Agent skill

Gemini Web Reverse-Engineered Client

by JimLiu in JimLiu/baoyu-skills

Generates text and images through an unofficial, reverse-engineered Gemini Web API, supporting reference images and multi-turn conversations.

MITAuto-check passedMedia & Creative

Install Gemini Web Reverse-Engineered Client

skills CLI
$ npx skills add JimLiu/baoyu-skills --skill baoyu-danger-gemini-web -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install JimLiu/baoyu-skills baoyu-danger-gemini-web --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/JimLiu/baoyu-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/baoyu-danger-gemini-web .claude/skills/baoyu-danger-gemini-web && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
baoyu-danger-gemini-web
GitHub stars
27k
Used in
5 other repos
Token cost
~1.6k tokens
SKILL.md length
548 words
Files
28 (incl. scripts)
Skills in repo
22
Repo updated
First seen
Licence
MIT

At a glance

Generates text and images through an unofficial, reverse-engineered Gemini Web API, supporting reference images and multi-turn conversations.

  • Works in 3 steps: Prefer built-in user-input tools exposed… → Fallback: if no such tool exists, emit a… → Batching: if the tool supports multiple…
  • Generating an image or text response through Gemini's web interface
  • SKILL.md covers User Input Tools, Script Directory, Consent Check (REQUIRED) and Preferences (EXTEND.md), plus 7 more sections
  • Runs TypeScript scripts from its folder; calls npx

What it does

Before first use it checks for a consent file recording that the user accepted a disclaimer about using a reverse-engineered API; without one it shows the disclaimer and asks through the agent's own question tool, writing a timestamped consent file on acceptance or stopping outright on a decline. Its logic lives in a bundled scripts folder, a TypeScript port of an existing Python client project, with a single CLI entry point for text and image generation.

When it needs to ask the user something, it prefers whatever built-in question tool the current agent runtime exposes, falling back to a numbered plain-text question only when no such tool exists, and batches multiple questions into one call when the runtime supports it. User preferences can override its defaults through a local extension file, checked in a defined priority order so the first one found wins.

When your agent uses it

  • Generating an image or text response through Gemini's web interface
  • Providing a reference image as vision input for a Gemini generation
  • Continuing a multi-turn conversation with the Gemini web backend

Example prompts

  • “Generate an image of a mountain cabin at sunset with Gemini.”
  • “Use this reference photo to generate a similar image with Gemini.”
  • “Continue this Gemini conversation and ask it to adjust the lighting.”

Requirements

  • Bun or npx to run the bundled TypeScript client
  • User consent recorded in a local disclaimer file

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Prefer built-in user-input tools exposed by the current agent runtime — e.g., AskUserQuestion, request_user_input, clarify, ask_user, or…
  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…
  3. Batching: if the tool supports multiple questions per call, combine all applicable questions into a single call; if only single-question…

What it can do on your machine

Read from SKILL.md and the folder at commit 1567581. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 15 files in scripts/ (TypeScript, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • npx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gemini Web Reverse-Engineered Client loads about 1.6k tokens when it runs. Until then it costs about 95 tokens; SKILL.md has 548 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~95
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from JimLiu/baoyu-skills at commit 1567581, republished under its MIT licence (© JimLiu). 548 words, ~1,625 tokens.

Download SKILL.mdSave it as .claude/skills/baoyu-danger-gemini-web/SKILL.md (or your agent's skills folder). This skill also uses 27 other files; get the full folder from GitHub.
name
baoyu-danger-gemini-web
description
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.
version
1.56.2

Gemini Web Client

Text/image generation via Gemini Web API. Supports reference images and multi-turn conversations.

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

Important: All scripts are located in the scripts/ subdirectory of this skill.

