网页搜索技能：为 Agent 补上可触发的网页检索与汇总
介绍 SkillHub 社区技能「网页搜索技能」（@user_c5d687fe/web-search-skill-v2，v1.0.0）。说明其通过「搜索」「查一下」等自然语言触发网页搜索并汇总结果，标注 requires_api_key=false。给出 skillhub CLI 安装步骤、Cursor/Claude Code/Codex 的 skills 目录与 install 命令示例，并说明适用场景与安装路径注意事项。
Read MoreBrave Search Skill：经 Brave Search API 做网页搜索与内容提取
Brave Search（@clawhub_steipete/brave-search，v1.0.1）通过 Brave Search API 提供无浏览器网页搜索与 Markdown 正文提取，需配置 BRAVE_API_KEY。本文基于 SkillHub 与 ClawHub 上游说明，介绍安装（skillhub install / openclaw skills install）、Cursor 等 skills 目录、npm ci 初始化，以及 search.js、content.js 的典型命令与适用场景。
Read MoreKeenable for DeepSeek Harness：无 Key 的网页搜索与抓取插件
`keenableai/dsh-keenable` 插件为 DeepSeek Harness 提供无需账号的网页搜索与抓取能力。它将 DSH 的内置工具桥接到 Keenable 服务，支持 Markdown 格式返回结果，并允许通过 API Key 提升速率限制。安装后无需配置即可使用，适合本地模型场景，但需注意隐私及非本地地址的限制。
Read Moredsh-hydrasearch: A TinyFish + AnySearch Web Search and Scraping Plugin
dsh-hydrasearch is a dual-backend search and scraping plugin designed for DeepSeek Harness (DSH). By integrating the two free services TinyFish and AnySearch, it builds an automatic failover chain to address request failures caused by rate limiting or outages on official backends. The plugin supports web search, scraping (Markdown/HTML/JSON), and pagination filtering, providing high availability. Installation requires running the specified command and configuring an API Key, and it supports adjusting backend priority and parameters inline. Note that DSH 0.2.0-rc.2 or later is required, and the Key is stored locally only.
Read Moredsh-travily-api: Tavily Web Search for DeepSeek Harness
`dsh-travily-api` is a plugin for DeepSeek Harness (DSH) that integrates Tavily's web search capabilities. It is loaded as a profile bundle, provides controllable search strategies via the `web_search` interface, and supports secure credential storage and fallback mechanisms for API Keys. Users can install it via the GUI or command line and configure parameters such as the API Key, search depth, and timeout in settings. The plugin is open source under the MIT license. After installation, DSH must be restarted for it to take effect.
Read MoreDeepSeek Harness Web Search Plugin: Z.AI (GLM) Provider
The `dsh-web-search-zai` plugin is designed to resolve the web search 401 authentication failure caused by a missing API Key when DeepSeek Harness (DSH) switches to Z.AI (GLM) routing. By registering a `zai-official` provider, it leverages Z.AI's Anthropic-compatible interface to implement native `web_search` functionality. It features zero dependencies, fault-tolerant retries (up to 3 times), citation-aware scanning, and URL deduplication. Installation requires command-line operations in the `web` configuration and ensuring that the environment variable `ZAI_API_KEY` is set. Usage consumes GLM model quota, does not support UI settings, and requires attention to compatibility with DSH versions.
Read MoreDSH Free Web Search Plugin (dsh-freeweb)
DSH-freeweb is a DSH plugin built on the Parallel free search backend, designed to replace the official paid search. Its core advantages include zero dependencies, complete error handling, and a bundled distribution. It can be installed via the plugin page, the CLI, or manual mounting (the lightest option). To configure it, specify `searchProvider: freeweb` in `cordis.patch.yml`. This plugin is mutually exclusive with the official search, is primarily intended for English search, and returns diagnostic information as text on failure. To roll back, uninstall the bundle or delete the configuration file.
Read Moreum-dsh-websearch: DeepSeek Harness Multi-Source Web Search Plugin
`um-dsh-websearch` is a web search plugin for DeepSeek Harness, designed to centrally manage multiple third-party data sources such as Exa, Parallel, and DeepSeek. Through strategy-layer encapsulation, the plugin supports multi-provider prioritization, paid/free dual tiers, multi-key polling, concurrent fan-out, and optimistic caching, ensuring search flexibility and security. Users can install it via pnpm and easily configure the master switch, concurrency mode, and credentials using the official settings card. The plugin requires a DeepSeek Harness version between 0.2.0-rc.1 and 0.3.0, automatically takes over default search after installation, and reverts automatically upon uninstallation.
Read MoreHermes Web MCP: Keyless Web Search and Automation Tool
`hermes-web-mcp` is a keyless MCP server intended to solve the API key restrictions and paid-access barriers encountered by desktop clients when performing web tasks. Maintained by ShadowMiner, its core value lies in being "key-free" and in "local rendering". By connecting to locally running Playwright Service, HTML-to-MD Service, and CDP Chrome instances, it provides web search, content extraction (including Markdown conversion), and real browser automation operations (9 tools in total). The plugin runs in an isolated context without interfering with the host browser. Node.js >= 22 must be installed and the relevant environment variables configured before deployment.
