菜单
Search the web using lynx and DuckDuckGo. Performs text-based web searches and can dump specific website content. Do NOT use in Claude Code — use the built-in WebSearch tool instead. Only use this skill in environments where WebSearch is unavailable.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/meain/dotfiles --skill web-search命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Create a literate org-mode document with executable bash source blocks (org-babel) so the user can re-run commands/queries themselves in Emacs, then open it via emacsclient. Triggers: /literate-org, 'literate org document', 'org file with runnable blocks', 'org doc I can execute', 'make this verifiable in org', 'create an org document with executable commands'
Manage Jira issues using the jira CLI — lookup, create, edit, transition, assign, comment, link, and search. Triggers: /jira, "look up jira issue", "check jira ticket", "create jira issue", "update jira", "move ticket to", "assign issue", "add comment to", "what's the status of PROJ-123", any mention of a Jira issue key like PROJ-123
Generate an interactive local HTML review page for a large PR or diff, grouping the changed files by logical concern (not just by file) so a reviewer can go through one theme at a time instead of a flat file list. Each concern gets its own section with a description, per-file summaries, the real diff (sliced to just the hunks relevant to that concern when a file serves more than one), and callouts for anything genuinely non-obvious. Triggers: /concern-review, "review this PR by concern", "review this large PR", "build a review dashboard", "group this diff by concern", "concern review", "help me review this PR".
基于 SOC 职业分类
正在显示 SKILL.md
| name | web-search |
| description | Search the web using lynx and DuckDuckGo. Performs text-based web searches and can dump specific website content. Do NOT use in Claude Code — use the built-in WebSearch tool instead. Only use this skill in environments where WebSearch is unavailable. |
| triggers | ["/web-search","search the web","search for","look up online","web search","find on the internet","search duckduckgo","search online","google this","find information about"] |
| metadata | {"author":"meain","version":"1.0.0","license":"MIT"} |
Search the web using lynx text browser with DuckDuckGo. Bypasses bot protection and provides clean, text-based results.
Note: This skill should only be used when the built-in WebSearch tool is not available and no other more specific search tools exist (e.g., documentation APIs, specialized search tools). If WebSearch is available in the current environment, use that instead.
# Basic web search
python3 ~/.agents/skills/web-search/scripts/search.py "search query"
# Search with more results
python3 ~/.agents/skills/web-search/scripts/search.py "search query" --limit 10
# Dump specific website content
python3 ~/.agents/skills/web-search/scripts/search.py --dump "https://example.com"
# Search and filter results
python3 ~/.agents/skills/web-search/scripts/search.py "search query" --filter "keyword"
# Basic search
python3 ~/.agents/skills/web-search/scripts/search.py "best budget earbuds india under 5000"
# Technology news search
python3 ~/.agents/skills/web-search/scripts/search.py "golang 1.24 release notes"
# Get specific website content
python3 ~/.agents/skills/web-search/scripts/search.py --dump "https://www.smartprix.com/mobile_headphones/best-earbuds-under-5000-list"
# Search with filtering
python3 ~/.agents/skills/web-search/scripts/search.py "rust programming tutorial" --filter "beginner"
# Limit results
python3 ~/.agents/skills/web-search/scripts/search.py "machine learning courses" --limit 5
lynx text browser (already available in your environment)curl and html2markdown instead of the --dump option for better compatibility and cleaner output