1---
2name: baoyu-danger-gemini-web
3description: 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.
4version: 1.56.1
5metadata:
6  openclaw:
7    homepage: https://github.com/JimLiu/baoyu-skills#baoyu-danger-gemini-web
8    requires:
9      anyBins:
10        - bun
11        - npx
12---
13 
14# Gemini Web Client
15 
16Text/image generation via Gemini Web API. Supports reference images and multi-turn conversations.
17 
18## User Input Tools
19 
20When this skill prompts the user, follow this tool-selection rule (priority order):
21 
221. **Prefer built-in user-input tools** exposed by the current agent runtime — e.g., `AskUserQuestion`, `request_user_input`, `clarify`, `ask_user`, or any equivalent.
232. **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.
243. **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.
25 
26Concrete `AskUserQuestion` references below are examples — substitute the local equivalent in other runtimes.
27 
28## Script Directory
29 
30**Important**: All scripts are located in the `scripts/` subdirectory of this skill.
31 
32**Agent Execution Instructions**:
331. Determine this SKILL.md file's directory path as `{baseDir}`
342. Script path = `{baseDir}/scripts/<script-name>.ts`
353. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun
364. Replace all `{baseDir}` and `${BUN_X}` in this document with actual values
37 
38**Script Reference**:
39| Script | Purpose |
40|--------|---------|
41| `scripts/main.ts` | CLI entry point for text/image generation |
42| `scripts/gemini-webapi/*` | TypeScript port of `gemini_webapi` (GeminiClient, types, utils) |
43 
44## Consent Check (REQUIRED)
45 
46Before first use, verify user consent for reverse-engineered API usage.
47 
48**Consent file locations**:
49- macOS: `~/Library/Application Support/baoyu-skills/gemini-web/consent.json`
50- Linux: `~/.local/share/baoyu-skills/gemini-web/consent.json`
51- Windows: `%APPDATA%\baoyu-skills\gemini-web\consent.json`
52 
53**Flow**:
541. Check if consent file exists with `accepted: true` and `disclaimerVersion: "1.0"`
552. If valid consent exists → print warning with `acceptedAt` date, proceed
563. If no consent → show disclaimer, ask user via `AskUserQuestion`:
57   - "Yes, I accept" → create consent file with ISO timestamp, proceed
58   - "No, I decline" → output decline message, stop
594. Consent file format: `{"version":1,"accepted":true,"acceptedAt":"<ISO>","disclaimerVersion":"1.0"}`
60 
61---
62 
63## Preferences (EXTEND.md)
64 
65Check EXTEND.md in priority order — the first one found wins:
66 
67| Priority | Path | Scope |
68|----------|------|-------|
69| 1 | `.baoyu-skills/baoyu-danger-gemini-web/EXTEND.md` | Project |
70| 2 | `${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-danger-gemini-web/EXTEND.md` | XDG |
71| 3 | `$HOME/.baoyu-skills/baoyu-danger-gemini-web/EXTEND.md` | User home |
72 
73If none found, use defaults.
74 
75**EXTEND.md supports**: Default model, proxy settings, custom data directory.
76 
77## Usage
78 
79```bash
80# Text generation
81${BUN_X} {baseDir}/scripts/main.ts "Your prompt"
82${BUN_X} {baseDir}/scripts/main.ts --prompt "Your prompt" --model gemini-3-flash
83 
84# Image generation
85${BUN_X} {baseDir}/scripts/main.ts --prompt "A cute cat" --image cat.png
86${BUN_X} {baseDir}/scripts/main.ts --promptfiles system.md content.md --image out.png
87 
88# Vision input (reference images)
89${BUN_X} {baseDir}/scripts/main.ts --prompt "Describe this" --reference image.png
90${BUN_X} {baseDir}/scripts/main.ts --prompt "Create variation" --reference a.png --image out.png
91 
92# Multi-turn conversation
93${BUN_X} {baseDir}/scripts/main.ts "Remember: 42" --sessionId session-abc
94${BUN_X} {baseDir}/scripts/main.ts "What number?" --sessionId session-abc
95 
96# JSON output
97${BUN_X} {baseDir}/scripts/main.ts "Hello" --json
98```
99 
100## Options
101 
102| Option | Description |
103|--------|-------------|
104| `--prompt`, `-p` | Prompt text |
105| `--promptfiles` | Read prompt from files (concatenated) |
106| `--model`, `-m` | Model: gemini-3-pro (default), gemini-3-flash, gemini-3-flash-thinking, gemini-3.1-pro-preview |
107| `--image [path]` | Generate image (default: generated.png) |
108| `--reference`, `--ref` | Reference images for vision input |
109| `--sessionId` | Session ID for multi-turn conversation |
110| `--list-sessions` | List saved sessions |
111| `--json` | Output as JSON |
112| `--login` | Refresh cookies, then exit |
113| `--cookie-path` | Custom cookie file path |
114| `--profile-dir` | Chrome profile directory |
115 
116## Models
117 
118| Model | Description |
119|-------|-------------|
120| `gemini-3-pro` | Default, latest 3.0 Pro |
121| `gemini-3-flash` | Fast, lightweight 3.0 Flash |
122| `gemini-3-flash-thinking` | 3.0 Flash with thinking |
123| `gemini-3.1-pro-preview` | 3.1 Pro preview (empty header, auto-routed) |
124 
125## Authentication
126 
127First run opens browser for Google auth. Cookies cached automatically.
128 
129When 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.
130Set `--profile-dir` or `GEMINI_WEB_CHROME_PROFILE_DIR` to force a dedicated profile and skip existing-session reuse.
131This is a best-effort CDP session reuse path, not the Chrome DevTools MCP prompt-based `--autoConnect` flow described in Chrome's official docs.
132 
133Supported browsers (auto-detected): Chrome, Chrome Canary/Beta, Chromium, Edge.
134 
135Force refresh: `--login` flag. Override browser: `GEMINI_WEB_CHROME_PATH` env var.
136 
137## Environment Variables
138 
139| Variable | Description |
140|----------|-------------|
141| `GEMINI_WEB_DATA_DIR` | Data directory |
142| `GEMINI_WEB_COOKIE_PATH` | Cookie file path |
143| `GEMINI_WEB_CHROME_PROFILE_DIR` | Chrome profile directory |
144| `GEMINI_WEB_CHROME_PATH` | Chrome executable path |
145| `HTTP_PROXY`, `HTTPS_PROXY` | Proxy for Google access (set inline with command) |
146 
147## Sessions
148 
149Session files stored in data directory under `sessions/<id>.json`.
150 
151Contains: `id`, `metadata` (Gemini chat state), `messages` array, timestamps.
152 
153## Extension Support
154 
155Custom configurations via EXTEND.md. See **Preferences** section for paths and supported options.
156