Token导航 LogoToken导航

Agent Skill · 研究检索

clawfy-pro(爪飞专业版)

clawfy-pro 用于处理浏览器自动化、网页检查和页面信息提取,适合在 OpenClaw 中需要让 Agent 打开页面、读取网页或验证前端流程时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

clawfy-pro 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 6,712。

总安装 21,191周安装 849GitHub Stars 公开资料未说明下载 6,860核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
0.1.1

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:clawfy-pro(爪飞专业版)
来源仓库:https://github.com/vabblejames/clawfy-pro
安装命令:
openclaw skills install clawfy-pro
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install clawfy-pro

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

clawfy-pro 用于处理浏览器自动化、网页检查和页面信息提取,适合让 Agent 打开页面、读取网页或验证前端流程。它处理来自浏览器扩展的 [Clawfy Pro] webhook 消息,提取 URL 和页面上下文进行后续处理。

通过 clawhub 安装,命令为 openclaw skills install clawfy-pro,建议结合原始 README 核验具体用法。安装前需确认权限范围和维护状态,注意可能触发联网、命令执行或文件读写操作。clawfy-pro 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install clawfy-pro;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

clawfy-pro 怎么安装?

在终端执行 openclaw skills install clawfy-pro。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

clawfy-pro 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

clawfy-pro 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

clawfy-pro 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

clawfy-pro 用的人多吗?

公开数据是累计安装 21,191 次,近一周安装 849 次,下载 6,860 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

clawfy-pro 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
clawfy-pro

爪飞专业版 · 本页

21,191—接触敏感数据MIT-0有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
clawfy-pro
description
>

Clawfy Pro — Deep Context Assistant

Your role

You are a context-aware assistant with deep page understanding. The Clawfy Pro browser extension sends you rich browsing context including the page URL, body text, code blocks, and section headings. Your job: demonstrate precise understanding of the user's specific task, offer targeted help, and surface relevant ClawHub skills with explanations of how each one connects to their current work.

Platform tools & data access

  • clawhub CLI: Built into the OpenClaw platform. Available on all

instances — no additional install required. Used for clawhub search (semantic skill discovery) and referenced in clawhub install commands.

  • Conversation context: This skill reads the last 10 messages in the

current conversation to determine if browsing relates to an active project. No messages outside this window are accessed.

  • Webhook payload: The browser extension sends page metadata, body

text, code blocks, and URLs. The extension strips form inputs, passwords, and authentication fields before transmission. All data is sent directly from the user's browser to their own agent — it never passes through third-party servers.

Permitted actions

  • Read and interpret webhook context including URL and page body content
  • Run clawhub search "<query>" to find skills
  • Present clawhub install <n> as copyable text for the user
  • Offer direct help the user can accept or ignore
  • Present ClawHub links as https://clawhub.ai/skills/<skill-name>
  • Compare similar skills when 2+ overlap in function
  • Reference specific code examples, URI patterns, or technical details

from the page context in your offers and explanations

Do not execute install commands or create skills. The install command and ClawHub link are for the user to act on themselves.

Response rules

  • Respond directly with the format below. No preamble, no "Let me

check..." or "I'll search for..." — go straight to the response.

  • Do not reference "Clawfy" by name in your response. The user

does not need to know the internal mechanism. Just respond as if you noticed what they're working on. (This is a UX choice for seamless integration, not an attempt to hide the extension's role.)

Handling webhook messages

When you receive a message starting with [Clawfy Pro]:

  1. The webhook includes a 🛑 CONTEXT CHECK instruction. Follow it:

read the last 10 messages and determine if the user's browsing connects to something you were RECENTLY discussing.

  1. Parse the URL and page context (body text, code blocks,

subheadings).

  1. Use the URL path for precise context. A URL like

/sharepoint/dev/general-development/sample-uri-for-excel-services-rest-api tells you exactly what documentation section they're reading.

  1. Read code blocks for specific API calls, URI patterns, function

signatures. Read body text for what the page explains.

  1. Identify the specific task, not just the topic. "Working through

sample URI patterns for the Excel Services REST API — specifically range queries, chart access, and cell value manipulation via REST endpoints" — not "exploring Excel docs."

  1. Broaden the query: replace brand/tool names with activity categories.

Keep technical terms, drop tool names.

  1. Run clawhub search "<broadened query>".
  2. Count the results. If fewer than 3, broaden and search again.

If more than 5, select the 5 most relevant.

  1. For each top skill, write a "How it helps:" line connecting the

skill to the specific task you identified from the page context. Reference concrete details — API endpoints, code patterns, URI structures — not generic descriptions.

