baoyu-danger-gemini-web
Generates images and text via reverse-engineered Gemini Web API.
Skill by guanyang
Chalk Labs
Need help deploying baoyu-danger-gemini-web?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/guanyang-baoyu-danger-gemini-web
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: backend
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill 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.
- License
- MIT
- Instructions
- 144 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
- Instructions read files in your home folder (~/.ssh, ~/.aws…)
Files (28)
- SKILL.md
- bun.lock · scripts/
- client.test.ts · scripts/gemini-webapi/
- client.ts · scripts/gemini-webapi/
- gem-mixin.ts · scripts/gemini-webapi/components/
- index.ts · scripts/gemini-webapi/components/
- constants.ts · scripts/gemini-webapi/
- exceptions.ts · scripts/gemini-webapi/
- index.ts · scripts/gemini-webapi/
- 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/types/
- cookie-file.ts · scripts/gemini-webapi/utils/
- decorators.ts · scripts/gemini-webapi/utils/
- get-access-token.ts · scripts/gemini-webapi/utils/
- http.ts · scripts/gemini-webapi/utils/
- index.ts · scripts/gemini-webapi/utils/
- load-browser-cookies.ts · scripts/gemini-webapi/utils/
- logger.ts · scripts/gemini-webapi/utils/
- parsing.ts · scripts/gemini-webapi/utils/
- paths.ts · scripts/gemini-webapi/utils/
- rotate-1psidts.ts · scripts/gemini-webapi/utils/
- upload-file.ts · scripts/gemini-webapi/utils/
- main.ts · scripts/
- package.json · scripts/
SKILL.md (first lines)
# 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
```bash
${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.From guanyang/open-agent-hub, MIT.
More from guanyang/open-agent-hub
- 0.700score
notebooklm
guanyang
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini.
SkillBFreshness: B★ 980Claude Code +9 - 0.691score
claude-academy-guide
guanyang
Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials…
SkillBFreshness: B★ 980Claude Code +9 - 0.648score
baoyu-image-cards
guanyang
Generates infographic image card series with 12 visual styles, 8 layouts, and 3 color palettes.
SkillCFreshness: C★ 980Claude Code +9 - 0.644score
baoyu-imagine
guanyang
AI image generation with OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream and Replicate APIs.
SkillCFreshness: C★ 980Claude Code +9 - 0.639score
remotion-best-practices
guanyang
Best practices and domain knowledge for building videos programmatically with Remotion (videos in React/TypeScript, rendered to MP4).
SkillCFreshness: C★ 980Claude Code +9 - 0.629score
mediabunny
guanyang
Multimedia handling with the Mediabunny library
SkillCFreshness: C★ 980Claude Code +9 - 0.541score
mcp-builder
guanyang
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools.
SkillCFreshness: C★ 980Claude Code +9 - 0.541score
skill-creator
guanyang
Create new skills, modify and improve existing skills, and measure skill performance.
SkillCFreshness: C★ 980Claude Code +9 - 0.537score
algorithmic-art
guanyang
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration.
SkillCFreshness: C★ 980Claude Code +9 - 0.537score
brand-guidelines
guanyang
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel.
SkillCFreshness: C★ 980Claude Code +9 - 0.537score
pdf
guanyang
Use this skill whenever the user wants to do anything with PDF files.
SkillCFreshness: C★ 980Claude Code +9 - 0.537score
canvas-design
guanyang
Create beautiful visual art in .png and .pdf documents using design philosophy.
SkillCFreshness: C★ 980Claude Code +9
Signals
- Stars
- 980
- Forks
- 165
- Open issues
- 4
- Last commit (this folder)
- Jun 20, 2026 (4 months ago)
- Last release
- Jun 24, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/guanyang/open-agent-hub
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
- 0.770score
baoyu-danger-gemini-web
JimLiu
Generates images and text via reverse-engineered Gemini Web API.
SkillCFreshness: C★ 26.9KClaude Code +9 - 0.299score
baoyu-danger-gemini-web
SassumiX
Generates images and text via reverse-engineered Gemini Web API.
SkillCFreshness: C★ 2Claude Code +9 - 0.246score
baoyu-danger-gemini-web
chengyihua
Generates images and text via reverse-engineered Gemini Web API.
SkillDFreshness: DClaude Code +9
More from guanyang
- 0.700score
notebooklm
guanyang
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini.
SkillBFreshness: B★ 980Claude Code +9 - 0.691score
claude-academy-guide
guanyang
Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials…
SkillBFreshness: B★ 980Claude Code +9 - 0.648score
baoyu-image-cards
guanyang
Generates infographic image card series with 12 visual styles, 8 layouts, and 3 color palettes.
SkillCFreshness: C★ 980Claude Code +9 - 0.644score
baoyu-imagine
guanyang
AI image generation with OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream and Replicate APIs.
SkillCFreshness: C★ 980Claude Code +9 - 0.639score
remotion-best-practices
guanyang
Best practices and domain knowledge for building videos programmatically with Remotion (videos in React/TypeScript, rendered to MP4).
SkillCFreshness: C★ 980Claude Code +9 - 0.629score
mediabunny
guanyang
Multimedia handling with the Mediabunny library
SkillCFreshness: C★ 980Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get baoyu-danger-gemini-web running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
baoyu-danger-gemini-web skill. Agent Mart. https://agentmart.dev/skills/guanyang-baoyu-danger-gemini-web (last updated 2026-10-24)