Token导航 LogoToken导航

Agent Skill · 研究检索

avbuzz(avbuzz 搜索)

avbuzz 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。

avbuzz 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为需要联网;许可证为 MIT-0,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 13,713。

总安装 9,149周安装 389GitHub Stars 公开资料未说明下载 3,205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
1.1.0

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:avbuzz(avbuzz 搜索)
来源仓库:https://github.com/zxcnny930/avbuzz
安装命令:
openclaw skills install avbuzz
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 avbuzz

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。

从 FANZA GraphQL API 查询 AV 新发布、排名和女演员信息。无需身份验证,支持直接 curl 查询和可选 Discord/Telegram 通知。适合快速检索成人娱乐行业相关数据。安装命令为 openclaw skills install avbuzz,注意数据来源合规性。

使用前需评估是否涉及敏感内容访问及地区法律限制。

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 avbuzz;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

    它需要需要联网,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

avbuzz 怎么安装?

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

avbuzz 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。

avbuzz 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

avbuzz 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。

avbuzz 用的人多吗?

公开数据是累计安装 9,149 次,近一周安装 389 次,下载 3,205 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。

avbuzz 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

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。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 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。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 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
avbuzz

avbuzz 搜索 · 本页

9,149—需要联网MIT-0通过

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
avbuzz
description
Query AV new releases, rankings, and actress info from FANZA GraphQL API. No authentication required. Supports direct curl queries and optional Discord/Telegram bot deployment.
version
1.1.0
user-invocable
true
metadata
openclaw
requires
bins
install
kind
brew
formula
curl
label
curl (HTTP client)
emoji
\F5F4
os
version
1.1.0

AVBUZZ — FANZA AV Query Skill

⚠️ Adult Content (R18+) — This skill indexes adult video (AV) content from FANZA. Users must be 18+ and comply with local laws.

Query AV new releases, rankings, actress info, and search from FANZA's free GraphQL API. No API keys or authentication required.

API Overview

Endpoint: POST https://api.video.dmm.co.jp/graphql

Authentication: None (public API)

Content-Type: application/json

All queries use the legacySearchPPV GraphQL operation. Results include: video code (番號), title, actresses, maker/studio, release date, cover image URL, star ratings, and bookmark count.

Determining Today's JST Date

FANZA uses JST (Japan Standard Time, UTC+9). To get today's date in JST:

date -u -d '+9 hours' '+%Y-%m-%d'

On macOS:

TZ=Asia/Tokyo date '+%Y-%m-%d'

Use this date value in any deliveryStartDate filter. For yesterday, subtract 1 day:

date -u -d '+9 hours -1 day' '+%Y-%m-%d'

Query Operations

1. Today's New Releases

Fetch videos released on a specific date (use JST date, format YYYY-MM-DD):

curl -s -X POST https://api.video.dmm.co.jp/graphql \
  -H "Content-Type: application/json" \
  -d '{"query":"{ legacySearchPPV(limit: 10, offset: 0, sort: DELIVERY_START_DATE, floor: AV, filter: { deliveryStartDate: \"2026-03-03\" }) { result { contents { id title deliveryStartAt contentType maker { name } actresses { id name } packageImage { largeUrl } review { average count } bookmarkCount } pageInfo { totalCount } } } }"}'

Change deliveryStartDate to any YYYY-MM-DD date. Use offset for pagination (0, 10, 20...).

2. Today's Hot (by Popularity)

Same as new releases but sorted by sales rank:

curl -s -X POST https://api.video.dmm.co.jp/graphql \
  -H "Content-Type: application/json" \
  -d '{"query":"{ legacySearchPPV(limit: 10, offset: 0, sort: SALES_RANK_SCORE, floor: AV, filter: { deliveryStartDate: \"2026-03-03\" }) { result { contents { id title deliveryStartAt contentType maker { name } actresses { id name } packageImage { largeUrl } review { average count } bookmarkCount } pageInfo { totalCount } } } }"}'

3. Rankings

Top videos by different criteria. Change sort value:

Sales ranking (best-selling):

curl -s -X POST https://api.video.dmm.co.jp/graphql \
  -H "Content-Type: application/json" \
  -d '{"query":"{ legacySearchPPV(limit: 10, sort: SALES_RANK_SCORE, floor: AV) { result { contents { id title deliveryStartAt contentType maker { name } actresses { id name } packageImage { largeUrl } review { average count } bookmarkCount } pageInfo { totalCount } } } }"}'

Review ranking (highest rated):

curl -s -X POST https://api.video.dmm.co.jp/graphql \
  -H "Content-Type: application/json" \
  -d '{"query":"{ legacySearchPPV(limit: 10, sort: REVIEW_RANK_SCORE, floor: AV) { result { contents { id title deliveryStartAt contentType maker { name } actresses { id name } packageImage { largeUrl } review { average count } bookmarkCount } pageInfo { totalCount } } } }"}'

