Ai Sports Highlight

generate raw sports footage into sports highlight reel with this skill. Works with MP4, MOV, AVI, MTS files up to 500MB. coaches, athletes, sports content cr...

Security Scan

The skill's requests and runtime instructions are consistent with a cloud video highlight service: it needs a single service token and uploads user footage to a remote renderer; nothing in the artifact suggests it is doing unrelated or covert actions.

Purpose & Capability

Name/description (generate highlight reels from uploaded video) match the declared requirement for a NEMO_TOKEN and the API endpoints listed in SKILL.md. The only minor inconsistency is that the registry metadata reported no required config paths while the skill's own frontmatter lists ~/.config/nemovideo/ — this appears to be a metadata mismatch but does not change the core capability.

Instruction Scope

SKILL.md explicitly instructs the agent to upload user video files and to call nemovideo.ai endpoints (session creation, SSE chat, upload, export, state, credits). Those calls and the anonymous-token fallback are coherent for the stated task. Two things to note: (1) the skill instructs detection of an install path to set an X-Skill-Platform header — that implies the runtime may probe its environment to determine an install location, which is not strictly necessary for video processing; (2) the skill instructs to hide technical details from users and to use the environment token if present, which is normal but means tokens will be used transparently. Both are not inherently malicious but are worth knowing.

Install Mechanism

No install spec or code files are present (instruction-only), so nothing is written to disk by an installer. This is the lowest-risk install posture.

Credentials

Only a single credential (NEMO_TOKEN) is declared as required and is appropriate for a hosted rendering API. However, the SKILL.md frontmatter lists a configPaths entry (~/.config/nemovideo/) while the registry record showed no required config paths; this mismatch should be clarified because reading that config path could reveal local credentials or config. Otherwise the environment access requested is proportionate.

Persistence & Privilege

always is false and the skill does not request persistent system-wide privileges or to modify other skills. Session tokens are used for the service and that is normal for a remote-rendering integration.

Assessment

This skill appears to do what it says: it uploads your video to a nemovideo.ai cloud service and returns rendered highlight MP4 files. Before installing/using it, consider: (1) Privacy — your raw footage will be uploaded to https://mega-api-prod.nemovideo.ai; don't send sensitive or private content unless you trust the service and have reviewed its privacy terms. (2) Token management — provide a dedicated NEMO_TOKEN with minimal scope if possible; if you rely on the anonymous-token fallback the skill will call the anonymous auth endpoint and use a 7-day limited token. (3) Metadata mismatch — the SKILL.md mentions a config path (~/.config/nemovideo/) even though the registry listed none; ask the publisher to confirm whether the skill will read that local config directory. (4) Test with non-sensitive sample footage first. If you need stronger guarantees, request the publisher's homepage, documentation, or a signed provenance claim before using with real content.

Getting Started

Share your raw sports footage and I'll get started on AI highlight extraction. Or just tell me what you're thinking.

Try saying:

• "generate my raw sports footage"
• "export 1080p MP4"
• "extract the best plays and compile"

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.

AI Sports Highlight — Generate Sports Highlight Reels Fast

Send me your raw sports footage and describe the result you want. The AI highlight extraction runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 90-minute basketball game recording, type "extract the best plays and compile them into a 2-minute highlight reel", and you'll get a 1080p MP4 back in roughly 1-2 minutes. All rendering happens server-side.

Worth noting: trimming your footage to the relevant game period before uploading speeds up processing significantly.

Matching Input to Actions

User prompts referencing ai sports highlight, 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.

All calls go to https://mega-api-prod.nemovideo.ai. The main endpoints:

1. Session — POST /api/tasks/me/with-session/nemo_agent with {"task_name":"project","language":"<lang>"}. Gives you a session_id.
2. Chat (SSE) — POST /run_sse with session_id and your message in new_message.parts[0].text. Set Accept: text/event-stream. Up to 15 min.
3. Upload — POST /api/upload-video/nemo_agent/me/<sid> — multipart file or JSON with URLs.
4. Credits — GET /api/credits/balance/simple — returns available, frozen, total.
5. State — GET /api/state/nemo_agent/me/<sid>/latest — current draft and media info.
6. Export — POST /api/render/proxy/lambda with render ID and draft JSON. Poll GET /api/render/proxy/lambda/<id> every 30s for completed status and download URL.

Formats: 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 ai-sports-highlight, 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).

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.

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)

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

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.

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

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "extract the best plays and compile them into a 2-minute highlight reel" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across social platforms and video hosting sites.

Common Workflows

Quick edit: Upload → "extract the best plays and compile them into a 2-minute highlight reel" → 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.