功能描述

Headless browser automation CLI optimized for AI agents with accessibility tree snapshots. And also 50+ models for image generation, video generation, text-t...

使用说明 (SKILL.md)

SkillBoss

Name: Pub Agent Browser Clawdbot
Author: modestyrichards

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 appears to be documentation for a remote aggregator API (api.heybossai.com) rather than a local headless browser tool as its name implies. Before installing or providing SKILLBOSS_API_KEY: (1) Confirm you actually want calls routed to https://api.heybossai.com and not local browser automation; (2) Verify the reputation and privacy policy of heybossai.com and the publisher (owner ID is unknown); (3) Limit the API key's privileges and rotate/revoke it if misused; (4) Avoid sending sensitive secrets, PII, or files to the skill until you trust the endpoint; (5) If you expected a local headless browser skill, do not install — this skill will not provide that functionality. If possible, ask the publisher for clarification or a version that actually includes the browser automation instructions/binaries.

功能分析

Type: OpenClaw Skill Name: agent-browser-clawdbots Version: 1.0.0 The skill bundle exhibits significant functional discrepancies, claiming in its description to be a 'Headless browser automation CLI' while the documentation focuses entirely on an API aggregator service (api.heybossai.com). It lists several non-existent or future-dated models, such as 'openai/gpt-5' and 'bedrock/claude-4-6-opus', which is highly deceptive. Furthermore, the documentation references a 'run.mjs' script that is missing from the bundle, and the inclusion of high-risk capabilities like SMS and Email via an unverified third-party API warrants caution.

能力评估

⚠ Purpose & Capability

Name/description advertise a headless browser automation CLI and accessibility snapshots, but the SKILL.md only documents calls to a remote service (https://api.heybossai.com) for many model types. There are no browser automation commands, local binaries, or references to accessibility trees — this is a clear mismatch between claimed purpose and actual content.

⚠ Instruction Scope

Instructions are concrete curl examples that send data to api.heybossai.com using SKILLBOSS_API_KEY. They enumerate many model types (chat, image, video, scrapers, email, SMS, LinkedIn scraping, etc.), meaning the skill will transmit user-provided content to that external API. The SKILL.md does not instruct reading local secrets or files, but it does give endpoints that can perform scraping and outbound messaging — which could cause sensitive data to be sent off‑platform if the agent forwards it.

✓ Install Mechanism

Instruction-only skill with no install spec and no code files — nothing is written to disk by the skill itself, reducing local persistence risk.

ℹ Credentials

Only one required env var (SKILLBOSS_API_KEY) is declared and used in examples, which is proportionate if the skill is a thin client for the named API. However, because the skill's description suggests a local browser tool (which would not need a remote API key), the requested credential is inconsistent with the advertised purpose. The API key would grant the external service the ability to act on behalf of the user for all listed model/actions (including scraping, email/SMS), so treat it as sensitive.

✓ Persistence & Privilege

always is false and there is no install or configuration write described. The skill does not request elevated or permanent agent privileges in the provided files.

版本历史

v1.0.0

Initial release of agent-browser-clawdbot: a headless browser automation CLI for AI agents, featuring rich AI model integrations. - Provides headless browser automation with accessibility tree snapshots for agents. - Integrates API access to 50+ models for chat, image/video generation, text-to-speech, speech-to-text, music, search, document processing, email, and SMS. - Includes detailed CLI usage examples for each supported AI service. - Supports unified API key authentication via SKILLBOSS_API_KEY. - Enables smart routing to automatically select optimal models for tasks.

元数据

Slug agent-browser-clawdbots

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 Clawdbot 是什么？

Headless browser automation CLI optimized for AI agents with accessibility tree snapshots. And also 50+ models for image generation, video generation, text-t... 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 Clawdbot？

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

Pub Agent Browser Clawdbot 是免费的吗？

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

Pub Agent Browser Clawdbot 支持哪些平台？

Pub Agent Browser Clawdbot 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 Clawdbot？

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

Pub Agent Browser Clawdbot