Recap Video

Turn a 2-hour event recording or five separate clip files into 1080p compiled recap video just by typing what you need. Whether it's condensing long event or...

Security Scan

The skill's behavior mostly matches a cloud-based video-compile tool, but there are inconsistencies in its metadata and it will automatically obtain/issue tokens and upload user video to a third-party service — you should be careful before installing or uploading sensitive files.

Purpose & Capability

The skill's name/description (cloud recap video compiler) align with the runtime instructions (upload clips, create session, render on nemovideo.ai). However the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) while the registry metadata stated no required config paths — this mismatch is unexplained and worth confirming with the publisher.

Instruction Scope

Instructions are narrowly scoped to creating sessions, uploading files, reading SSE streams, and starting renders against https://mega-api-prod.nemovideo.ai. That matches the described purpose. Important privacy-impacting behavior: the skill will upload user-provided videos to a third-party cloud service and will automatically obtain an anonymous token if no NEMO_TOKEN is supplied. The SKILL.md does not instruct reading unrelated system files beyond the (discrepant) config path.

Install Mechanism

No install spec and no code files — instruction-only. This minimizes on-disk execution risk because nothing in the skill will be written to disk by an installer.

Credentials

Only one env var (NEMO_TOKEN) is declared, which is proportionate to an API-backed service. However SKILL.md frontmatter includes a configPaths entry (~/.config/nemovideo/) that suggests possible access to local config; the registry listing omitted this. Also the skill will create an anonymous token via an API call if no NEMO_TOKEN is present, meaning it can operate without explicit user-provided credentials — reasonable for a free tier but worth noting that your uploads will still go to the remote service.

Persistence & Privilege

The skill does not request always:true, does not install anything, and does not ask to modify other skills or system-wide settings. It operates as a normal, non-persistent instruction-only skill.

Scan Findings in Context

[no_regex_findings] expected: The static scanner found nothing to analyze because this is an instruction-only skill with no code files. That is expected but not an assurance of safety — the runtime instructions themselves are the primary surface to review.

What to consider before installing

This skill uploads user video to a third-party domain (nemovideo.ai) and will use either a NEMO_TOKEN from the environment or obtain an anonymous token automatically. Before installing or using it: (1) confirm you trust the nemovideo.ai service and its privacy/data retention policy; do not upload sensitive or private video unless you are comfortable with remote processing; (2) ask the publisher to explain the metadata mismatch about ~/.config/nemovideo/ (is the skill going to read that directory?); (3) if you prefer control, provide your own NEMO_TOKEN from an account you manage rather than relying on anonymous tokens; and (4) verify the homepage, ownership, or documentation for the service — the skill's registry entry lists no homepage and an unknown source, which reduces transparency. If you need higher assurance, request the skill author supply a privacy/security statement or a verified service homepage before use.

Getting Started

Send me your video clips and I'll handle the AI highlight compilation. Or just describe what you're after.

Try saying:

• "create a 2-hour event recording or five separate clip files into a 1080p MP4"
• "create a 90-second recap of the key moments from this conference footage"
• "condensing long event or meeting footage into short highlight reels for marketers, event organizers, content 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.

Recap Video — Compile highlights into short videos

Drop your video clips in the chat and tell me what you need. I'll handle the AI highlight compilation on cloud GPUs — you don't need anything installed locally.

Here's a typical use: you send a a 2-hour event recording or five separate clip files, ask for create a 90-second recap of the key moments from this conference footage, and about 1-2 minutes later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — trimming your source footage to relevant sections before uploading speeds up processing significantly.

Matching Input to Actions

User prompts referencing recap 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.

Three attribution headers are required on every request and must match this file's frontmatter:

Header	Value
X-Skill-Source	recap-video
X-Skill-Version	frontmatter version
X-Skill-Platform	auto-detect: clawhub / cursor / unknown from install path

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

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.

Backend Response Translation

The backend assumes a GUI exists. Translate these into API actions:

Backend says	You do
"click [button]" / "点击"	Execute via API
"open [panel]" / "打开"	Query session state
"drag/drop" / "拖拽"	Send edit via SSE
"preview in timeline"	Show track summary
"Export button" / "导出"	Execute 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 "create a 90-second recap of the key moments from this conference footage" — 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 and presentation platforms.

Common Workflows

Quick edit: Upload → "create a 90-second recap of the key moments from this conference footage" → Download MP4. Takes 1-2 minutes 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.