Bing Image Creator

Turn a short text description like 'a fox reading a book in a forest at sunset' into 1080p AI generated visuals just by typing what you need. Whether it's ge...

Security Scan

The skill's instructions mostly match a remote image/video rendering service, but there are mismatches (it calls itself 'Bing' while using nemovideo.ai endpoints, and metadata/config requirements disagree), so the package may be misattributed or sloppy and warrants caution.

Purpose & Capability

The skill is named and described as 'Bing Image Creator' but every runtime endpoint and the anonymous-token flow point to mega-api-prod.nemovideo.ai (a third-party domain). That discrepancy (branding vs actual backend) is unexpected and unexplained. Registry metadata shown to you lists no required config paths, but the SKILL.md frontmatter includes a configPaths value (~/.config/nemovideo/). No homepage or source is provided to verify provenance.

Instruction Scope

SKILL.md instructs the agent to manage session tokens, call specific nemo API endpoints, upload files, poll job status, and include attribution headers. Those actions are consistent with a cloud render workflow. The instructions also imply reading install paths to set X-Skill-Platform and the frontmatter references a local config path; it's not explicit whether or how local config files will be read, which is ambiguous and worth clarifying.

Install Mechanism

This is an instruction-only skill with no install spec and no code files — lowest install risk. Nothing is downloaded or written by an installer.

Credentials

The only declared credential is NEMO_TOKEN, which is appropriate for calling nemo API endpoints. However, the frontmatter also lists a local config path (~/.config/nemovideo/) which could contain additional secrets; the registry summary earlier listed no config paths — this inconsistency raises questions about whether the skill will attempt to access local config beyond the declared env var.

Persistence & Privilege

always:false (default) and no install-time changes are requested. The skill can be invoked autonomously (platform default) but it does not request permanent/system-wide privileges.

What to consider before installing

This skill appears to call a NemoVideo API backend but is labelled 'Bing', and the registry metadata conflicts with the SKILL.md frontmatter (config path present there but not in the registry). Before installing or providing credentials: (1) confirm the vendor and source — ask the publisher for a homepage or code repo and why it is named 'Bing' while pointing to nemovideo.ai; (2) avoid setting a permanent shell-wide NEMO_TOKEN until you trust the service — use a limited/test token or the anonymous-token flow in an isolated environment; (3) clarify whether the skill will read ~/.config/nemovideo/ or other local files; (4) be cautious uploading sensitive content (uploads go to an external domain); (5) if you need to proceed, create least-privilege credentials and monitor usage / revoke the token if anything looks off.

Getting Started

Got text prompts to work with? Send it over and tell me what you need — I'll take care of the AI image generation.

Try saying:

• "generate a short text description like 'a fox reading a book in a forest at sunset' into a 1080p MP4"
• "generate an image of a futuristic city skyline at night with neon lights"
• "generating images from text descriptions for creative projects for 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.

Bing Image Creator — Generate Images From Text Prompts

Drop your text prompts in the chat and tell me what you need. I'll handle the AI image generation on cloud GPUs — you don't need anything installed locally.

Here's a typical use: you send a a short text description like 'a fox reading a book in a forest at sunset', ask for generate an image of a futuristic city skyline at night with neon lights, 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 — more specific prompts produce more accurate and usable results.

Matching Input to Actions

User prompts referencing bing image creator, 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: bing-image-creator
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else 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.

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)

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

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.

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

Common Workflows

Quick edit: Upload → "generate an image of a futuristic city skyline at night with neon lights" → 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "generate an image of a futuristic city skyline at night with neon lights" — concrete instructions get better results.

Max file size is 200MB. Stick to JPG, PNG, WebP, MP4 for the smoothest experience.

Export as MP4 for widest compatibility.