功能描述

A fast headless browser automation CLI that enables AI agents to navigate, click, type, and snapshot pages. And also 50+ models for image generation, video g...

使用说明 (SKILL.md)

SkillBoss

Name: Pub Agent Browser
Author: quincygunter

One API key, 50+ models across providers (Bedrock, OpenAI, Vertex, ElevenLabs, Replicate, Minimax, and more). Call any model directly by ID, or use smart routing to auto-select the cheapest or highest-quality option for a task.

Base URL: https://api.heybossai.com/v1 Auth: -H "Authorization: Bearer $SKILLBOSS_API_KEY"

List Models

curl -s https://api.heybossai.com/v1/models \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY"

Filter by type:

curl -s "https://api.heybossai.com/v1/models?types=image" \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY"

Get full docs for specific models:

curl -s "https://api.heybossai.com/v1/models?ids=mm/img,bedrock/claude-4-5-sonnet" \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY"

Types: chat, image, video, tts, stt, music, search, scraper, email, storage, ppt, embedding

Chat

curl -s -X POST https://api.heybossai.com/v1/chat/completions \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "bedrock/claude-4-5-sonnet",
    "messages": [{"role": "user", "content": "Explain quantum computing"}]
  }'

Parameter	Description
`model`	`bedrock/claude-4-5-sonnet`, `bedrock/claude-4-6-opus`, `openai/gpt-5`, `vertex/gemini-2.5-flash`, `deepseek/deepseek-chat`
`messages`	Array of `{role, content}` objects
`system`	Optional system prompt
`temperature`	Optional, 0.0–1.0
`max_tokens`	Optional, max output tokens

Response: choices[0].message.content

Image Generation

curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mm/img",
    "inputs": {"prompt": "A sunset over mountains"}
  }'

Save to file:

URL=$(curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mm/img", "inputs": {"prompt": "A sunset over mountains"}}' \
  | jq -r '.image_url // .result.image_url // .data[0]')
curl -sL "$URL" -o sunset.png

Parameter	Description
`model`	`mm/img`, `replicate/black-forest-labs/flux-2-pro`, `replicate/black-forest-labs/flux-1.1-pro-ultra`, `vertex/gemini-2.5-flash-image-preview`, `vertex/gemini-3-pro-image-preview`
`inputs.prompt`	Text description of the image
`inputs.size`	Optional, e.g. `"1024*768"`
`inputs.aspect_ratio`	Optional, e.g. `"16:9"`

Response: image_url, data[0], or generated_images[0]

Video Generation

curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mm/t2v",
    "inputs": {"prompt": "A cat playing with yarn"}
  }'

Image-to-video:

curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mm/i2v",
    "inputs": {"prompt": "Zoom in slowly", "image": "https://example.com/photo.jpg"}
  }'

Parameter	Description
`model`	`mm/t2v` (text-to-video), `mm/i2v` (image-to-video), `vertex/veo-3-generate-preview`
`inputs.prompt`	Text description
`inputs.image`	Image URL (for i2v)
`inputs.duration`	Optional, seconds

Response: video_url

Text-to-Speech

curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax/speech-01-turbo",
    "inputs": {"text": "Hello world", "voice_setting": {"voice_id": "male-qn-qingse", "speed": 1.0}}
  }'

Parameter	Description
`model`	`minimax/speech-01-turbo`, `elevenlabs/eleven_multilingual_v2`, `openai/tts-1`
`inputs.text`	Text to speak
`inputs.voice`	Voice name (e.g. `alloy`, `nova`, `shimmer`) for OpenAI
`inputs.voice_id`	Voice ID for ElevenLabs

Response: audio_url or binary audio data

Speech-to-Text

curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/whisper-1",
    "inputs": {"audio_data": "BASE64_AUDIO", "filename": "recording.mp3"}
  }'

Response: text

Music Generation

curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "replicate/elevenlabs/music",
    "inputs": {"prompt": "upbeat electronic", "duration": 30}
  }'

Parameter	Description
`model`	`replicate/elevenlabs/music`, `replicate/meta/musicgen`, `replicate/google/lyria-2`
`inputs.prompt`	Music description
`inputs.duration`	Duration in seconds

Response: audio_url

Background Removal

curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "replicate/remove-bg",
    "inputs": {"image": "https://example.com/photo.jpg"}
  }'

Response: image_url or data[0]

Document Processing

curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "reducto/parse",
    "inputs": {"document_url": "https://example.com/file.pdf"}
  }'

Parameter	Description
`model`	`reducto/parse` (PDF/DOCX to markdown), `reducto/extract` (structured extraction)
`inputs.document_url`	URL of the document
`inputs.instructions`	For extract: `{"schema": {...}}`

Web Search

curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "linkup/search",
    "inputs": {"query": "latest AI news", "depth": "standard", "outputType": "searchResults"}
  }'

Parameter	Description
`model`	`linkup/search`, `perplexity/sonar`, `firecrawl/scrape`
`inputs.query`	Search query
`inputs.depth`	`standard` or `deep`
`inputs.outputType`	`searchResults`, `sourcedAnswer`, `structured`

Email

curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "email/send",
    "inputs": {"to": "[email protected]", "subject": "Hello", "html": "\x3Cp>Hi\x3C/p>"}
  }'

SMS Verification

Send OTP:

curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "prelude/verify-send",
    "inputs": {"target": {"type": "phone_number", "value": "+1234567890"}}
  }'