Agent Execution Instructions:

  1. Determine this SKILL.md file's directory path as {baseDir}
  2. Script path = {baseDir}/scripts/<script-name>.ts
  3. Resolve ${BUN_X} runtime: if bun installed → bun; if npx available → npx -y bun; else suggest installing bun
  4. Replace all {baseDir} and ${BUN_X} in this document with actual values

Script Reference:

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

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

Consent file locations:

  • 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

Flow:

  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)

Check EXTEND.md in priority order — the first one found wins:

PriorityPathScope
1.baoyu-skills/baoyu-danger-gemini-web/EXTEND.mdProject
2${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-danger-gemini-web/EXTEND.mdXDG
3$HOME/.baoyu-skills/baoyu-danger-gemini-web/EXTEND.mdUser home

If none found, use defaults.

EXTEND.md supports: Default model, proxy settings, custom data directory.

Usage

bash
# Text generation
${BUN_X} {baseDir}/scripts/main.ts "Your prompt"
${BUN_X} {baseDir}/scripts/main.ts --prompt "Your prompt" --model gemini-3-flash

# Image generation
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cute cat" --image cat.png
${BUN_X} {baseDir}/scripts/main.ts --promptfiles system.md content.md --image out.png

# Vision input (reference images)
${BUN_X} {baseDir}/scripts/main.ts --prompt "Describe this" --reference image.png
${BUN_X} {baseDir}/scripts/main.ts --prompt "Create variation" --reference a.png --image out.png

# Multi-turn conversation
${BUN_X} {baseDir}/scripts/main.ts "Remember: 42" --sessionId session-abc
${BUN_X} {baseDir}/scripts/main.ts "What number?" --sessionId session-abc

# JSON output
${BUN_X} {baseDir}/scripts/main.ts "Hello" --json
Show full SKILL.md (233 more words)Show less

Options

OptionDescription
--prompt, -pPrompt text
--promptfilesRead prompt from files (concatenated)
--model, -mModel: gemini-3-pro (default), gemini-3-flash, gemini-3-flash-thinking, gemini-3.1-pro-preview
--image [path]Generate image (default: generated.png)
--reference, --refReference images for vision input
--sessionIdSession ID for multi-turn conversation
--list-sessionsList saved sessions
--jsonOutput as JSON
--loginRefresh cookies, then exit
--cookie-pathCustom cookie file path
--profile-dirChrome profile directory

Models

ModelDescription
gemini-3-proDefault, latest 3.0 Pro
gemini-3-flashFast, lightweight 3.0 Flash
gemini-3-flash-thinking3.0 Flash with thinking
gemini-3.1-pro-preview3.1 Pro preview (empty header, auto-routed)

Authentication

First run opens browser for Google auth. Cookies cached automatically.

When no explicit profile dir is set, cookie refresh may reuse an already-running local Chrome/Chromium debugging session tied to a standard user-data dir. Set --profile-dir or GEMINI_WEB_CHROME_PROFILE_DIR to force a dedicated profile and skip existing-session reuse. This is a best-effort CDP session reuse path, not the Chrome DevTools MCP prompt-based --autoConnect flow described in Chrome's official docs.

Supported browsers (auto-detected): Chrome, Chrome Canary/Beta, Chromium, Edge.

Force refresh: --login flag. Override browser: GEMINI_WEB_CHROME_PATH env var.

Environment Variables

VariableDescription
GEMINI_WEB_DATA_DIRData directory
GEMINI_WEB_COOKIE_PATHCookie file path
GEMINI_WEB_CHROME_PROFILE_DIRChrome profile directory
GEMINI_WEB_CHROME_PATHChrome executable path
HTTP_PROXY, HTTPS_PROXYProxy for Google access (set inline with command)

Sessions

Session files stored in data directory under sessions/<id>.json.

Contains: id, metadata (Gemini chat state), messages array, timestamps.

Extension Support

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

© JimLiu, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 27 other files (scripts) in skills/baoyu-danger-gemini-web of JimLiu/baoyu-skills.

