Token导航 LogoToken导航

Agent Skill · 研究检索

flowtriq(flowtriq 搜索)

flowtriq 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。

flowtriq 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 16,673。

总安装 7,050周安装 288GitHub Stars 公开资料未说明下载 2,258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
1.0.0

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:flowtriq(flowtriq 搜索)
来源仓库:https://github.com/jacob-masse/flowtriq
安装命令:
openclaw skills install flowtriq
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 flowtriq

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。

使用 Flowtriq API 实时监控和管理 Flowtriq DDoS 检测。每当用户询问主动攻击、节点状态、事件等时,请使用此技能。

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 flowtriq;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

flowtriq 怎么安装?

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

flowtriq 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。

flowtriq 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。

flowtriq 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。

flowtriq 用的人多吗?

公开数据是累计安装 7,050 次,近一周安装 288 次,下载 2,258 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。

flowtriq 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
flowtriq

flowtriq 搜索 · 本页

7,050—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
flowtriq-monitor
description
>
metadata
openclaw
requires
env

Flowtriq Monitor Skill

This skill lets you monitor your Flowtriq-protected infrastructure directly from your OpenClaw agent. Ask natural language questions and the agent will query the Flowtriq API and interpret the results for you.

Base URL: https://flowtriq.com Auth headers required on all agent endpoints:

Authorization: Bearer $FLOWTRIQ_API_KEY
X-Node-UUID: $FLOWTRIQ_NODE_UUID

What You Can Ask

  • "Are any of my nodes under attack right now?"
  • "What's the current traffic on my server?"
  • "Show me recent incidents"
  • "What was the peak PPS in the last attack?"
  • "Is my agent online?"
  • "Pull my node config and thresholds"
  • "Any IOC matches recently?"

API Calls Reference

Check Agent Health / Node Status

GET https://flowtriq.com/api/health

No auth needed. Returns { "status": "ok" }. Use this first to confirm the Flowtriq platform is reachable before making authenticated calls.


Get Node Config + Current Thresholds

GET https://flowtriq.com/api/v1/agent/config
Headers: Authorization + X-Node-UUID

Returns the node's current PPS threshold, baseline stats (p99, mean), loaded IOC patterns, and any pending commands queued for the agent.

Key fields to surface to the user:

  • pps_threshold — what PPS level triggers an incident
  • baseline.p99_pps — the node's normal p99 traffic level
  • baseline.mean_pps — average baseline
  • ioc_patterns — count how many are loaded
  • pending_commands — flag any that exist, user may want to review

Get Latest Metrics (Current Traffic)

POST https://flowtriq.com/api/v1/agent/metrics
Headers: Authorization + X-Node-UUID

The agent POSTs metrics to this endpoint every second. To read current traffic state, use the dashboard API. Since the dashboard endpoints require session auth, instruct the user to check https://flowtriq.com/dashboard for a live view, or pull from config endpoint for baseline context.


Submit / Check Incidents

POST https://flowtriq.com/api/v1/agent/incident
Headers: Authorization + X-Node-UUID

The agent uses this to open and update incidents. When interpreting incident data returned or confirmed by the user, extract and explain:

FieldWhat to tell the user
attack_familyPlain English: "UDP flood", "SYN flood", etc.
severityLow / Medium / High / Critical
peak_pps"peaked at X packets per second"
peak_bpsConvert to Gbps/Mbps for readability
source_ip_count"came from X unique source IPs"
geo_breakdownTop countries by volume
ioc_matchesNamed botnet/pattern matches
spoofing_detectedWarn user if true
botnet_detectedWarn user if true

Attack family plain-English map:

  • udp_flood = UDP Flood
  • syn_flood = SYN Flood
  • http_flood = HTTP Flood
  • icmp_flood = ICMP/Ping Flood
  • dns_flood = DNS Amplification
  • multi_vector = Multi-Vector (combined attack types)
  • unknown = Unclassified

Severity guidance:

  • low = below 2x baseline, informational
  • medium = 2-5x baseline, monitor closely
  • high = 5-20x baseline, mitigation likely active
  • critical = 20x+ baseline, full response mode

Register a New Node (if user asks)

POST https://flowtriq.com/api/deploy
Headers: Authorization: Bearer YOUR_DEPLOY_TOKEN
Body: { "name": "node-name", "ip": "x.x.x.x" }

Note: this uses a deploy token not the node API key. The user must provide their deploy token separately. Returns a new node_uuid and api_key for the registered node.


Interpreting Results for the User

Always translate raw API data into plain NOC-style summaries. Example patterns:

All clear:

"Your node is online. Baseline p99 is 12,000 PPS, threshold set at 50,000 PPS. No active incidents. 8 IOC patterns loaded."

Active attack:

"Active incident on [node]. SYN flood, critical severity. Peaked at 47,821 PPS (1.7 Gbps). 3,241 source IPs, spoofing detected. IOC match: mirai-variant (94% confidence). Mitigation should be active — check your dashboard for FlowSpec rule status."

Degraded / agent offline:

"The Flowtriq platform is reachable but your node hasn't sent a heartbeat recently. Your agent may be down. Run sudo systemctl status ftagent on the server to check."

Error Handling

HTTPMeaningTell the user
401Bad API key"Your API key looks wrong or expired. Rotate it in the Flowtriq dashboard."
402Payment issue"Your Flowtriq subscription may have lapsed. Check billing."
409Duplicate node name"A node with that name already exists in your workspace."
400Missing fieldsShow which fields are missing and ask user to provide them
5xxPlatform error"Flowtriq returned a server error. Check https://flowtriq.com/status for outages."

Setup Reminder (if user hasn't configured env vars)

If FLOWTRIQ_API_KEY or FLOWTRIQ_NODE_UUID are missing, tell the user:

"To use this skill you need two environment variables set in OpenClaw: - FLOWTRIQ_API_KEY — find this in your Flowtriq dashboard under Settings > API Keys - FLOWTRIQ_NODE_UUID — find this on your node's settings page Add them to your OpenClaw env config and reload the agent."

Reference Files

  • references/attack-types.md — detailed breakdown of all 8 attack

families, what causes them, and recommended responses

  • references/api-endpoints.md — full endpoint reference with all

parameters for quick lookup during complex tasks

平台分布

OpenClaw

70%
按下载量换算1,581

安全审计

VirusTotal

可疑

ClawScan

通过

Static analysis

通过

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