baoyu-danger-gemini-webGenerates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input,...
Install via ClawdBot CLI:
clawdbot install wjctim/baoyu-danger-gemini-webGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
UPLOAD → https://content-push.googleapis.com/uploadCalls external URL not in known-safe list
https://lh3.googleusercontent.com/gg-dl/Uses known external API (expected, informational)
googleapis.comAI Analysis
The skill uses Google's Gemini API endpoints (content-push.googleapis.com, lh3.googleusercontent.com) which are consistent with its stated purpose of reverse-engineering the Gemini Web API. The consent mechanism provides user awareness, and no credential harvesting or hidden instructions are evident. However, using a reverse-engineered API carries inherent risk of unexpected data handling.
Generated Mar 20, 2026
Marketing agencies can use this skill to generate visual and textual content for campaigns, such as creating ad images from prompts and writing copy. It supports vision input to analyze reference images for brand consistency, enabling quick iteration on creative assets.
Educators and e-learning platforms can leverage this skill to generate diagrams, illustrations, and explanatory text for courses. The multi-turn conversation feature allows for interactive lesson planning, while reference images help create variations of existing educational visuals.
Design teams can utilize the image generation capabilities to brainstorm product concepts and create visual prototypes from textual descriptions. Vision input with reference images enables style transfer and refinement, speeding up the design iteration process.
Businesses can integrate this skill to generate automated responses and visual aids for customer inquiries. The text generation handles common queries, while image generation can create diagrams or instructions, enhancing support efficiency with multi-turn conversations for context retention.
Writers and filmmakers can use this skill to generate story ideas, character descriptions, and scene images for storyboarding. The ability to process reference images aids in maintaining visual consistency across scenes, supporting collaborative creative projects.
Offer a subscription-based service where users access this skill via a web interface to generate images and text on-demand. Revenue comes from tiered plans based on usage limits, with premium features like advanced models and priority support.
License this skill to marketing and design agencies as a backend tool for their internal workflows. Charge a flat fee or per-project basis, providing customization options and API access to integrate seamlessly with their existing systems.
Develop a mobile app that uses this skill for on-the-go image and text generation, with a free tier offering basic features and paid upgrades for advanced models, higher resolution images, and ad-free experience. Monetize through in-app purchases and ads.
💬 Integration Tip
Ensure user consent is managed upfront via the required flow, and leverage environment variables for flexible deployment across different systems.
Scored Apr 19, 2026
Audited Apr 16, 2026 · audit v1.0
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
Gemini CLI for one-shot Q&A, summaries, and generation.
Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates openclaw.json. Use when the user mentions free AI, OpenRouter, model switching, rate limits, or wants to reduce AI costs.
Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates opencla...
Reduce OpenClaw AI costs by 97%. Haiku model routing, free Ollama heartbeats, prompt caching, and budget controls. Go from $1,500/month to $50/month in 5 min...
HTML-first PDF production skill for reports, papers, and structured documents. Must be applied before generating PDF deliverables from HTML.