  • SKILL.md
  • scripts/bun.lock
  • scripts/gemini-webapi/client.test.ts
  • scripts/gemini-webapi/client.ts
  • scripts/gemini-webapi/components/gem-mixin.ts
  • scripts/gemini-webapi/components/index.ts
  • scripts/gemini-webapi/constants.ts
  • scripts/gemini-webapi/exceptions.ts
  • scripts/gemini-webapi/index.ts
  • scripts/gemini-webapi/types/candidate.ts
  • scripts/gemini-webapi/types/gem.ts
  • scripts/gemini-webapi/types/grpc.ts
  • scripts/gemini-webapi/types/image.ts
  • scripts/gemini-webapi/types/index.ts
  • scripts/gemini-webapi/types/modeloutput.ts
  • scripts/gemini-webapi/utils/cookie-file.ts
  • … and 12 more

Open the folder on GitHubat commit 1567581

Used in 5 other repositories

We found 5 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 5 other GitHub owners. This page covers the copy in JimLiu/baoyu-skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Gemini Web Reverse-Engineered Client next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Gemini Web Reverse-Engineered Client compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gemini Web Reverse-Engineered Client this skillJimLiu/baoyu-skills27k5 repos~1.6kAutomated safety check: PassMIT
AI Image Generation and Editingzhayujie/CowAgent47k—~1.3kAutomated safety check: PassMIT
Logo Generatorop7418/logo-generator-skill2.2k—~1.8kAutomated safety check: NotesNone
SEO Image GeneratorAgriciDaniel/claude-seo19k2 repos~2.1kAutomated safety check: PassMIT
BlockRun Image GenerationBlockRunAI/ClawRouter6.6k—~2.1kAutomated safety check: PassMIT
Antigravity Gemini ImageuluckyXH/OpenMOSS1.3k—~730Automated safety check: NotesMIT

Similar skills

  • Generates or edits images from text prompts through a Python script that picks an image backend based on which API keys are configured.

    47k GitHub stars~1.3k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Logo Generator

    op7418/logo-generator-skill

    Generate professional SVG logos and high-end showcase images.

    2.2k GitHub stars~1.8k tokensUpdated 5 mo ago
    Media & CreativeAuto-check: notes
  • SEO Image Generator

    AgriciDaniel/claude-seo

    Generates Open Graph previews, blog hero images, product photos and infographics for SEO use through Gemini image tools and the banana extension.

    19k GitHub starsUsed in 2 repos~2.1k tokens
    Media & CreativeAuto-check passed
  • BlockRun Image Generation

    BlockRunAI/ClawRouter

    Generates or edits images through ClawRouter's local image API, with a choice of models and sizes and payment handled automatically through x402.

    6.6k GitHub stars~2.1k tokensUpdated 5 days ago
    Media & CreativeAuto-check passed
  • Antigravity Gemini Image

    uluckyXH/OpenMOSS

    Generate or edit images using the Antigravity-hosted Gemini image model via the local gateway.

    1.3k GitHub stars~730 tokensUpdated 3 mo ago
    Media & CreativeAuto-check: notes
  • Imagen

    sanjay3290/ai-skills

    Generate images using Google Gemini's image generation capabilities.

    432 GitHub starsUsed in 6 repos~657 tokens
    Media & CreativeAuto-check passed

More from JimLiu/baoyu-skills

All 22 skills in this repo
  • Markdown Article Formatter

    JimLiu/baoyu-skills

    Reformats plain text or Markdown articles with frontmatter, a title, a summary, headings, bold, lists and code blocks, and saves a separate formatted copy.

    27k GitHub starsUsed in 6 repos~3.5k tokens
    Auto-check passed
  • X to Markdown Converter

    JimLiu/baoyu-skills

    Saves tweets, threads and X Articles as Markdown files with YAML front matter, using an unofficial API that asks for your consent first.

    27k GitHub starsUsed in 4 repos~1.8k tokens
    Auto-check: warnings
  • SVG Diagram Generator

    JimLiu/baoyu-skills

    Creates standalone dark-themed SVG diagrams, including architecture, flowchart, sequence, structural, mind map, timeline and state machine types.

