Generator Chrome

generate video clips into chrome effect videos with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. TikTok creators use it for adding chrome me...

Security Scan

The skill's declared purpose (apply a chrome effect to videos) matches its network calls and single required credential (NEMO_TOKEN), but the runtime instructions ask the agent to read install paths / frontmatter and reference a local config path that is not declared in the registry metadata — an inconsistency that deserves caution.

Purpose & Capability

The skill's name/description (video chrome effects) align with the API calls and the single required env var (NEMO_TOKEN). Requiring a token for a cloud render service is proportionate. However, SKILL.md metadata references a config path (~/.config/nemovideo/) and install-path detection for attribution headers while the registry metadata lists no config paths — this mismatch is unexplained.

Instruction Scope

The instructions guide the agent to: (a) use NEMO_TOKEN or obtain an anonymous token via an external auth endpoint; (b) create sessions, upload files, use SSE, poll render status — all expected for a cloud render flow; (c) read this file's YAML frontmatter at runtime and detect the agent install path (~/.clawhub/, ~/.cursor/skills/) to set an X-Skill-Platform header. The install-path detection and reading of frontmatter/config is scope creep relative to purely uploading and rendering user videos and implies filesystem access which isn't justified by the registry metadata.

Install Mechanism

Instruction-only skill with no install spec and no code files — lowest install risk. All runtime behavior is via network calls described in SKILL.md.

Credentials

Only NEMO_TOKEN is declared and used; that's appropriate for a hosted render API. Caveat: SKILL.md's metadata lists a config path (~/.config/nemovideo/) which could contain credentials or other user data; the registry metadata did not declare that config path. The skill will also use any NEMO_TOKEN present in the environment automatically, so users should verify what value is stored in that env var before invoking the skill.

Persistence & Privilege

The skill does not request always:true, does not install binaries, and does not ask to modify other skills or system-wide configuration. It uses short-lived sessions and cloud-side render jobs; no persistent local privileges appear requested.

What to consider before installing

This skill mostly looks like a straightforward cloud-video-render integration, but there are a few things to check before installing or using it: - Confirm the network domain (mega-api-prod.nemovideo.ai) is expected and trustworthy for your use. The skill will send your videos and tokens to that service. - Check what value (if any) you have in the NEMO_TOKEN environment variable. The skill will use it automatically; if that env var contains a sensitive or high-privilege token, avoid using it or unset it before running the skill. - The SKILL.md mentions a local config directory (~/.config/nemovideo/) and asks the agent to detect install paths to set an attribution header — that implies the agent may check filesystem paths. Ask the publisher why filesystem detection is needed or request code/source before trusting the skill. - If you only want to try the skill, prefer letting it obtain an anonymous token (the instructions support this) rather than exposing an existing token. - If you need higher assurance, ask the publisher for the skill source or an install spec (so you can audit exact behavior), or run it in an environment without sensitive env vars or configs present. Given the mismatch between the registry metadata and the SKILL.md (config path present only in the SKILL.md) and the filesystem-detection behavior, treat this as suspicious until the developer clarifies those points or publishes source.

Getting Started

Share your video clips and I'll get started on chrome effect generation. Or just tell me what you're thinking.

Try saying:

• "generate my video clips"
• "export 1080p MP4"
• "apply a chrome metallic overlay effect"

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.

Generator Chrome — Generate Chrome Effect Videos

Drop your video clips in the chat and tell me what you need. I'll handle the chrome effect generation on cloud GPUs — you don't need anything installed locally.

Here's a typical use: you send a a 30-second product clip, ask for apply a chrome metallic overlay effect to my video, and about 20-40 seconds later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — shorter clips under 15 seconds render the chrome effect faster.

Matching Input to Actions

User prompts referencing generator chrome, 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 calls go to https://mega-api-prod.nemovideo.ai. The main endpoints:

1. Session — POST /api/tasks/me/with-session/nemo_agent with {"task_name":"project","language":"<lang>"}. Gives you a session_id.
2. Chat (SSE) — POST /run_sse with session_id and your message in new_message.parts[0].text. Set Accept: text/event-stream. Up to 15 min.
3. Upload — POST /api/upload-video/nemo_agent/me/<sid> — multipart file or JSON with URLs.
4. Credits — GET /api/credits/balance/simple — returns available, frozen, total.
5. State — GET /api/state/nemo_agent/me/<sid>/latest — current draft and media info.
6. Export — POST /api/render/proxy/lambda with render ID and draft JSON. Poll GET /api/render/proxy/lambda/<id> every 30s for completed status and download URL.

Formats: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.

Skill attribution — read from this file's YAML frontmatter at runtime:

• X-Skill-Source: generator-chrome
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

Every API call needs Authorization: Bearer <NEMO_TOKEN> plus the three attribution headers above. If any header is missing, exports return 402.

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)

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.

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 "apply a chrome metallic overlay effect to my 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 → "apply a chrome metallic overlay effect to my video" → Download MP4. Takes 20-40 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.