Token导航 LogoToken导航

Agent Skill · 研究检索

fizzread-skill(嘶嘶声技巧)

fizzread-skill 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。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。

fizzread-skill 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 11,738。

总安装 10,968周安装 457GitHub Stars 1下载 3,656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
0.1.5

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:fizzread-skill(嘶嘶声技巧)
来源仓库:https://github.com/yang1997434/fizzread-skill
安装命令:
openclaw skills install fizzread-skill
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 fizzread-skill

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。

通过音频摘要快速获取十万本非小说类书籍内容。支持按关键词搜索、浏览和收听精选书摘片段。提供免费演示密钥,无需注册即可试用基础功能。适用于知识速览与学习资料快速筛选场景。fizzread-skill 属于研究检索类 Skill,可作为该场景下的辅助能力补充。需注意版权限制,仅用于个人理解辅助而非商业用途。

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 fizzread-skill;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

fizzread-skill 怎么安装?

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

fizzread-skill 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。

fizzread-skill 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。

fizzread-skill 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。

fizzread-skill 用的人多吗?

公开数据是累计安装 10,968 次,近一周安装 457 次,下载 3,656 次,GitHub 1 星。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。

fizzread-skill 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
fizzread-skill

嘶嘶声技巧 · 本页

10,9681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
fizzread
description
Instant access to 100K+ nonfiction book summaries with 1-minute audio previews. Free demo key included — no signup needed. Search, browse, and listen via FizzRead.
homepage
https://github.com/yang1997434/fizzread-skill
emoji
\F4DA
metadata
clawdbot
requires
env
bins

FizzRead — AI Book Summaries & Audio Previews

Instant access to 100K+ nonfiction book summaries with 1-minute audio previews. Free demo key included — start exploring immediately. Get daily recommendations, search by keyword, browse categories, and listen — all inside your conversation.


Setup

Built-in Demo Key: This skill includes a free demo API key so everyone can try it immediately — no signup required.

Demo key: 3272ed72f9d0b120706038f94220770b

API Key Resolution Order

When making API calls, determine the API key using this priority:

  1. Environment variable FIZZREAD_API_KEY — if set, always use it
  2. Demo key (3272ed72f9d0b120706038f94220770b) — use as fallback when no env var is set

First-time Setup Flow

On first use, check if FIZZREAD_API_KEY is set by running:

echo "$FIZZREAD_API_KEY"

If set and non-empty: Use it directly. Run a quick connectivity test with the Daily Pick endpoint and show the result.

If not set (empty): Use the demo key and show today's book. Then append this guidance:

You're using the free demo key. For your own key with higher rate limits: 1. Visit fizzread.ai and sign up 2. Go to Settings > API Keys > Generate 3. Add it to your system environment to persist across sessions: macOS / Linux — add to your ~/.bashrc or ~/.zshrc: ``bash export FIZZREAD_API_KEY="your_key_here" ` Then run source ~/.zshrc (or restart terminal). **Windows** — run in PowerShell: `powershell [System.Environment]::SetEnvironmentVariable("FIZZREAD_API_KEY", "your_key_here", "User") `` Then restart terminal.

When the user provides a key manually

If a user pastes a key during conversation, run a connectivity test:

curl -s -H "Authorization: Bearer {user_provided_key}" "https://skill.fizzread.ai/v1/daily"
  • If the response contains data.title, the test passed. Remember this key for all subsequent API calls in this session. Also guide the user to save it as an environment variable (using the instructions above) so it persists across sessions.
  • On 401: "This API key appears to be invalid. Please double-check and try again."
  • On network failure: "Could not connect to FizzRead API. Please check your network connection and try again."

Important: Once a key is determined (from env var, demo, or user-provided), remember it and substitute it directly into the Authorization: Bearer header of every subsequent curl command. Do not rely on shell environment variables persisting between commands.

Base URL: https://skill.fizzread.ai/v1

All requests must include the header:

Authorization: Bearer <the resolved API key>

Daily Pick

When the user asks for a daily book recommendation (e.g. "recommend a book", "today's book", "daily pick"):

  1. Run:
   curl -s -H "Authorization: Bearer $FIZZREAD_API_KEY" "https://skill.fizzread.ai/v1/daily"
  1. Parse the JSON response. All API responses wrap data in a data field (e.g. {"data": {...}}). Extract fields from data and output using this template:
   📖 Today's Pick

   [{title}]({app_url}) by {author}

   {about}

   ---
   Full 10-min audio free on FizzRead App 👉 {download_url}

   🎧 [1-min Audio Preview (English)]({audio_url})

- If the user's language is not English, translate the about field to the user's language. Keep title and author in the original English. - If audio_url is null, omit the audio line entirely. - Always mark audio as "(English)" since all audio content is in English. - Do NOT output cover_url as a raw URL. The book cover will be shown automatically via Telegram's link preview of the app_url.


