images and runs timelapse video creation through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have 200 JPEG photos taken every 30 seconds and want to combine these photos into a 30-second timelapse at 24fps — the backend processes it in about 30-60 seconds and hands you a 1080p MP4.

Tip: evenly spaced photo intervals produce the smoothest timelapse playback.

Matching Input to Actions

User prompts referencing lapse 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.

Skill attribution — read from this file's YAML frontmatter at runtime:

• X-Skill-Source: lapse-video
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

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

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 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 "combine these photos into a 30-second timelapse at 24fps" — concrete instructions get better results.

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

Export as MP4 with H.264 codec for widest compatibility across platforms.

Common Workflows

Quick edit: Upload → "combine these photos into a 30-second timelapse at 24fps" → 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.