Twitch Highlight Editor

Skip the learning curve of professional editing software. Describe what you want — find the best moments and cut them into a 5-minute highlight reel — and ge...

Security Scan

The skill's requirements and runtime instructions align with its stated purpose (remote video highlight extraction) but there are small metadata inconsistencies and some transparency trade-offs you should be aware of.

Purpose & Capability

The skill is a remote video highlight/editor and it only requires a NEMO_TOKEN to call the nemo video API and upload media — this is coherent with the described functionality. One minor inconsistency: the SKILL.md frontmatter metadata references a config path (~/.config/nemovideo/) while the registry metadata reported earlier listed no required config paths.

Instruction Scope

The instructions stay within the stated domain (upload video files, create sessions, run SSE edit commands, request renders). The skill instructs the agent to obtain an anonymous token when NEMO_TOKEN is absent and to create sessions and poll renders on nemovideo.ai. It also instructs the agent to 'keep the technical details out of the chat,' which reduces transparency about background network actions to the user — not necessarily malicious, but worth noting.

Install Mechanism

Instruction-only skill with no install spec and no code files; nothing is written to disk by an installer, which is low-risk.

Credentials

Only a single credential (NEMO_TOKEN) is requested, which is proportional to a service that requires API authorization. However, the skill will create and use an anonymous token if none is present (via an API POST), and the SKILL.md frontmatter mentions a local config path that the registry summary did not — this mismatch could indicate either optional local credential lookup or simply metadata drift.

Persistence & Privilege

always: false and no install hooks; the skill does not request persistent system privileges or modifications to other skills. Autonomous invocation is allowed (platform default) but not combined with elevated privileges.

Assessment

This skill appears to do what it claims: upload your video to nemo's API, run highlight extraction, and return a rendered MP4. Before installing or using it: (1) confirm you trust the remote service (mega-api-prod.nemovideo.ai) because you will be uploading potentially sensitive video content; (2) treat NEMO_TOKEN like any API secret — don't provide a long-lived personal token unless you intend to; use an anonymous token if available or create a dedicated service token with minimal scope; (3) note the SKILL.md says it may auto-create/use an anonymous token and implies a local config path (~/.config/nemovideo/) in its frontmatter — ask the skill owner how (and whether) the skill will read local config files or write any tokens to disk; (4) because the skill hides technical details in chat, expect network activity to occur behind the scenes — if you need full transparency, request explicit logging of API calls or avoid using the skill.

Getting Started

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

Try saying:

• "edit my raw stream footage"
• "export 1080p MP4"
• "find the best moments and cut"

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.

Twitch Highlight Editor — Clip and Export Stream Highlights

Send me your raw stream 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 3-hour Twitch VOD recording, type "find the best moments and cut them into a 5-minute highlight reel", and you'll get a 1080p MP4 back in roughly 1-3 minutes. All rendering happens server-side.

Worth noting: trimming your VOD to the best 30-minute segment before uploading speeds up processing significantly.

Matching Input to Actions

User prompts referencing twitch highlight editor, 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 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.

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

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

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.

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

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.

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)

Common Workflows

Quick edit: Upload → "find the best moments and cut them into a 5-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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "find the best moments and cut them into a 5-minute highlight reel" — concrete instructions get better results.

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

Export as MP4 with H.264 codec for easy upload to Twitch, YouTube, and social platforms.