妙达网页抓取

Use when user needs to crawl or fetch a specific URL to extract/summarize its content. Provides necessary command usage instructions for fetching known URLs....

Security Scan

The skill's purpose (web fetching) matches its instructions, but it relies on an external CLI (miaoda-studio-cli) that is not declared or provided — this mismatch is incomplete and worth verifying before use.

Purpose & Capability

Name and description claim simple webpage fetch/extract functionality, which is coherent. However, the SKILL.md explicitly requires running `miaoda-studio-cli web-crawl` (and references `miaoda-studio-cli search-summary`), yet the skill declares no required binaries or install steps. That omission is a capability–requirement mismatch: either the CLI should be declared/installed or the instructions should not depend on it.

Instruction Scope

Instructions are narrowly scoped to invoking the `miaoda-studio-cli` commands with URL and output options and to using a companion search skill. They do not instruct reading arbitrary local files or environment variables, nor do they direct data to unexpected remote endpoints. The main issue is the instruction's implicit dependency on an external CLI not declared in metadata.

Install Mechanism

This is an instruction-only skill with no install spec and no code files. That lowers direct installation risk, but it also means it assumes the runtime already provides `miaoda-studio-cli`. The lack of an install specification or verification step for that CLI is an omission that can lead to runtime failures or substitution attacks if an untrusted CLI is present.

Credentials

The skill requests no environment variables, credentials, or config paths. There are no disproportionate secret requests.

Persistence & Privilege

The skill does not request always: true or other elevated persistence. It is user-invocable and allows normal autonomous invocation behavior by default.

What to consider before installing

This skill appears to be a thin wrapper around an external CLI (`miaoda-studio-cli`) but does not declare or install that CLI. Before using: (1) verify whether `miaoda-studio-cli` is already installed in your agent environment and ensure it comes from a trusted source; (2) prefer a skill that declares its dependencies or provides an install method, or add the required binary to your environment from an official release; (3) inspect the `miaoda-studio-cli` implementation (or its package) to confirm it won't exfiltrate sensitive data or execute unintended actions; (4) if you cannot verify the CLI, avoid granting the agent autonomous access to run tools that can fetch external URLs. Providing the CLI's origin or adding a proper install spec would reduce this concern.

Web Fetch

通过 miaoda-studio-cli web-crawl 抓取指定网页内容，由 AI 自动总结/提取。

Quick Reference

参数	说明	必需	默认值
--url	网页 URL	是	-
--output, -o	输出格式: text/json	否	text

命令选择决策树

用户想获取互联网信息
├─ 有具体 URL → miaoda-studio-cli web-crawl
├─ 无具体 URL，需搜索 → miaoda-studio-cli search-summary（见 miaoda-web-search skill）
└─ 先搜索再深入 → search-summary 获取 URL（见 miaoda-web-search skill）→ web-crawl 提取详情

使用示例

# 抓取指定 URL 并提取信息
miaoda-studio-cli web-crawl --url https://example.com/pricing

# 搜索 → 深入抓取：先搜索找到目标 URL，再抓取提取详细信息
miaoda-studio-cli search-summary --query "ByteDance 开源项目" --output json
miaoda-studio-cli web-crawl --url <搜索结果中的URL>

Common Mistakes

错误	正确做法
无具体 URL 时用 miaoda-studio-cli web-crawl	无 URL 用 miaoda-studio-cli search-summary（见 miaoda-web-search skill）
需要后续程序处理结果但未加 --output json	需要解析结果时始终加 --output json
命令失败后不检查退出码	退出码 1 表示失败，检查参数和网络后重试