skill Skill
description: Real-time web research/search and URL content fetching via Grok API (outputs JSON with content and sources).
Want an agent-native computer in the browser? Try HappyCapy.
Cloud sandbox for AI agents · No setup · Run autonomous workflows from your browser
Affiliate link — we may earn a commission at no extra cost to you.
Why use this skill
skill is most useful when you want an agent workflow that is more structured than an ad-hoc prompt. Instead of restating the same expectations every time, a dedicated SKILL.md file gives the assistant a repeatable brief. In this case, the core value is clarity: the repo already frames the workflow around backend skills tasks, and the skill source gives you a portable starting point you can evaluate, adapt, and reuse. The inferred platform for this skill is Generic Skills, which helps you judge whether it is likely to feel native in your current agent ecosystem or whether it is better treated as a general reference.
That matters because AI assistants are better when the operating context is explicit. A good skill turns hidden team expectations into visible instructions. It can name preferred tools, describe failure modes, define what “done” looks like, and reduce the amount of corrective prompting you need after the first draft. For developers exploring the wider SKILL.md ecosystem, this page helps answer the practical question: is this skill specific and maintained enough to be worth trying?
How to evaluate and use it
Start with the source repo and the preview below. The preview tells you whether the instructions are actionable or just aspirational. Strong skills usually describe triggers, recommended tools, steps, and known pitfalls. Weak skills tend to stay generic. This one lives in piexian/astrbot_plugin_grok_web_search, which gives you a concrete repo context, update history, and direct ownership trail.
Once you confirm the scope looks right, test it on a small task before making it part of a larger workflow. If it improves consistency, keep it. If it is too broad, outdated, or conflicts with your own process, treat it as a reference rather than a drop-in rule. That is the healthiest way to use directory-discovered skills: not as magic plugins, but as reusable operational knowledge that still deserves judgment.
SKILL.md preview
Previewing the source is one of the fastest ways to judge whether a skill is truly useful. This snippet comes from the public file in the linked repository.
--- name: grok-search description: Real-time web research/search and URL content fetching via Grok API (outputs JSON with content and sources). disable_tools: true --- ## Important **使用此 Skill 时必须禁用工具调用**，否则 AI 会直接调用 `grok_web_search` 工具而非执行脚本。 ## When to use Use this skill **aggressively** - default to searching before answering anything that might be: - Outdated or time-sensitive (API versions, release info, changelogs) - Error messages or troubleshooting - Documentation lookups - Real-time status queries - Any information you're not 100% confident about When you need to read a specific web page's full content, use the **fetch mode** to get structured Markdown. If you feel even slightly unsure, search first, then answer with evidence. ## Configuration **AstrBot 插件自动配置（推荐）**：如果在 AstrBot 中已配置 `astrbot_plugin_grok_web_search` 插件，脚本会自动读取插件配置，无需额外设置。 **手动配置（备选）**： 环境变量： ```bash export GROK_BASE_URL="https://your-grok-endpoint.example" export GROK_API_KEY="your-api-key" export GROK_MODEL="grok-4-expert" # optional ``` 或使用配置文件： - AstrBot 插件配置（自动读取，优先级最高） - `./config.json` (skill directory) - `./config.local.json` (skill directory, gitignored) - `~/.codex/config/grok-search.json` (user global) ## Run ### Search mode (default) ```bash python scripts/grok_search.py --query "your search query" # With images for multimodal queries: python scripts/grok_search.py --query "What is in this image?" --image-files "/path/to/image.jpg" ``` ### Fetch mode (URL content extraction) ```bash python scripts/grok_search.py --fetch-url "https://example.com/article" ``` Fetch mode u ...