Book Search

When the user wants to search for books (e.g. "search for atomic habits", "find books about productivity"):

  1. Extract the search keyword from the user's message.
  1. URL-encode the keyword to prevent shell injection and handle special characters. Replace spaces with %20, and encode any special characters.
  1. Run:
   curl -s -H "Authorization: Bearer $FIZZREAD_API_KEY" "https://skill.fizzread.ai/v1/search?q={encoded_keyword}&limit=5"

If the user explicitly asks for books with audio only, append &audio_only=true.

  1. Parse the JSON response. Extract data.results and data.total. If results is empty, tell the user no books were found and suggest trying different keywords.
  1. Output as a numbered list:
   Found {total} books for "{keyword}":

   1. [{title}]({app_url})  — {author}
      {about, first sentence only}

   2. [{title}]({app_url})  — {author}
      {about, first sentence only}

   ...

   Reply with a number to see the full summary and audio preview.

   ---
   Explore 100K+ book summaries on FizzRead App
   Download: {download_url from first result}

- If the user's language is not English, translate each about excerpt. - When the user replies with a number, use the corresponding slug to call the Book Summary flow below.


Book Summary

When the user asks for a specific book's summary (e.g. by selecting from search results, or naming a book directly):

  1. Determine the book's slug. If you have it from a previous search, use it directly. Otherwise, first search for the book to find the slug.
  1. URL-encode the slug before using it in the URL.
  1. Run:
   curl -s -H "Authorization: Bearer $FIZZREAD_API_KEY" "https://skill.fizzread.ai/v1/book/{slug}"
  1. Parse the JSON response. Extract fields from data and output:
   📖 [{title}]({app_url})
   Author: {author}

   {about}

   ---
   Full version free on FizzRead App 👉 {download_url}

   🎧 [1-min Audio Preview (English)]({audio_url})

- If the user's language is not English, translate the about field. - If audio_url is null, omit the audio line. - Do NOT output cover_url as a raw URL. The cover shows via Telegram link preview of app_url.


Category Recommendations

When the user asks for books by category or topic (e.g. "recommend psychology books", "what productivity books do you have"):

  1. Extract the category/topic from the user's message.
  1. First, fetch available categories:
   curl -s -H "Authorization: Bearer $FIZZREAD_API_KEY" "https://skill.fizzread.ai/v1/categories"
  1. Fuzzy-match the user's requested topic against the returned data[].name list. Pick the closest match. If no reasonable match exists, tell the user the available categories and ask them to pick one.
  1. URL-encode the matched category name.
  1. Fetch recommendations:
   curl -s -H "Authorization: Bearer $FIZZREAD_API_KEY" "https://skill.fizzread.ai/v1/recommend?category={encoded_category}&limit=5"
  1. Output as a numbered list (same format as Book Search results):
   Top books in {category} ({count} books available):

   1. [{title}]({app_url})  — {author}
      {about, first sentence only}

   ...

   Reply with a number to see the full summary and audio preview.

   ---
   Explore 100K+ book summaries on FizzRead App
   Download: {download_url from first result}

- If the user's language is not English, translate each about excerpt.


Output Rules

  1. Language: Detect the user's conversation language. If not English, translate about content to the user's language. Keep book titles, author names, and audio labels in English.
  1. Audio: All audio is in English. Always label audio links with "(English)" so non-English users know what to expect.
  1. No fabrication: Only use data returned by the API. Never invent book titles, summaries, or URLs. If the API returns an error or empty result, say so honestly.
  1. CTA (Call to Action): Every response that includes book data must end with a download link to the FizzRead App. Use the download_url from the API response.
  1. Audio handling: When audio_url is null for a book, simply skip the audio section — do not mention that audio is unavailable.
  1. Cover image: NEVER output cover_url as a raw URL or text. Instead, embed app_url as a hyperlink on the book title: [{title}]({app_url}). Telegram will auto-generate a link preview card with the book cover from the page's og:image metadata. This is the only way to display covers.

Error Handling

When an API call returns an error, respond with a friendly message:

  • 401 Unauthorized: "Your FizzRead API key appears to be invalid. Please check your FIZZREAD_API_KEY and try again. Get a new key at fizzread.ai."
  • 404 Not Found: "That book wasn't found in the FizzRead library. Try searching with different keywords."
  • 429 Too Many Requests: "You've made too many requests. Please wait a moment and try again."
  • 500 / other errors: "FizzRead is temporarily unavailable. Please try again in a few minutes."
  • Network / curl failure: "Could not reach the FizzRead API. Please check your network connection and try again."

平台分布

OpenClaw

80.04%
按下载量换算2,926

安全审计

VirusTotal

通过

ClawScan

可疑

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