To Maker Generator

Turn a 60-second raw clip or series of short recordings into 1080p finished video files just by typing what you need. Whether it's converting raw clips into...

Security Scan

The skill's instructions generally match a cloud video-rendering service, but there are internal inconsistencies about required configuration/credentials and some ambiguous behaviors (token handling, session persistence, platform autodetection) that you should understand before installing.

Purpose & Capability

The skill claims to be a cloud video-renderer and references a single service (nemovideo). That purpose aligns with the API endpoints and upload/export flows in SKILL.md. However, the registry metadata lists NEMO_TOKEN as a required environment variable, while the runtime instructions explicitly say to generate an anonymous token if NEMO_TOKEN is not present. Also the SKILL.md frontmatter includes a config path (~/.config/nemovideo/) that the registry metadata did not list. These mismatches between declared requirements and the instructions are incoherent and worth clarifying.

Instruction Scope

Instructions direct the agent to perform network calls to mega-api-prod.nemovideo.ai, upload user-supplied files (multipart or by URL), establish sessions, send SSE streams, and poll for render status — all expected for this purpose. The skill does not instruct reading unrelated system files or unrelated credentials, but it does instruct auto-detection of an install path for the X-Skill-Platform header and to 'keep' session_id for subsequent operations (ambiguous where/session state is stored). It also explicitly warns not to expose tokens. Overall instructions are within the expected scope but contain small ambiguities about local state handling and header auto-detection.

Install Mechanism

There is no install spec and no code files; this is an instruction-only skill. That minimizes disk footprint and install-time risk.

Credentials

The only credential declared is NEMO_TOKEN (primaryEnv) which fits the service. But SKILL.md allows obtaining an anonymous token via POST to /api/auth/anonymous-token when NEMO_TOKEN is not present, contradicting the registry declaration that NEMO_TOKEN is required. The frontmatter also declares a config path (~/.config/nemovideo/), which was not listed in the top-level metadata. These inconsistencies about what credentials/config are actually required are disproportionate to the stated single-API purpose because they create uncertainty about what secrets or files the skill will actually use or create.

Persistence & Privilege

The skill is not always-enabled and does not request special system privileges. It instructs the agent to 'keep the returned session_id for all operations' but doesn't specify whether this is in-memory only or persisted to disk/config. That ambiguity is worth clarifying because persistent storage of session tokens or anonymous credentials could have privacy implications for future runs.

What to consider before installing

This skill appears to be a straightforward cloud video-renderer, but there are mismatches you should clear up before installing: (1) The skill registry says NEMO_TOKEN is required, yet SKILL.md will generate an anonymous token if NEMO_TOKEN is missing — ask the publisher which is correct and whether anonymous tokens are appropriate for your use. (2) Confirm where session tokens are stored (in-memory vs written to disk) and whether ~/.config/nemovideo/ will be created or read. (3) Review privacy: uploads are sent to mega-api-prod.nemovideo.ai — do not send sensitive or private videos until you trust the service and its privacy terms. (4) Test with throwaway content and, if possible, a throwaway or limited-scope API token to confirm behavior. (5) Ask the author for a homepage/source and a published privacy/terms page; the skill's source is unknown which increases risk. If you cannot get clear answers to the above, treat installation with caution or avoid it.

Getting Started

Share your raw video clips and I'll get started on AI video creation. Or just tell me what you're thinking.

Try saying:

• "convert my raw video clips"
• "export 1080p MP4"
• "turn my clips into a finished"

Quick Start Setup

This skill connects to a cloud processing backend. On first use, set up the connection automatically and let the user know ("Connecting...").

Token check: Look for NEMO_TOKEN in the environment. If found, skip to session creation. Otherwise:

• Generate a UUID as client identifier
• POST https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with X-Client-Id header
• Extract data.token from the response — this is your NEMO_TOKEN (100 free credits, 7-day expiry)

Session: POST https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Keep the returned session_id for all operations.

Let the user know with a brief "Ready!" when setup is complete. Don't expose tokens or raw API output.

To Maker Generator — Convert Clips Into Finished Videos

Send me your raw video clips and describe the result you want. The AI video creation runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 60-second raw clip or series of short recordings, type "turn my clips into a finished video with transitions and music", and you'll get a 1080p MP4 back in roughly 1-2 minutes. All rendering happens server-side.

Worth noting: shorter input clips under 2 minutes generate results significantly faster.

Matching Input to Actions

User prompts referencing to maker 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.

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

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

Header	Value
X-Skill-Source	to-maker-generator
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

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

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)

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "turn my clips into a finished video with transitions and music" — 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 → "turn my clips into a finished video with transitions and music" → 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.