Sports Highlight Ai

generate raw game footage into highlight reel clips with this skill. Works with MP4, MOV, AVI, MKV files up to 500MB. coaches, sports creators, team managers...

Security Scan

The skill's behavior (uploading user videos and using a NEMO_TOKEN to call an external API) is coherent with its goal, but provenance gaps and small inconsistencies (frontmatter vs registry metadata, no homepage/source) mean you should proceed cautiously before installing or uploading sensitive footage.

Purpose & Capability

The skill's declared purpose (turn raw game footage into highlight reels) matches the actions described (upload video, create session, run render/export, return download URL). Requiring a NEMO_TOKEN is appropriate for a third‑party API. However, SKILL.md frontmatter lists a config path (~/.config/nemovideo/) while the registry metadata showed no required config paths — this mismatch in declared requirements is an inconsistency and provenance is unknown (no homepage/source).

Instruction Scope

The instructions clearly direct the agent to obtain/accept a token, create a session, upload user-supplied video files (multipart or URL), stream SSE, poll status, and fetch download URLs. Those actions are necessary for a cloud render pipeline. Important runtime behaviors: it uploads user content to https://mega-api-prod.nemovideo.ai, stores session_id and tokens, and asks to auto-detect install path for an attribution header. The upload of user media to a remote service is expected for this skill but is a privacy/exfiltration risk for sensitive footage. The install-path auto-detection instruction implies reading an agent install location — minor privacy/footprint concern.

Install Mechanism

No install spec or code files — instruction-only skill. This is the lowest install risk; nothing is written to disk by an installer step. The runtime instructions will make network calls, but there is no bundled arbitrary code to download/execute.

Credentials

Only NEMO_TOKEN is required (primaryEnv), which is proportionate for authenticating to the described API. Caveats: SKILL.md also references a local config path in frontmatter and instructs generating anonymous tokens and saving them, which implies storing credentials/session state. Requesting a single API token is reasonable, but you should confirm how tokens/session IDs are stored and rotated.

Persistence & Privilege

The skill is not always-enabled and does not request elevated platform privileges. It does persist session_id/token state for its own use (normal). It does not ask to modify other skills or system-wide settings.

What to consider before installing

This skill appears to do what it says (upload video to a cloud renderer and return highlight MP4s), but there are two reasons to be cautious: (1) the skill sends your videos and session tokens to an external domain (mega-api-prod.nemovideo.ai) — don't upload footage you consider private or confidential; (2) provenance is missing (no homepage or source repo) and there's an inconsistency about a config path in the skill frontmatter. Before installing or using: verify the vendor or official endpoint; prefer using a token with limited scope/expiry; avoid uploading sensitive footage; ask the publisher for a privacy policy and confirmation of where tokens/session IDs are stored; and request clarification about the frontmatter config path discrepancy. If you can provide the skill's source repo or an official homepage, I can re-evaluate with higher confidence.

Getting Started

Ready when you are. Drop your raw game footage here or describe what you want to make.

Try saying:

• "generate a 90-minute football match recording into a 1080p MP4"
• "extract the best goals and key plays into a 2-minute highlight reel"
• "generating short highlight reels from full sports game recordings for coaches, sports creators, team managers"

Automatic Setup

On first interaction, connect to the processing API before doing anything else. Show a brief status like "Setting things up...".

Token: If NEMO_TOKEN environment variable is already set, use it and skip to Session below.

Free token: Generate a UUID as client identifier, then POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id: <uuid>. The response field data.token becomes your NEMO_TOKEN (100 credits, 7-day expiry).

Session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Save session_id from the response.

Confirm to the user you're connected and ready. Don't print tokens or raw JSON.

Sports Highlight AI — Generate Game Highlight Reels Fast

Drop your raw game footage in the chat and tell me what you need. I'll handle the AI highlight detection on cloud GPUs — you don't need anything installed locally.

Here's a typical use: you send a a 90-minute football match recording, ask for extract the best goals and key plays into a 2-minute highlight reel, and about 1-3 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 footage to the relevant half or quarter before uploading speeds up processing significantly.

Matching Input to Actions

User prompts referencing sports highlight ai, 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.

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

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

Include Authorization: Bearer <NEMO_TOKEN> and all attribution headers on every request — omitting them triggers a 402 on export.

API base: https://mega-api-prod.nemovideo.ai

Create session: POST /api/tasks/me/with-session/nemo_agent — body {"task_name":"project","language":"<lang>"} — returns task_id, session_id.

Send message (SSE): POST /run_sse — body {"app_name":"nemo_agent","user_id":"me","session_id":"<sid>","new_message":{"parts":[{"text":"<msg>"}]}} with Accept: text/event-stream. Max timeout: 15 minutes.

Upload: POST /api/upload-video/nemo_agent/me/<sid> — file: multipart -F "files=@/path", or URL: {"urls":["<url>"],"source_type":"url"}

Credits: GET /api/credits/balance/simple — returns available, frozen, total

Session state: GET /api/state/nemo_agent/me/<sid>/latest — key fields: data.state.draft, data.state.video_infos, data.state.generated_media

Export (free, no credits): POST /api/render/proxy/lambda — body {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll GET /api/render/proxy/lambda/<id> every 30s until status = completed. Download URL at output.url.

Supported formats: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.

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 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)

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 goals and key plays into a 2-minute highlight reel" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across social platforms and coaching apps.

Common Workflows

Quick edit: Upload → "extract the best goals and key plays into a 2-minute highlight reel" → Download MP4. Takes 1-3 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.