小红书搜索建议关键词收集工具
v1.0.1小红书搜索建议关键词收集工具。通过浏览器自动化访问小红书探索页，在搜索栏输入关键词并收集自动提示框中的相关关键词列表。使用场景：(1) 用户需要获取小红书搜索联想词 (2) 关键词调研和热门话题发现 (3) SEO优化和内容选题 (4) 竞品分析中的关键词挖掘。触发词："小红书关键词"、"搜索建议"、"联想词"、...
⭐ 0· 117·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the runtime instructions: the SKILL.md only instructs using a browser tool to open https://www.xiaohongshu.com/explore, type keywords into the search box, wait for suggestion popups, and collect them. No unrelated binaries, env vars, or installs are required.
Instruction Scope
Instructions stay within the stated scope (navigate, locate search input, type keywords, collect suggestion list). The doc explicitly forbids pressing Enter/clicking search and notes login/captcha as manual interventions. It does not instruct reading unrelated files or environment variables.
Install Mechanism
This is an instruction-only skill with no install spec and no code files — lowest-risk install footprint. It relies on an external 'browser' tool being available (declared).
Credentials
The skill declares no required credentials or env vars, which is appropriate. The doc does mention that some content may require login and that captchas may occur; users and integrators should ensure the agent does not request/store credentials outside normal, explicit browser-based login flows.
Persistence & Privilege
always is false and the skill is user-invocable only. There is no instruction to modify other skills, system configuration, or persist credentials.
Assessment
This skill appears coherent and lightweight: it only automates a browser to read suggestion popups on Xiaohongshu. Before using it, consider: (1) run it in an environment where the browser automation tool is trusted and isolated; (2) do not provide secrets (passwords/API keys) to the skill — if login is needed, perform the login interactively in the browser session rather than giving credentials as environment variables; (3) be aware of Xiaohongshu's terms of service and rate limits and expect anti-bot measures (CAPTCHAs) that may require manual handling; (4) if you need persistent or large-scale scraping, prefer an approach that follows site policies and legal constraints. If you want higher assurance, ask the publisher for a code-based implementation or an official integration rather than an instruction-only skill.Like a lobster shell, security has layers — review code before you run it.
latestvk97e8cqb0ndg25qpqxjapzewkd83b7as
License
MIT-0
Free to use, modify, and redistribute. No attribution required.