Verify OTP:

curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "prelude/verify-check",
    "inputs": {"target": {"type": "phone_number", "value": "+1234567890"}, "code": "123456"}
  }'

Smart Mode (auto-select best model)

List task types:

curl -s -X POST https://api.heybossai.com/v1/pilot \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"discover": true}'

Run a task:

curl -s -X POST https://api.heybossai.com/v1/pilot \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "type": "image",
    "inputs": {"prompt": "A sunset over mountains"}
  }'

Available Models (50+)

Category	Models	Details
Chat	25+ models — Claude, GPT, Gemini, DeepSeek, Qwen, HuggingFace	`chat-models.md`
Image	9 models — Gemini, FLUX, upscaling, background removal	`image-models.md`
Video	3 models — Veo, text-to-video, image-to-video	`video-models.md`
Audio	11 models — TTS, STT, music generation	`audio-models.md`
Search & Scraping	19 models — Perplexity, Firecrawl, ScrapingDog, CEO interviews	`search-models.md`
Tools	11 models — documents, email, SMS, embeddings, presentations	`tools-models.md`

Notes:

Get SKILLBOSS_API_KEY at https://www.skillboss.co
Use the models endpoint to discover all available models live
Use smart mode (pilot) to auto-select the best model for any task

安全使用建议

This skill is suspicious because its name/description promise a headless browser CLI but the SKILL.md is actually documentation for a third‑party multi‑model API (api.heybossai.com) and requires an API key. Before installing: 1) Verify the skill's source and reputation (there's no homepage or repo). 2) Ask the publisher why the browser functionality is missing and whether any local browser automation will run (right now it will only call a remote API). 3) Treat the SKILLBOSS_API_KEY like a powerful credential — do not supply it if you would be sending sensitive files, credentials, or private data to an untrusted third party. 4) If you need local headless browser automation, prefer a skill that documents local binaries (puppeteer/playwright) or provides clear install steps and code. 5) Consider testing with a scoped/limited API key or on non-sensitive data and review billing/terms on api.heybossai.com before use.

功能分析

Type: OpenClaw Skill Name: agent-browsers Version: 1.0.0 The skill bundle describes an AI model aggregator service ('SkillBoss') but contains several red flags, including the listing of non-existent or unreleased models (e.g., 'openai/gpt-5', 'bedrock/claude-4-6-opus') and a discrepancy between its description as a 'headless browser' and its actual content as a REST API wrapper. The documentation references a missing execution script ('run.mjs') and directs users to provide an API key for an external domain (heybossai.com/skillboss.co). While no direct evidence of malware or exfiltration was found, the deceptive model claims and inconsistent functional descriptions are characteristic of fraudulent services or prompt-injection lures.

能力评估

⚠ Purpose & Capability

Name/description advertise a 'fast headless browser automation CLI' but SKILL.md contains only curl examples and model/API documentation for https://api.heybossai.com/v1 (many models). There are no browser automation commands, binaries, or local tooling described. The declared SKILLBOSS_API_KEY is consistent with the docs but not with the advertised local/browser automation purpose — this is a clear mismatch.

⚠ Instruction Scope

Runtime instructions tell the agent to call an external API (api.heybossai.com) for chat, image/video/tts/stt, scraping, email, SMS, document parsing, storage, etc. The agent is guided to upload data (audio, images, documents, base64 audio) and download results. While the skill does not instruct reading local secrets or arbitrary files explicitly, it enables sending potentially sensitive content to a third party. No instructions implement local headless browser automation despite the skill name.

✓ Install Mechanism

No install spec and no code files — this is instruction-only, so nothing is written to disk by the skill itself. That reduces installation risk. The primary remaining risk is network I/O to the external API.

⚠ Credentials

The skill requests a single env var, SKILLBOSS_API_KEY, which is appropriate for an API-based skill. However, that single key grants broad capabilities (access to 50+ models, email/SMS/send, storage, document parsing, scraping). Given the mismatch between the advertised browser purpose and the API functionality, the breadth of operations that the key enables is disproportionate to what a user might expect from a 'browser' skill and could permit data exfiltration or actions the user did not intend.

✓ Persistence & Privilege

always is false and the skill is user-invocable; it does not request permanent presence or system-wide configuration changes. Autonomous invocation is allowed by default (disable-model-invocation is false) which is normal; this combination is not itself an added red flag.

版本历史

v1.0.0

- Initial release of agent-browser. - Provides a fast headless browser automation CLI for AI agents to navigate, click, type, and snapshot pages. - Supports over 50 models for image, video, and music generation, text-to-speech, speech-to-text, chat, web search, document parsing, email, and SMS. - Centralizes API access to models from providers such as Bedrock, OpenAI, Vertex, ElevenLabs, Replicate, and Minimax. - Features smart routing to automatically select the best or most cost-effective model for each task. - Requires a single API key for unified access.

元数据

Slug agent-browsers

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题

Pub Agent Browser 是什么？

A fast headless browser automation CLI that enables AI agents to navigate, click, type, and snapshot pages. And also 50+ models for image generation, video g... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 293 次。

如何安装 Pub Agent Browser？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install agent-browsers」即可一键安装，无需额外配置。

Pub Agent Browser 是免费的吗？

是的，Pub Agent Browser 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Pub Agent Browser 支持哪些平台？

Pub Agent Browser 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Pub Agent Browser？

由 QuincyGunter（@quincygunter）开发并维护，当前版本 v1.0.0。

Pub Agent Browser