Read MoreDeepSeek Harness Plugin: Perplexity Consumer Account Web Search
DeepSeek Harness (DSH) plugin `genson1808/dsh-web-search-perplexity-account` allows users to perform web searches using an already logged-in Perplexity Consumer Pro account, without configuring an API key or paying per request. The plugin authenticates via browser SSO or email OTP, forwards DSH search requests to Perplexity, and returns the results. Currently, the official does not provide an installation command, requiring manual setup, and the plugin runs with the permissions of the current DSH process. This solution is suitable for users who already have a Pro account and want to integrate it with DSH, but they should inspect the source code and license before installing.
Read Morebing-web-search: DeepSeek Harness Web Search Plugin
bing-web-search is a zero-configuration web search plugin for DeepSeek Harness. It automatically falls back to free Bing search when no API key is provided, and uses Tavily for higher-quality results when an API key is available. To install it, place the directory in `node_modules`, register the plugin in `cordis.patch.yml`, and specify the search provider. The API key can be configured via environment variables or a credentials file, and the plugin also supports setting a timeout and result count. Developers can use it as-is without any configuration, or use Tavily to get more accurate search results and summaries.
Read Moredsh-web-search-openai: Integrate OpenAI Responses API Web Search for DSH
dsh-web-search-openai is a DSH plugin developed by flg1217, designed to integrate a search provider based on the OpenAI Responses API into `ctx.web` without modifying the DSH source code. The plugin achieves server-side retrieval by invoking the `POST /responses` interface and utilizing the native `web_search` tool, unifying structured results or message-level annotations into citable sources. It supports a Web settings card that allows users to configure the endpoint, model, API Key, and retrieval context; notably, the API Key supports input without echoing or reading from the `OPENAI_API_KEY` environment variable. Installation requires ensuring the DSH version is not lower than 0.1.0-rc.6 and proceeding via `dsh pl`...
Read Moredsh-web-search-anysearch: AnySearch Web Search Plugin for DeepSeek Harness
`dsh-web-search-anysearch` is a native Web search plugin for DeepSeek Harness (DSH), maintained by mcxianyujun, and licensed under the MIT License. It provides web search capabilities by interfacing with AnySearch's `POST /v1/search` REST API, without requiring patching of the Harness core or reliance on a JSON-RPC bridge. Its core features include an independent Web settings area and credential management, utilizing a dedicated `ANYSEARCH_API_KEY` securely stored via the DSH credentials service and avoiding the reuse of DeepSeek's default keys. The plugin supports complete source information (URL, title, ...
Read Moredsh-kit: Adding Dock Panels and Free Web Search to DSH Session Workspaces
dsh-kit is an MIT-licensed plugin for DeepSeek Harness (dsh), maintained by zhouzhencheng07, requiring Node.js ≥ 22. This plugin provides a toggleable dock panel for dsh web, integrating terminal, file tree, source code management, background tasks, skill management, and mobile access features, while incorporating the free multi-source web search capability from dsh-free-search v0.2.0. Users can quickly open each panel via keyboard shortcuts: the terminal supports multi-tab background execution; the file tree supports file editing and diff, with recycle bin protection for deletions on Windows; source code management handles git operations; background tasks monitor session running status; skill management covers skill configurations at various levels. Mobile access generates links and QR codes via tokens, supporting
Read Moredsh-web-search-pro: DSH Multi-Engine Web Search with Persistent Caching
dsh-web-search-pro is a DSH bundle plugin maintained by anweat, integrating multi-engine search, 20-platform retrieval, content scraping, SQLite+LRU caching, and Playwright rendering into 11 tools. It requires paired installation with @anweat/dsh-browser and supports engine fallbacks for Exa/DDG/Bing/Jina, Chinese community login states, and site-specific rules. This article covers installation commands, typical usage, configuration highlights, and security considerations.
Read MoreUsing firecrawl-build-search: Start from queries and write web discovery into product code
`firecrawl-build-search` is an official Agent Skill for Firecrawl, specifically designed to connect the `/search` endpoint to product code: the functionality starts from queries instead of URLs. It first discovers, ranks and selects sources, then decides whether to hydrate the content or hand it over to `/scrape`. This article cross-verifies installation commands, authentication fields, one-step/two-step call differences, and error-prone upgrade paths such as paper indexing and developer indexing based on GitHub's SKILL.md, repository README, officialskills.sh and docs.firecrawl.dev.
Read MoreIntegrate Web Search, Crawling and Browser Interaction into Application Code with firecrawl-build
`firecrawl-build` is the official application integration entry Skill of Firecrawl, located in the `firecrawl/skills` repository. It targets scenarios where products, agents or workflows need to obtain webpage data through code. It first clarifies what data to fetch and how to fetch it, then routes the requirements to `/scrape`, `/search` or `/interact`, instead of mixing "help me search a page in the current session" with "integrate Firecrawl into the backend". This article checks the installation commands, environment variables, SDK, sub-skill division, smoke test, and the boundaries with CLI/Workflow skills against the SKILL.md, repository README and official documentation.
Read More