Chapter Generator

Turn a 45-minute tutorial video recording into 1080p chaptered video file just by typing what you need. Whether it's adding timestamped chapters to long YouT...

Security Scan

The skill's requests and runtime instructions are consistent with a cloud-based video chaptering service: it only needs a single service token and instructs uploading videos to that service for server-side rendering.

Purpose & Capability

The name and description (generate timestamped chapters and server-side 1080p exports) match the runtime instructions (upload video, create session, start render, poll for status). Requesting a single service token (NEMO_TOKEN) is proportional. Minor metadata mismatch: the registry metadata listed no required config paths, but the SKILL.md frontmatter includes configPaths ["~/.config/nemovideo/"]. This is likely an authoring inconsistency rather than malicious behavior, but it should be clarified.

Instruction Scope

Instructions are focused on connecting to the nemo video backend, uploading user-provided media, streaming SSE responses, starting render jobs, and polling state. They do not instruct reading unrelated system files, other credentials, or exfiltrating arbitrary local data. The only potential scope creep is the frontmatter claim of a config path (~/.config/nemovideo/) which is not referenced elsewhere in SKILL.md; the skill does not otherwise direct the agent to read local configs or secrets.

Install Mechanism

No install spec or code files are present; the skill is instruction-only and will not write files to disk or download remote code. This is the lowest-risk install model and is consistent with the declared behavior.

Credentials

Only a single environment variable (NEMO_TOKEN) is required and is the declared primary credential. The SKILL.md also describes obtaining an anonymous token from the service when NEMO_TOKEN is not present; no other credentials or unrelated secrets are requested. This is proportionate for a third-party cloud API integration.

Persistence & Privilege

The skill is not always-enabled and does not request elevated or persistent system privileges. It does not modify other skills or system-wide agent settings. Autonomous invocation is allowed (platform default) but not combined with any unusual privileges.

Assessment

This skill uploads whatever video and media you provide to a third-party service at https://mega-api-prod.nemovideo.ai and uses a NEMO_TOKEN (or an anonymous token it will fetch) to authorize requests. Before installing or using it: (1) Confirm you trust that external service to process and store your videos (privacy/retention matters); (2) Prefer using a purpose-limited NEMO_TOKEN if possible, and don’t reuse an unrelated secret under that name; (3) Ask the publisher to clarify the frontmatter vs registry metadata mismatch about the config path (~/.config/nemovideo/); verify the skill will not read local files unexpectedly; (4) Be aware anonymous tokens provide temporary credits and that export jobs run on remote GPUs and can be orphaned if you close your session. If any of those are concerning, don’t install or provide sensitive content to the skill.

Getting Started

Ready when you are. Drop your long-form video here or describe what you want to make.

Try saying:

• "generate a 45-minute tutorial video recording into a 1080p MP4"
• "generate chapters with timestamps and titles for my YouTube video"
• "adding timestamped chapters to long YouTube or course videos for YouTubers and course 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.

Chapter Generator — Generate Timestamped Chapters for Videos

Send me your long-form video and describe the result you want. The AI chapter generation runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 45-minute tutorial video recording, type "generate chapters with timestamps and titles for my YouTube video", and you'll get a 1080p MP4 back in roughly 30-60 seconds. All rendering happens server-side.

Worth noting: clear topic transitions in your video help the AI detect chapter boundaries more accurately.

Matching Input to Actions

User prompts referencing chapter generator, 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	chapter-generator
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 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

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)

Common Workflows

Quick edit: Upload → "generate chapters with timestamps and titles for my YouTube video" → 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "generate chapters with timestamps and titles for my YouTube video" — 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 YouTube, Vimeo, and LMS platforms.