Bookmark ranking (most saved):

curl -s -X POST https://api.video.dmm.co.jp/graphql \
  -H "Content-Type: application/json" \
  -d '{"query":"{ legacySearchPPV(limit: 10, sort: BOOKMARK_COUNT, floor: AV) { result { contents { id title deliveryStartAt contentType maker { name } actresses { id name } packageImage { largeUrl } review { average count } bookmarkCount } pageInfo { totalCount } } } }"}'

Available sort values:

Sort ValueUse When
DELIVERY_START_DATEUser asks for "latest" / "newest" / "最新" — sorted by release date
SALES_RANK_SCOREUser asks for "popular" / "best-selling" / "熱門" / "銷售"
REVIEW_RANK_SCOREUser asks for "highest rated" / "best reviewed" / "評分"
BOOKMARK_COUNTUser asks for "most saved" / "most bookmarked" / "收藏"

4. Search by Keyword

Search by actress name, title, video code, or any keyword:

curl -s -X POST https://api.video.dmm.co.jp/graphql \
  -H "Content-Type: application/json" \
  -d '{"query":"{ legacySearchPPV(limit: 10, offset: 0, sort: SALES_RANK_SCORE, floor: AV, queryWord: \"蒼井空\") { result { contents { id title deliveryStartAt contentType maker { name } actresses { id name } packageImage { largeUrl } review { average count } bookmarkCount } pageInfo { totalCount } } } }"}'

Replace 蒼井空 with any search term. Works with:

  • Actress names (Japanese): 波多野結衣, 蒼井 空 (space may help)
  • Video codes: SSNI, IPZ-123
  • Keywords: VR, 4K, studio names
  • English terms work too

Important notes on search:

  • Keyword search is fuzzy/broad — partial kanji matches may return unrelated results. If searching for a specific actress returns unexpected results, try adding a space between family and given name, or search for just the family name
  • Video code format: Users typically write SSIS-001 but FANZA uses ssis00001 (lowercase, no hyphen, 5-digit zero-padded number). Try both formats — the API handles uppercase/lowercase, but removing the hyphen and padding zeros improves accuracy
  • For exact actress works, prefer the Actress ID search (Section 5) over keyword search

5. Search by Actress ID

If you know the actress ID (from a previous search result), fetch all her works:

curl -s -X POST https://api.video.dmm.co.jp/graphql \
  -H "Content-Type: application/json" \
  -d '{"query":"{ legacySearchPPV(limit: 20, sort: DELIVERY_START_DATE, floor: AV, filter: { actressIds: { ids: [{ id: \"26225\" }] } }) { result { contents { id title deliveryStartAt contentType maker { name } actresses { id name } packageImage { largeUrl } review { average count } bookmarkCount } pageInfo { totalCount } } } }"}'

Replace 26225 with the actress ID. Note the nested object syntax: actressIds: { ids: [{ id: "ID" }] }.


Response Format

All queries return the same structure:

{
  "data": {
    "legacySearchPPV": {
      "result": {
        "contents": [
          {
            "id": "ssni00001",
            "title": "Title in Japanese",
            "deliveryStartAt": "2026-03-03",
            "contentType": "TWO_DIMENSION",
            "maker": { "name": "Studio Name" },
            "actresses": [
              { "id": "26225", "name": "波多野結衣" }
            ],
            "packageImage": {
              "largeUrl": "https://pics.dmm.co.jp/..."
            },
            "review": { "average": 4.5, "count": 123 },
            "bookmarkCount": 456
          }
        ],
        "pageInfo": { "totalCount": 42 }
      }
    }
  }
}

Field Reference

FieldDescription
idFANZA product code / 番號 (e.g., ssni00001) — display as UPPERCASE
titleVideo title (Japanese)
deliveryStartAtRelease date (YYYY-MM-DD)
contentTypeTWO_DIMENSION for normal, VR for VR content
maker.nameStudio/maker name
actressesArray of { id, name } — performer info
packageImage.largeUrlCover image URL (DMM CDN)
review.averageStar rating 1.0–5.0
review.countNumber of reviews
bookmarkCountNumber of user bookmarks/saves
pageInfo.totalCountTotal matching results (for pagination)

Pagination

Use limit and offset parameters:

  • Page 1: limit: 10, offset: 0
  • Page 2: limit: 10, offset: 10
  • Page 3: limit: 10, offset: 20

Maximum limit is 50.

FANZA Product Page URL

To link to a video's FANZA page:

https://www.dmm.co.jp/digital/videoa/-/detail/=/cid={id}/

Replace {id} with the product code (lowercase).


Error Handling

HTTP CodeMeaningAction
200SuccessParse data.legacySearchPPV.result
200 + errorsGraphQL validation error (wrong syntax)Check query syntax against examples above
429Rate limitedRetry after 2-10 seconds (exponential backoff)
500Server errorRetry after 5 seconds; if persistent, API may be temporarily down
503Service unavailableAPI is temporarily down; retry after 30 seconds
TimeoutNetwork issueCheck connectivity; retry after 5 seconds

Empty results (contents: [], totalCount: 0) are NOT errors — they mean no matching content was found.

