baoyu-skills is a collection of reusable skills that give AI coding agents instructions for tasks such as preparing and publishing content. It supports agents including Claude Code, Codex, and OpenClaw, with users installing only the workflows they need. The catalogue contains selected skills from this collection.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add JimLiu/baoyu-skills --skill baoyu-danger-gemini-webgit clone --depth 1 https://github.com/JimLiu/baoyu-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jimliu/baoyu-skills/baoyu-danger-gemini-web)<a href="https://agentmods.dev/skills/jimliu/baoyu-skills/baoyu-danger-gemini-web"><img src="https://agentmods.dev/badge/skills/jimliu/baoyu-skills/baoyu-danger-gemini-web/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jimliu/baoyu-skills/baoyu-danger-gemini-web"><img src="https://agentmods.dev/badge/skills/jimliu/baoyu-skills/baoyu-danger-gemini-web.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Excessive Agency · line 82 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium MCP Rug Pull · line 35 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Excessive Agency · line 56 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00074 | $0.01695 |
| Opus 5 | $0.00037 | $0.00847 |
| Sonnet 5 | $0.00015 | $0.00339 |
| Haiku 4.5 | $0.00007 | $0.00169 |
Grade A, and why
baoyu-danger-gemini-web scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
3 near-identical copies found in the catalogue:
- baoyu-danger-gemini-web — 100% identical, 0 lines differ
- baoyu-danger-gemini-web — 100% identical, 0 lines differ
- baoyu-danger-gemini-web — 86% identical, 51 lines differ
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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):
- Prefer built-in user-input tools exposed by the current agent runtime — e.g.,
AskUserQuestion,request_user_input,clarify,ask_user, or any equivalent. - 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.
- 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:
- Determine this SKILL.md file's directory path as
{baseDir} - Script path =
{baseDir}/scripts/<script-name>.ts - Resolve
${BUN_X}runtime: ifbuninstalled →bun; ifnpxavailable →npx -y bun; else suggest installing bun - Replace all
{baseDir}and${BUN_X}in this document with actual values
Script Reference:
| 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 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:
- Check if consent file exists with
accepted: trueanddisclaimerVersion: "1.0" - If valid consent exists → print warning with
acceptedAtdate, proceed - 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
- Consent file format:
{"version":1,"accepted":true,"acceptedAt":"<ISO>","disclaimerVersion":"1.0"}
What ships with it
27 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- scripts/bun.lock 389 B
- scripts/gemini-webapi/client.test.ts 1.0 KB runs code
- scripts/gemini-webapi/client.ts 23 KB runs code
- scripts/gemini-webapi/components/gem-mixin.ts 5.6 KB runs code
- scripts/gemini-webapi/components/index.ts 44 B runs code
- scripts/gemini-webapi/constants.ts 3.8 KB runs code
- scripts/gemini-webapi/exceptions.ts 1.2 KB runs code
- scripts/gemini-webapi/index.ts 273 B runs code
- scripts/gemini-webapi/types/candidate.ts 1.3 KB runs code
- scripts/gemini-webapi/types/gem.ts 1.8 KB runs code
- scripts/gemini-webapi/types/grpc.ts 369 B runs code
- scripts/gemini-webapi/types/image.ts 3.4 KB runs code
- scripts/gemini-webapi/types/index.ts 232 B runs code
- scripts/gemini-webapi/types/modeloutput.ts 816 B runs code
- scripts/gemini-webapi/utils/cookie-file.ts 2.3 KB runs code
- scripts/gemini-webapi/utils/decorators.ts 1.1 KB runs code
- scripts/gemini-webapi/utils/get-access-token.ts 7.4 KB runs code
- scripts/gemini-webapi/utils/http.ts 1.6 KB runs code
- scripts/gemini-webapi/utils/index.ts 1021 B runs code
- scripts/gemini-webapi/utils/load-browser-cookies.ts 9.6 KB runs code
- scripts/gemini-webapi/utils/logger.ts 1.2 KB runs code
- scripts/gemini-webapi/utils/parsing.ts 1.3 KB runs code
- scripts/gemini-webapi/utils/paths.ts 2.3 KB runs code
- scripts/gemini-webapi/utils/rotate-1psidts.ts 1.5 KB runs code
- scripts/gemini-webapi/utils/upload-file.ts 1.1 KB runs code
- scripts/main.ts 15 KB runs code
- scripts/package.json 145 B
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 13d ago First seen · 156 lines · 74 tokens per session scan A 290c0f8b3957
baoyu-danger-gemini-web is a skill published in the GitHub repository JimLiu/baoyu-skills (25,839 stars, last pushed 2d ago), licensed MIT. It adds 74 tokens to every session and 1,695 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
llm-inference-benchmark
Benchmark OpenAI-compatible LLM inference servers (vLLM, SGLang, or anything serving /v1/completions; local, cross-host via TARGETHOST= , or behind a TLS+Bearer proxy via --base-url + OPENAIAPIKEY) with sglang.benchserving run as a standalone dockerized client — one engine-agnostic script (scripts/benchsweep.sh)…
deploy-kimi-k26-on-rtx-pro-6000
Deploy and serve Moonshot Kimi-K2.6 (1T MoE, MLA, 256K context, vision) in a user-chosen quantization — official INT4 QAT (moonshotai/Kimi-K2.6, compressed-tensors→Marlin; vLLM or SGLang) or NVFP4 (nvidia/Kimi-K2.6-NVFP4, ModelOpt FP4; vLLM only — SGLang NVFP4 is NaN-broken on sm120) — on a Linux server (verified…
deploy-kimi-k3-on-rtx-pro-6000
Deploy and serve Moonshot Kimi-K3 (2.8T MoE, hybrid KDA+MLA attention, native vision via MoonViT-3d) from Unsloth's GGUF quantizations (unsloth/Kimi-K3-GGUF) via llama.cpp on a Linux server with 8x NVIDIA RTX PRO 6000 Blackwell Server Edition (96 GB, sm120) GPUs. Unlike vLLM/SGLang's tensor-parallel all-in-VRAM…
ubuntu-nvidia-gpu-enablement
Enable NVIDIA GPUs on a Ubuntu server for compute/inference serving — install the open-kernel-module driver (required for Blackwell/Hopper), CUDA toolkit, turn on IOMMU (inteliommu=on iommu=pt), set up nvidia-persistenced, and install/wire a container runtime (Docker + nvidia-container-toolkit, or the minimal CLI)…
daftai-gpt-image-2-5-prompt-optimizer
A prompt editor that turns natural-language image ideas and rough requests into ready-to-use prompts for GPT Image 2.5. It produces text prompts, not images, and follows that model’s official prompting guidance.
dl-transformer-finetune
Build transformer fine-tuning run plans with task settings, hyperparameters, and model-card outputs. Use for repeatable Hugging Face or PyTorch finetuning workflows.