    27k GitHub starsUsed in 1 repo~3.1k tokens
    Auto-check passed
  • Publishes articles and image-text posts to a WeChat Official Account through the API or Chrome CDP, converting markdown to WeChat-ready HTML with link citations.

    27k GitHub starsUsed in 2 repos~3.6k tokens
    Auto-check: warnings
  • Image Compressor

    JimLiu/baoyu-skills

    Compresses images to WebP by default, or to PNG or JPEG, picking the best available tool on the machine and optionally processing whole folders.

    27k GitHub starsUsed in 5 repos~598 tokens
    Auto-check passed
  • Baoyu Translate

    JimLiu/baoyu-skills

    Translates articles and files in quick, normal or refined mode, with a custom glossary, saved preferences and a review-and-polish workflow for publication quality.

    27k GitHub starsUsed in 1 repo~3.9k tokens
    Auto-check passed

Works with

Questions about Gemini Web Reverse-Engineered Client

What does Gemini Web Reverse-Engineered Client do?

Generates text and images through an unofficial, reverse-engineered Gemini Web API, supporting reference images and multi-turn conversations. Before first use it checks for a consent file recording that the user accepted a disclaimer about using a reverse-engineered API; without one it shows the disclaimer and asks through the agent's own question tool, writing a timestamped consent file on acceptance or stopping outright on a decline. Its logic lives in a bundled scripts folder, a TypeScript port of an existing Python client project, with a single CLI entry point for text and image generation.

When should I use Gemini Web Reverse-Engineered Client?

Gemini Web Reverse-Engineered Client fits situations like: generating an image or text response through Gemini's web interface; providing a reference image as vision input for a Gemini generation; continuing a multi-turn conversation with the Gemini web backend.

How do I install Gemini Web Reverse-Engineered Client in Claude Code?

Run `npx skills add JimLiu/baoyu-skills --skill baoyu-danger-gemini-web -a claude-code`. Or copy the skill folder (skills/baoyu-danger-gemini-web in JimLiu/baoyu-skills) into .claude/skills/baoyu-danger-gemini-web in your project. Claude Code loads it when a task matches its description.

How do I install Gemini Web Reverse-Engineered Client in Codex?

Run `npx skills add JimLiu/baoyu-skills --skill baoyu-danger-gemini-web -a codex`. Or copy the skill folder (skills/baoyu-danger-gemini-web in JimLiu/baoyu-skills) into .agents/skills/baoyu-danger-gemini-web in your project. Codex loads it when a task matches its description.

Can I use Gemini Web Reverse-Engineered Client in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add JimLiu/baoyu-skills --skill baoyu-danger-gemini-web -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/baoyu-danger-gemini-web, .gemini/skills/baoyu-danger-gemini-web, .github/skills/baoyu-danger-gemini-web and .opencode/skills/baoyu-danger-gemini-web in your project.

What does Gemini Web Reverse-Engineered Client need to run?

Going by SKILL.md and its folder, Gemini Web Reverse-Engineered Client needs TypeScript for the scripts in its folder and the command-line tools its instructions call (npx). Our summary lists: Bun or npx to run the bundled TypeScript client; User consent recorded in a local disclaimer file.

Does Gemini Web Reverse-Engineered Client access the network?

SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Gemini Web Reverse-Engineered Client safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Gemini Web Reverse-Engineered Client use?

Gemini Web Reverse-Engineered Client is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Gemini Web Reverse-Engineered Client use?

About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Gemini Web Reverse-Engineered Client?

Skills that share tags, products or a category with Gemini Web Reverse-Engineered Client: AI Image Generation and Editing (zhayujie/CowAgent, 47k stars), Logo Generator (op7418/logo-generator-skill, 2.2k stars), SEO Image Generator (AgriciDaniel/claude-seo, 19k stars) and BlockRun Image Generation (BlockRunAI/ClawRouter, 6.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gemini Web Reverse-Engineered Client?

JimLiu (a GitHub user) maintains it in JimLiu/baoyu-skills, which has 26,507 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on September 10, 2026.

Source: JimLiu/baoyu-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.