Style Generator

generate video clips or images into stylized video clips with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. TikTok creators, Instagram market...

Security Scan

The skill is internally consistent with a cloud-based video styling service: it asks for one service token, posts user media to a remote API, and has no install step — but missing source info and a small metadata mismatch reduce confidence.

Purpose & Capability

The name/description (apply visual styles to videos) matches the instructions (upload media, create session, render via mega-api-prod.nemovideo.ai). Requesting a single service token (NEMO_TOKEN) is proportional. One minor inconsistency: the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) while the registry metadata reported no required config paths — this is a small mismatch but could indicate stale metadata.

Instruction Scope

Runtime instructions are focused on authenticating, creating sessions, uploading user media, handling SSE and polling render status — all within the stated purpose. The skill will upload user-provided files to an external API (expected for this service) and requires adding specific attribution headers. It also asks the agent to auto-detect platform from an install path (implies access to agent environment/install path), which is outside the narrow media-processing description but not necessarily malicious.

Install Mechanism

No install spec and no code files (instruction-only). This minimizes disk write/execution risk; nothing is downloaded or installed by the skill.

Credentials

Only NEMO_TOKEN is declared as required (primary credential) which matches the API's Bearer auth. The skill also supports creating an anonymous token by calling the API (so it can operate without a pre-provided token). Ensure NEMO_TOKEN is not used to pass unrelated or highly privileged credentials. The earlier-mentioned config path in the SKILL.md frontmatter is not declared in registry metadata — a minor inconsistency.

Persistence & Privilege

always:false and no install means the skill does not request elevated persistent presence. It does instruct saving session_id for the session lifecycle (normal for a session-based API).

Assessment

This skill appears to do what it says: it uploads user media to a third‑party rendering API and returns styled videos. Before installing, consider: 1) privacy — all uploaded videos/images/audio will be sent to https://mega-api-prod.nemovideo.ai; do not upload sensitive or private content. 2) Token scope — NEMO_TOKEN grants access to that service; don't reuse other secret keys as NEMO_TOKEN. 3) Transparency — the skill has no source/homepage; ask the publisher for docs or a privacy policy if you need assurance. 4) Test with non-sensitive sample media first and confirm outputs. 5) The SKILL.md frontmatter mentions a config path (~/.config/nemovideo/) that isn't listed in registry metadata — verify what local files (if any) the skill will read. If any of these are unacceptable, don't install or provide a token.

Getting Started

Send me your video clips or images and I'll handle the AI style transformation. Or just describe what you're after.

Try saying:

• "generate a 30-second lifestyle clip or product photo set into a 1080p MP4"
• "apply a cinematic film noir style to my footage"
• "applying visual styles and aesthetics to raw video footage for TikTok creators, Instagram marketers, content creators"

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.

Style Generator — Apply Visual Styles to Videos

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

A quick example: upload a 30-second lifestyle clip or product photo set, type "apply a cinematic film noir style to my footage", and you'll get a 1080p MP4 back in roughly 30-90 seconds. All rendering happens server-side.

Worth noting: shorter clips under 60 seconds produce the most consistent style results.

Matching Input to Actions

User prompts referencing style 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	style-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 Handling

Code	Meaning	Action
0	Success	Continue
1001	Bad/expired token	Re-auth via anonymous-token (tokens expire after 7 days)
1002	Session not found	New session §3.0
2001	No credits	Anonymous: show registration URL with ?bind=<id> (get <id> from create-session or state response when needed). Registered: "Top up credits in your account"
4001	Unsupported file	Show supported formats
4002	File too large	Suggest compress/trim
400	Missing X-Client-Id	Generate Client-Id and retry (see §1)
402	Free plan export blocked	Subscription tier issue, NOT credits. "Register or upgrade your plan to unlock export."
429	Rate limit (1 token/client/7 days)	Retry in 30s once

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 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)

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "apply a cinematic film noir style to my footage" — 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 social platforms.

Common Workflows

Quick edit: Upload → "apply a cinematic film noir style to my footage" → 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.