← 返回 Skills 市场
117
总下载
0
收藏
0
当前安装
5
版本数
在 OpenClaw 中安装
/install llms-txt-sniffer
功能描述
Locate and utilize AI-friendly documentation index files (llms.txt, llms-full.txt) or sitemap.xml. Use when encountering documentation URLs (containing /docs...
使用说明 (SKILL.md)
llms-txt-sniffer: The Smart Document Radar
This skill streamlines documentation ingestion by locating the most AI-optimized version of a site's content.
🧠 Why llms.txt?
It provides a high-density, Markdown-based index designed for LLMs to map entire sites instantly and save tokens.
🚀 Discovery Strategy (Two-Stage)
Stage 1: Quick Jump Probes (Instructional)
- URL + /llms.txt: Probe
{input_url}/llms.txtusingcurl -I. - Domain Root: Probe
https://{domain}/llms.txtusingcurl -I.
Stage 2: Advanced Sniffing (Tool-based)
If Stage 1 fails, run the companion sniffer script located in this skill's directory:
python3 sniffer.py $ARGUMENTS
📜 Behavioral Rules
- User-Initiated Only: Only invoke this skill when the user explicitly provides a documentation URL. Do not autonomously scan domains.
- Switch to High-Speed Mode: Once an index is found, prioritize its links over manual scraping.
- Index Summary: Always present a brief structure overview.
- Fallback: Use
sitemap.xmlparser results ifllms.txtis missing.
安全使用建议
This skill appears coherent and limited: it runs HTTP probes and a small Python script to find llms.txt or sitemap.xml and returns a short preview. Before installing, consider: (1) only use it against public documentation URLs you control or are authorized to scan (the script does DNS lookups and fetches content and could reveal page text); (2) the script returns up to 2000 characters of file content — avoid running it on URLs that might expose secrets; (3) the SKILL.md asks for user-initiated use only, but the platform permits autonomous invocation by default — ensure you only enable autonomous runs if you trust it; (4) source/homepage is unknown — if you need stronger assurances, review or run the sniffer.py code in a sandboxed environment yourself before use.
功能分析
Type: OpenClaw Skill
Name: llms-txt-sniffer
Version: 1.3.1
The skill bundle is designed to locate AI-friendly documentation index files (llms.txt and sitemap.xml) to optimize documentation ingestion. The Python script `sniffer.py` includes proactive security measures, such as an SSRF protection mechanism (`is_internal_host`) to prevent the agent from probing internal network resources. The instructions in `SKILL.md` are transparent, align with the tool's stated purpose, and include behavioral constraints to ensure the tool is only used upon explicit user request.
能力评估
Purpose & Capability
Name, description, declared binaries (python3, curl), and included script align with the stated goal of locating llms.txt / sitemap.xml on documentation sites. No unrelated credentials, config paths, or binaries are requested.
Instruction Scope
SKILL.md restricts use to user-initiated document URLs and describes probing with curl -I then running sniffer.py. The script performs HTTP GETs (via urllib) and returns a content preview (up to 2000 chars). It does not read local files or environment variables. Note: the skill performs network requests and DNS resolution; this is expected but the agent should follow the 'user-initiated only' guideline when invoking it.
Install Mechanism
Instruction-only with a bundled small Python script. No install spec or external downloads; nothing is written to disk beyond the existing code file. Low install risk.
Credentials
No environment variables, credentials, or config paths are requested. The required tools (python3, curl) are appropriate for the task.
Persistence & Privilege
always is false and the skill does not request elevated or persistent platform privileges. It does not modify other skills or system-wide settings.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install llms-txt-sniffer - 安装完成后，直接呼叫该 Skill 的名称或使用
/llms-txt-sniffer触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.3.1
Security: add SSRF protection (block internal IPs), fix metadata (remove requests), clarify allowed-tools, add User-Initiated-Only rule
v1.2.9
New format with argument-hint and allowed-tools
v1.3.0
Streamline description, simplified content
v1.2.2
Fix YAML syntax, add allowed-tools for Claude Code
v1.2.1
v1.2.1: 移除requests依赖,新增触发场景说明
元数据
常见问题
llms-txt-sniffer 是什么？
Locate and utilize AI-friendly documentation index files (llms.txt, llms-full.txt) or sitemap.xml. Use when encountering documentation URLs (containing /docs... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 117 次。
如何安装 llms-txt-sniffer？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install llms-txt-sniffer」即可一键安装，无需额外配置。
llms-txt-sniffer 是免费的吗？
是的，llms-txt-sniffer 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
llms-txt-sniffer 支持哪些平台？
llms-txt-sniffer 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 llms-txt-sniffer？
由 JDChi（@jdchi）开发并维护，当前版本 v1.3.1。
推荐 Skills