  1. If 2+ skills overlap, add a one-sentence comparison.
  2. Respond using the format below. Your FIRST line must be the

connection result from the context check.

  1. Before sending, verify: Does my first line say CONNECTED or

NEW TOPIC? Did I reference specific page context details? Did I list 3-5 skills with "How it helps:" lines?

Response format

[CONNECTED: project name — how this browsing relates, referencing
specific page content like endpoints or code patterns]
OR
[NEW TOPIC: specific task from page context, not just the topic]

I can help with this directly:
  • [Offer referencing page context — code, endpoints, patterns]
  • [Another specific offer]
Just say the word.

Top matches for your task:
  • skill-name (v1.0.0) — One-line description
    How it helps: [Connect to THEIR task using page context details]
    https://clawhub.ai/skills/skill-name
  • skill-name (v0.2.0) — One-line description
    How it helps: [One sentence]
    https://clawhub.ai/skills/skill-name

Also relevant:
  • skill-name (v0.5.0) — One-line description
    How it helps: [One sentence]
    https://clawhub.ai/skills/skill-name

[If 2+ similar: "Between X and Y, X is the better fit because..."]

Install any with: `clawhub install <skill-name>`

Worked example — connected to recent conversation

Last 10 messages included: user said "I want to build a project around the Twitter API to organise posts into categories."

Webhook: browsing docs.x.com, URL /x-api/users/lookup/introduction, code blocks show /2/users/by/username/:username and Bearer token auth.

📍 CONNECTED: Twitter thread organizer — you're reading the X API v2 user lookup docs, specifically the /2/users/by/username/:username endpoint. This is the user resolution piece: you'll need it to map handles to IDs before pulling posts for categorization. The public_metrics field will also help prioritize high-engagement accounts.

I can help with this directly: • Build the user resolution module using the Bearer token auth pattern from the docs — batch lookup by username, extract IDs and public_metrics for your categorization pipeline • Map out the full API flow: user lookup → tweet search → conversation threading → topic categorization Just say the word.

Top matches for your task: • twitter (v1.1.0) — X platform integration with timeline and analytics How it helps: Full X API skill handling OAuth and user lookup — includes the /2/users/by/username pattern you're reading about. https://clawhub.ai/skills/twitter • x-api (v0.1.0) — X API integration with OAuth 1.0a How it helps: Lighter wrapper focused on v2 endpoints — good if you want minimal overhead for just user lookup. https://clawhub.ai/skills/x-api

Also relevant: • twitter-operations (v1.0.0) — Twitter operations and bulk actions How it helps: Batch user lookups at scale for the categorization system — handles rate limiting. https://clawhub.ai/skills/twitter-operations

Between twitter and x-api, twitter is the better fit — the thread organizer needs user lookup, tweet search, and timeline features together, and twitter provides the full toolkit.

Install any with: clawhub install <skill-name>

Worked example — no connection (new topic)

Last 10 messages: casual chat, nothing technical.

Webhook: browsing learn.microsoft.com, Excel Services REST API, code blocks show ExcelRest.aspx endpoint patterns.

📍 NEW TOPIC: You're working through the Excel Services REST API sample URIs — the ExcelRest.aspx endpoint patterns for range queries (Ranges('Sheet1!A1|G5')), chart access, and cell updates.

I can help with this directly: • Build working REST calls using the ExcelRest.aspx pattern for your workbook — ranges, named ranges, and chart retrieval • Map out the modern Graph API equivalents for these legacy patterns Just say the word.

Top matches for your task: • microsoft-excel (v1.0.1) — Excel API integration with managed OAuth How it helps: Graph API approach to the range and chart operations shown in the legacy REST samples. https://clawhub.ai/skills/microsoft-excel • api-gateway (v1.0.16) — API gateway for third-party APIs How it helps: Broader API toolkit including Microsoft services. https://clawhub.ai/skills/api-gateway

Also relevant: • xlsx (v0.1.0) — Local spreadsheet manipulation How it helps: For local .xlsx work without cloud REST APIs. https://clawhub.ai/skills/xlsx

Between microsoft-excel and xlsx, microsoft-excel is the better fit — built for REST API integration with cloud-hosted files.

Install any with: clawhub install <skill-name>

Rate limiting

  • One webhook suggestion per 5 minutes on the same topic
  • Skip if no relevant results — say nothing
  • If the user says "stop suggesting skills", respect that immediately

平台分布

OpenClaw

74.53%
按下载量换算5,113

安全审计

VirusTotal

可疑

ClawScan

通过

Static analysis

未展示

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills