Index of every page on this site: llms.txt
All skills
jimliu avatar

/baoyu-danger-gemini-web

@bf1ff07 official
by Jim Liu 宝玉jimliu/baoyu-skills28k stars
3,011
Run it yourself

Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Use when other skills need image generation backend, or when user requests "generate image with Gemini", "Gemini text generation", or needs vision-capable AI generation.

Use this Skill: https://skilld.dev/gh/jimliu/baoyu-skills/baoyu-danger-gemini-web

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈95 tokens for metadata: the name and description. ≈1.3k when used: this file. ≈37 more on demand in 1 file.

Description uses 4.8% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈382 characters, or 4.8%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Gemini Web Client

User Input Tools

When this skill prompts the user, follow this tool-selection rule (priority order):

  1. Prefer built-in user-input tools exposed by the current agent runtime — e.g., AskUserQuestion, request_user_input, clarify, ask_user, or any equivalent.
  2. Fallback: if no such tool exists, emit a numbered plain-text message and ask the user to reply with the chosen number/answer for each question.
  3. Batching: if the tool supports multiple questions per call, combine all applicable questions into a single call; if only single-question, ask them one at a time in priority order.

Concrete AskUserQuestion references below are examples — substitute the local equivalent in other runtimes.

Script Directory

{baseDir} = this SKILL.md's directory; scripts are at {baseDir}/scripts/<script-name>.ts. Resolve ${BUN_X}: bun if installed; else npx -y bun; else suggest installing bun. Replace {baseDir} and ${BUN_X} with actual values.

Script Purpose
scripts/main.ts CLI entry point for text/image generation
scripts/gemini-webapi/* TypeScript port of gemini_webapi (GeminiClient, types, utils)

Consent Check (REQUIRED)

Before first use, verify user consent for reverse-engineered API usage. Consent file:

  • macOS: ~/Library/Application Support/baoyu-skills/gemini-web/consent.json
  • Linux: ~/.local/share/baoyu-skills/gemini-web/consent.json
  • Windows: %APPDATA%\baoyu-skills\gemini-web\consent.json
  1. Check if consent file exists with accepted: true and disclaimerVersion: "1.0"
  2. If valid consent exists → print warning with acceptedAt date, proceed
  3. If no consent → show disclaimer, ask user via AskUserQuestion:
    • "Yes, I accept" → create consent file with ISO timestamp, proceed
    • "No, I decline" → output decline message, stop
  4. Consent file format: {"version":1,"accepted":true,"acceptedAt":"<ISO>","disclaimerVersion":"1.0"}

Preferences (EXTEND.md)

First found wins:

Priority Path Scope
1 .baoyu-skills/baoyu-danger-gemini-web/EXTEND.md Project
2 ${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-danger-gemini-web/EXTEND.md XDG
3 $HOME/.baoyu-skills/baoyu-danger-gemini-web/EXTEND.md User home

If none found, use defaults. EXTEND.md supports: default model, proxy settings, custom data directory.

Usage

${BUN_X} {baseDir}/scripts/main.ts "Your prompt"                                     # text
${BUN_X} {baseDir}/scripts/main.ts --prompt "Your prompt" --model gemini-3-flash
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cute cat" --image cat.png             # image
${BUN_X} {baseDir}/scripts/main.ts --promptfiles system.md content.md --image out.png
${BUN_X} {baseDir}/scripts/main.ts --prompt "Describe this" --reference image.png    # vision input
${BUN_X} {baseDir}/scripts/main.ts --prompt "Create variation" --reference a.png --image out.png
${BUN_X} {baseDir}/scripts/main.ts "Remember: 42" --sessionId session-abc           # multi-turn
${BUN_X} {baseDir}/scripts/main.ts "What number?" --sessionId session-abc
${BUN_X} {baseDir}/scripts/main.ts "Hello" --json

Options

Option Description
--prompt, -p Prompt text
--promptfiles Read prompt from files (concatenated)
--model, -m Model (see Models; default gemini-3-pro)
--image [path] Generate image (default: generated.png)
--reference, --ref Reference images for vision input
--sessionId Session ID for multi-turn conversation
--list-sessions List saved sessions
--json Output as JSON
--login Refresh cookies, then exit
--cookie-path Custom cookie file path
--profile-dir Chrome profile directory

Models

Model Description
gemini-3-pro Default, latest 3.0 Pro
gemini-3-flash Fast, lightweight 3.0 Flash
gemini-3-flash-thinking 3.0 Flash with thinking
gemini-3.1-pro-preview 3.1 Pro preview (empty header, auto-routed)

Authentication

First run opens a browser for Google auth; cookies are cached. Force refresh: --login. Override browser: GEMINI_WEB_CHROME_PATH. Auto-detected browsers: Chrome, Chrome Canary/Beta, Chromium, Edge.

Without an explicit profile dir, cookie refresh may reuse an already-running local Chrome/Chromium debugging session tied to a standard user-data dir (best-effort CDP reuse, not Chrome DevTools MCP's --autoConnect flow). Set --profile-dir or GEMINI_WEB_CHROME_PROFILE_DIR to force a dedicated profile and skip that reuse.

Environment Variables

Variable Description
GEMINI_WEB_DATA_DIR Data directory
GEMINI_WEB_COOKIE_PATH Cookie file path
GEMINI_WEB_CHROME_PROFILE_DIR Chrome profile directory
GEMINI_WEB_CHROME_PATH Chrome executable path
HTTP_PROXY, HTTPS_PROXY Proxy for Google access (bash: set inline with command; PowerShell: $env:HTTPS_PROXY = '...' before running)

Sessions

Stored in the data directory as sessions/<id>.json, containing id, metadata (Gemini chat state), messages array, timestamps.

Extension Support

Custom configurations via EXTEND.md. See Preferences section for paths and supported options.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

2 warnings15d5 checks · Risk SAFE
  • Gen Agent Trust Hub17d

    This skill provides a client for the reverse-engineered Gemini Web API, allowing text and image generation. It handles sensitive Google session cookies and performs local browser automation to facilitate authentication, which is transparently documented as its core functionality. The skill communicates exclusively with official Google domains and includes a user consent mechanism for its operation.

  • Socket15d

    4 alerts: gptSecurity, gptAnomaly

  • Snyk17d

    Risk: LOW · No issues

  • Runlayer8mo

    7/29 files flagged

  • ZeroLeaks7mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at bf1ff07. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 3 weeks ago
version
1.56.2
Other metadata
metadata
{
  "openclaw": {
    "homepage": "https://github.com/JimLiu/baoyu-skills#baoyu-danger-gemini-web",
    "requires": {
      "anyBins": [
        "bun",
        "npx"
      ]
    }
  }
}
  • API
  • TypeScript
  • gemini
  • image-generation
  • text-generation
  • vision
  • reverse-engineered
  • multi-turn

README badge

README badge for jimliu/baoyu-skills/baoyu-danger-gemini-web

Generates text and images via reverse-engineered Gemini Web API, with support for vision input from reference images and multi-turn conversations. Use this skill when you need Gemini text or image generation as a backend, or when the user explicitly requests "generate image with Gemini" or vision-capable generation.

Generated from the current SKILL.md.

Does this skill require authentication?
Yes. First run opens a browser for Google authentication, and cookies are cached automatically. You can force a refresh with the --login flag.
What models does this skill support?
gemini-3-pro (default), gemini-3-flash, gemini-3-flash-thinking, and gemini-3.1-pro-preview. The model can be specified via the --model flag.
Can this skill use reference images for vision input?
Yes. Pass reference images with the --reference flag to provide vision context. You can also generate new images while referencing existing ones.
Does this skill support multi-turn conversations?
Yes. Use the --sessionId flag to maintain conversation state across multiple prompts. Sessions are stored and can be listed with --list-sessions.
What is the consent check requirement?
Before first use, the skill checks for user consent to use the reverse-engineered Gemini Web API. If no consent exists, the user is prompted to accept a disclaimer before proceeding.

Generated from the current SKILL.md. These answers refresh after source changes.