VR Content Filtering

The GraphQL API does NOT support filtering by contentType (VR vs normal). To find VR content:

  1. Query normally (by date, keyword, ranking, etc.)
  2. Filter results client-side: check contentType === "VR" in the response
  3. Recommended fallback: If client-side filtering returns no VR results (e.g., top-rated are all 2D), combine queryWord: "VR" with your desired sort to get VR-specific results

Tips for Effective Queries

  1. Date format is JST — Japan is UTC+9. "Today" in JST may differ from your timezone
  2. Actress names — Try with and without spaces: 蒼井空 and 蒼井 空
  3. Sort wisely — Use SALES_RANK_SCORE for popular, DELIVERY_START_DATE for newest
  4. VR content — Check contentType === "VR" (normal content is "TWO_DIMENSION") and mark with 🥽
  5. Cover images — packageImage.largeUrl works directly in Discord embeds, Telegram, web, etc.
  6. Error responses — API returns {"errors":[...]} on invalid queries. HTTP 429 means rate limited — retry after a few seconds.

Daily Notifications

This skill provides on-demand queries only. The AI queries FANZA when you ask, but cannot autonomously push daily notifications.

For automatic daily new release alerts, deploy the AVBUZZ Discord bot to a VPS (see "Advanced: Discord Bot Deployment" below). The bot supports:

  • Daily digest at configurable JST time (default 00:05)
  • Actress tracking alerts every 6 hours
  • /notify on / /notify off to toggle daily push per channel

Disclaimer

FANZA GraphQL API is undocumented and unofficial. This skill uses a reverse-engineered API endpoint (api.video.dmm.co.jp/graphql) that is not publicly supported by DMM/FANZA. The API could change or become unavailable at any time without notice. Use at your own risk. This project is not affiliated with DMM, FANZA, or any content producers.

Advanced: Discord Bot Deployment

AVBUZZ can also run as a persistent Discord bot with slash commands, automatic daily digests, actress tracking alerts, and Telegram integration.

GitHub: github.com/zxcnny930/avbuzz

Quick Setup

git clone https://github.com/zxcnny930/avbuzz.git
cd avbuzz
npm install
cp config.example.json config.json  # Edit with your tokens
npm start

Requires: node, npm, git

Configuration

All settings in config.json:

{
  "discord": {
    "token": "YOUR_DISCORD_BOT_TOKEN",
    "guildId": "YOUR_GUILD_ID",
    "channelId": "YOUR_CHANNEL_ID"
  },
  "telegram": {
    "botToken": "YOUR_TELEGRAM_BOT_TOKEN",
    "chatId": "YOUR_CHAT_ID"
  },
  "schedule": {
    "dailyPushHourJST": 0,
    "dailyPushMinuteJST": 5,
    "actressCheckIntervalHours": 6
  }
}

Discord Setup

  1. Create app at discord.com/developers → Bot tab → Add Bot → copy Token
  2. OAuth2 → URL Generator → scopes: bot → permissions: Send Messages, Embed Links → invite bot
  3. Right-click server → Copy Server ID (enable Developer Mode first)
  4. Right-click channel → Copy Channel ID

Telegram Setup (Optional)

  1. Message @BotFather on Telegram → /newbot → copy Token
  2. Send a message, then visit https://api.telegram.org/bot<TOKEN>/getUpdates → find chat.id
  3. Leave both fields empty to run Discord-only

Discord Slash Commands

CommandDescription
/new [date]New releases for date (default: today JST)
/todayToday's trending (by sales rank)
`/ranking <sales\review\bookmark>`Top 10 by category
/search <keyword>Search by actress, title, code
/track <name>Track actress — alerts on new releases
/untrack <name>Stop tracking
/tracklistShow all tracked actresses
/randomRandom video recommendation
/statusSystem status and API health check
/code <id>Exact video code lookup (e.g., SSIS-001)
/digestWeekly top picks (rating, bookmark, sales)

Scheduling

TaskFrequencyDescription
Daily DigestOnce/day (configurable JST time)Top 20 new releases → Discord + Telegram
Actress CheckEvery 6h (configurable)New releases for tracked actresses → alerts
Weekly DigestSunday JST 20:00Top rated, bookmarked, best-selling → Discord + Telegram

VPS Deployment (systemd)

ssh root@your-vps.com
git clone https://github.com/zxcnny930/avbuzz.git /root/avbuzz
cd /root/avbuzz && npm install
cp config.example.json config.json && nano config.json

Create /etc/systemd/system/avbuzz.service:

[Unit]
Description=AVBUZZ Discord Bot
After=network.target

[Service]
Type=simple
WorkingDirectory=/root/avbuzz
ExecStart=/usr/bin/node src/index.js
Restart=always
RestartSec=10

[Install]
WantedBy=multi-user.target
systemctl daemon-reload && systemctl enable avbuzz && systemctl start avbuzz
journalctl -u avbuzz -f  # View logs

Reconfiguring

nano config.json && systemctl restart avbuzz

License

Dual License — Non-commercial use is free under PolyForm Noncommercial 1.0.0. Commercial use requires a separate license from the author.

GitHub: github.com/zxcnny930/avbuzz

平台分布

OpenClaw

74.53%
按下载量换算2,389

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。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