Video Transcript Generator

YouTubers, podcasters, content creators generate video files into transcribed video files using this skill. Accepts MP4, MOV, AVI, WebM up to 500MB, renders...

Security Scan

The skill's declared purpose (cloud video transcription/rendering) matches the actions it instructs (obtaining/using a NEMO_TOKEN, creating a session, uploading video files, polling render status); nothing in the instructions demands unrelated credentials or installs, but there are minor metadata inconsistencies and you should be aware that user media will be uploaded to an external service.

Purpose & Capability

The skill's name/description line up with the requirements: it needs a NEMO_TOKEN to call the nemo_video API to upload videos and request rendering/transcription. No unrelated credentials or platform-level privileges are requested. Minor inconsistency: the registry summary above listed no required config paths, while the SKILL.md frontmatter references a config path (~/.config/nemovideo/)—this is likely harmless but should be clarified.

Instruction Scope

The SKILL.md instructs the agent to obtain/use NEMO_TOKEN, create sessions, upload user-provided video files (multipart or by URL), use SSE for streaming results, and poll render endpoints. Those actions are consistent with a cloud transcription/render flow. Be aware the skill will transmit full user media and metadata to https://mega-api-prod.nemovideo.ai. The document also mentions detection of an 'install path' (~/.clawhub, ~/.cursor/skills/) for X-Skill-Platform headers—this implies the agent may check for certain filesystem paths to set a header, which is outside pure transcript generation but not a strong red flag; clarify whether the agent actually reads those paths or just infers the platform.

Install Mechanism

No install spec or code files are included (instruction-only). This is lowest-risk from an install perspective because nothing is downloaded or written to disk by the skill itself.

Credentials

Only one environment variable (NEMO_TOKEN) is required and is appropriate for calling the remote API. The SKILL.md also describes generating an anonymous token via an API call if NEMO_TOKEN is missing. The earlier registry summary claimed 'no required config paths' but the skill frontmatter lists ~/.config/nemovideo/—this mismatch should be resolved. No unrelated secrets (AWS, GitHub, etc.) are requested.

Persistence & Privilege

always:false and no install steps; the skill asks the agent to save session_id and use tokens for API calls (normal for a session-based API). There is no indication it tries to alter other skills or request persistent/global privileges.

Assessment

This skill appears to do what it says: it will upload video files and use a NEMO_TOKEN to call a remote API that performs transcription and renders results. Before installing/using it, consider: (1) You will be sending your media to https://mega-api-prod.nemovideo.ai — verify you trust that service and understand its privacy/retention policy. (2) The skill can generate an anonymous token for you (100 credits, 7-day expiry) by POSTing a client UUID — this will happen automatically if NEMO_TOKEN is not set. (3) There is a small metadata mismatch (config path listed in SKILL.md but not in registry metadata) and the skill may check for certain local directories only to set a header — ask the publisher to clarify whether it reads local filesystem paths. (4) No extra credentials (AWS, GitHub, etc.) are requested. If you need stronger assurance, request the publisher's homepage or privacy/terms info and ask them to confirm where uploaded content is stored and how long it is retained.

Getting Started

Share your video files and I'll get started on AI transcript generation. Or just tell me what you're thinking.

Try saying:

• "generate my video files"
• "export 1080p MP4"
• "generate a full transcript with timestamps"

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.

Video Transcript Generator — Generate Text from Video Audio

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

A quick example: upload a 10-minute YouTube tutorial recording, type "generate a full transcript with timestamps for my interview video", and you'll get a 1080p MP4 back in roughly 30-90 seconds. All rendering happens server-side.

Worth noting: cleaner audio with less background noise produces more accurate transcripts.

Matching Input to Actions

User prompts referencing video transcript 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.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is video-transcript-generator, 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.

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.

SSE Event Handling

Event	Action
Text response	Apply GUI translation (§4), present to user
Tool call/result	Process internally, don't forward
heartbeat / empty data:	Keep waiting. Every 2 min: "⏳ Still working..."
Stream closes	Process final response

~30% of editing operations return no text in the SSE stream. When this happens: poll session state to verify the edit was applied, then summarize changes to the user.

Translating GUI Instructions

The backend responds as if there's a visual interface. Map its instructions to API calls:

• "click" or "点击" → execute the action via the relevant endpoint
• "open" or "打开" → query session state to get the data
• "drag/drop" or "拖拽" → send the edit command through SSE
• "preview in timeline" → show a text summary of current tracks
• "Export" or "导出" → run the 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)

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 "generate a full transcript with timestamps for my interview 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.

Common Workflows

Quick edit: Upload → "generate a full transcript with timestamps for my interview video" → Download MP4. Takes 30-90 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.