Not in the top 1,000 by GitHub stars

hexian2001/soushen-hunter

搜神猎手 - 高性能 Bing/google 搜索引擎 Skill for OpenClaw

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

1a7b7d322b88 → 1a7b7d322b88

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 1a7b7d322b88

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 1a7b7d322b8863337b39a4c4d4f91912c603a5e4

101GitHub stars
0stars in 7 days
1skill in this repository
0commits in 30 days

Heat

0.3
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Oct 25, 2026Oct 25, 2026101

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

soushen-hunter

When your agent uses it

高性能 Bing/Google 搜索引擎 Skill - "搜神猎手" 使用 Playwright 底层 API 进行深度网页搜索和元素提取 功能: 1. Bing/Google 搜索执行 - 返回结构化搜索结果(标题、链接、摘要、来源) 2. 深度页面分析 - 提取页面的所有关键元素(链接、表单、按钮、脚本、元数据) 3. 可配置搜索引擎 - 支持 Bing 和 Google 切换 触发条件: - 用户需要进行网络搜索时 - 需要提取网页结构信息(链接、表单等)时 - 需要无 API 成本的搜索解决方案时 使用方法: - 基础搜索:./soushen "搜索关键词" [--num N] [--engine ENGINE] - 深度分析:./soushen --deep <目标 URL> - 配置引擎:./soushen --set-default-engine bing|google

What it loads into context

Frontmatter

237 tokens

Always available to the agent

SKILL.md

948 tokens

When the skill is activated

Reference documents

1,619 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. 核心功能
  2. 使用方法
  3. 依赖要求
  4. 配置说明
  5. 反检测特性
  6. 注意事项

Scripts executed separately

  • scripts/bing_search.py
  • scripts/google_search.py
  • soushen

Files

  • README.mddoc5,816 bytes
  • SKILL.mdcore3,367 bytes
  • SKILL.mdcore3,367 bytes
  • SKILL.mdcore3,367 bytes
  • SKILL.mdcore3,367 bytes
  • SKILL.mdcore3,367 bytes
  • scripts/bing_search.pyruns19,110 bytes
  • scripts/google_search.pyruns30,578 bytes
  • soushenruns6,693 bytes

No excerpt is shown for this license. Read the source on GitHub.

View the complete source on GitHub

Skills included

  • soushen-hunter

Repository facts

License
No license detected
Created
Mar 4, 2026
Last pushed
Mar 6, 2026
Forks
2
Open issues
1
Project activity
Slowing

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 5, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 4 notes
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 47 signals by file

README.md

  • Network accessline 19
    # 克隆仓库 git clone https://github.com/hexian2001/soushen-hunter.git
  • Network accessline 20
    git clone https://github.com/hexian2001/soushen-hunter.git
  • Network accessline 63
    # 深度页面分析 ./soushen --deep "https://目标网址"
  • Network accessline 64
    ./soushen --deep "https://目标网址"
  • Network accessline 82
    # 深度页面分析 python scripts/bing_search.py --deep "https://目标网址"
  • Network accessline 83
    python scripts/bing_search.py --deep "https://目标网址"
  • Network accessline 94
    # 深度页面分析 python scripts/google_search.py --deep "https://目标网址"
  • Network accessline 95
    python scripts/google_search.py --deep "https://目标网址"
  • Network accessline 130
    # 使用 Bing 引擎 async with BingSearchAgent() as agent:     elements = await agent.extract_page_elements("https://example.com")
  • Network accessline 131
    async with BingSearchAgent() as agent:     elements = await agent.extract_page_elements("https://example.com")     print(f"找到 {len(elements.links)} 个链接")
  • Network accessline 132
    elements = await agent.extract_page_elements("https://example.com")
  • Network accessline 135
    # 使用 Google 引擎 async with GoogleSearchAgent() as agent:     elements = await agent.extract_page_elements("https://example.com")
  • Network accessline 136
    async with GoogleSearchAgent() as agent:     elements = await agent.extract_page_elements("https://example.com")     print(f"找到 {len(elements.links)} 个链接")
  • Network accessline 137
    elements = await agent.extract_page_elements("https://example.com")

SKILL.md

  • Network accessline 60
    ./soushen --deep https://example.com
  • Network accessline 87
    # 深度分析 elements = await agent.extract_page_elements("https://example.com")
  • Network accessline 88
    elements = await agent.extract_page_elements("https://example.com")

scripts/bing_search.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Access to secretsline 27
    [Credential-related source omitted]
  • Access to secretsline 28
    [Credential-related source omitted]
  • Network accessline 145
    try:             await self.page.goto('https://www.bing.com', wait_until='domcontentloaded')
  • Network accessline 146
    await self.page.goto('https://www.bing.com', wait_until='domcontentloaded')
  • Network accessline 464
    "python bing_search.py 'OpenClaw AI'",                 "python bing_search.py 'AI' --num 20",                 "python bing_search.py --deep https://example.com",
  • Network accessline 465
    "python bing_search.py 'AI' --num 20",                 "python bing_search.py --deep https://example.com",                 "python bing_search.py --deep https://example.com --text-limit 50000",
  • Network accessline 466
    "python bing_search.py --deep https://example.com",
  • Network accessline 467
    "python bing_search.py --deep https://example.com --text-limit 50000",
  • Network accessline 468
    "python bing_search.py --deep https://example.com --text-offset 10000 --text-limit 10000"
  • Access to secretsline 477
    [Credential-related source omitted]

scripts/google_search.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Access to secretsline 30
    [Credential-related source omitted]
  • Access to secretsline 31
    [Credential-related source omitted]
  • Access to secretsline 168
    [Credential-related source omitted]
  • Network accessline 310
    encoded_query = quote(query)             search_url = f'https://www.google.com/search?q={encoded_query}&num={num_results}'
  • Network accessline 311
    search_url = f'https://www.google.com/search?q={encoded_query}&num={num_results}'
  • Network accessline 408
    if url and url.startswith('/url?q='):                 url = url.split('/url?q=')[1].split('&')[0]             elif url and url.startswith('http://www.google.com/url?q='):
  • Network accessline 409
    url = url.split('/url?q=')[1].split('&')[0]             elif url and url.startswith('http://www.google.com/url?q='):                 from urllib.parse import parse_qs
  • Network accessline 410
    elif url and url.startswith('http://www.google.com/url?q='):                 from urllib.parse import parse_qs                 parsed = urlparse(url)
  • Network accessline 762
    "examples": [                 "python google_search.py 'OpenClaw AI'",                 "python google_search.py --deep https://example.com",
  • Network accessline 763
    "python google_search.py 'OpenClaw AI'",                 "python google_search.py --deep https://example.com",                 "python google_search.py --deep https://example.com --text-limit 50000",
  • Network accessline 764
    "python google_search.py --deep https://example.com",
  • Network accessline 765
    "python google_search.py --deep https://example.com --text-limit 50000",
  • Network accessline 766
    "python google_search.py --deep https://example.com --text-offset 10000 --text-limit 10000"
  • Access to secretsline 783
    [Credential-related source omitted]

soushen

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Network accessline 73
    "./soushen 'AI 人工智能' --num 20",             "./soushen 'AI 人工智能' --engine google",             "./soushen --deep https://example.com",
  • Network accessline 74
    "./soushen 'AI 人工智能' --engine google",             "./soushen --deep https://example.com",             "./soushen --config --engine google  # 设置默认使用 Google",
  • Network accessline 75
    "./soushen --deep https://example.com",

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Declared and executed: 2 facts
Signal confidence: 47 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.