Video Collage Maker

Skip the learning curve of professional editing software. Describe what you want — arrange my clips side by side in a 2x2 grid with background music — and ge...

Security Scan

The skill's requirements and runtime instructions are consistent with a cloud video-rendering service (it needs a service token and instructs uploading clips to a remote API), but there are a few minor metadata inconsistencies and privacy/usability points you should review before installing.

Purpose & Capability

The skill is a cloud-based video collage renderer and only requests a single service credential (NEMO_TOKEN) and interaction with a remote Nemovideo API — these needs align with the stated purpose. One minor inconsistency: the registry metadata lists no required config paths, but the SKILL.md frontmatter lists a config path (~/.config/nemovideo/). That mismatch should be clarified.

Instruction Scope

The SKILL.md instructs the agent to read NEMO_TOKEN or else obtain an anonymous token by POSTing to the Nemovideo auth endpoint, create sessions, upload user videos, start renders, and poll for results — all expected for this functionality. It does explicitly instruct uploading user media to an external service (core functionality). It also asks the agent to auto-detect an install path to set X-Skill-Platform, which is unclear for an instruction-only skill and may produce inconsistent header values ('unknown'), but this is not malicious.

Install Mechanism

No install spec and no code files: instruction-only. This is the lowest-risk install surface because nothing is written to disk by an installer. Network calls are required at runtime, which is expected.

Credentials

The skill only requires a single service credential (NEMO_TOKEN) and documents an anonymous-token flow if that env var is absent — proportionate to a cloud service. The discrepancy between the registry's 'no config paths' and the SKILL.md frontmatter listing ~/.config/nemovideo/ should be resolved. There are no other unrelated SECRET/TOKEN env vars requested.

Persistence & Privilege

always is false and the skill is user-invocable (normal). disable-model-invocation is false (also normal), which means the agent could call this skill autonomously; combined with the ability to upload user files to an external service, that creates a privacy consideration (the skill could be invoked without a user uploading files in some workflows). This is not a disqualifying privilege, but you should consider whether you want the agent to be allowed to call it autonomously.

Assessment

This skill appears to do what it says: it uploads user videos to Nemovideo's cloud service and returns rendered collages, and it needs a NEMO_TOKEN (or will create an anonymous token). Before installing, consider: (1) Privacy — user media will be transmitted to https://mega-api-prod.nemovideo.ai; confirm you trust that service and check their data retention/privacy policy. (2) Metadata mismatch — ask the skill author to clarify the config path (~/.config/nemovideo/) vs. the registry's 'none'. (3) Autonomy — if you are concerned about your agent sending files without an explicit user action, restrict autonomous invocation for this skill or require explicit user confirmation before uploads. (4) Token handling — the skill will obtain/hold session tokens; ensure your environment uses a scoped/anonymous token if you want to limit access. If these points are acceptable, the skill's footprint is coherent with its stated purpose.

Getting Started

Share your multiple video clips and I'll get started on AI collage assembly. Or just tell me what you're thinking.

Try saying:

• "combine my multiple video clips"
• "export 1080p MP4"
• "arrange my clips side by side"

Quick Start Setup

This skill connects to a cloud processing backend. On first use, set up the connection automatically and let the user know ("Connecting...").

Token check: Look for NEMO_TOKEN in the environment. If found, skip to session creation. Otherwise:

• Generate a UUID as client identifier
• POST https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with X-Client-Id header
• Extract data.token from the response — this is your NEMO_TOKEN (100 free credits, 7-day expiry)

Session: POST https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Keep the returned session_id for all operations.

Let the user know with a brief "Ready!" when setup is complete. Don't expose tokens or raw API output.

Video Collage Maker — Combine Clips into One Video

Send me your multiple video clips and describe the result you want. The AI collage assembly runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload five 10-second vacation clips, type "arrange my clips side by side in a 2x2 grid with background music", and you'll get a 1080p MP4 back in roughly 30-60 seconds. All rendering happens server-side.

Worth noting: keep individual clips under 30 seconds for faster processing and cleaner grid layouts.

Matching Input to Actions

User prompts referencing video collage maker, 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	video-collage-maker
X-Skill-Version	frontmatter version
X-Skill-Platform	auto-detect: clawhub / cursor / unknown from install path

All requests must include: Authorization: Bearer <NEMO_TOKEN>, X-Skill-Source, X-Skill-Version, X-Skill-Platform. Missing attribution headers will cause export to fail with 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 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 "arrange my clips side by side in a 2x2 grid with background music" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across social platforms.

Common Workflows

Quick edit: Upload → "arrange my clips side by side in a 2x2 grid with background music" → 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.