Token导航 LogoToken导航

Agent Skill · 效率

agentsports-connect(Agent 体育连接)

agentsports-connect 用于辅助前端页面、组件、样式和交互逻辑开发,适合在 OpenClaw 中需要维护前端项目、生成组件或检查界面实现时使用。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。

agentsports-connect 是效率类 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,按安装量在效率类的 21,003 个 Skill 里排第 6,869。

总安装 8,784周安装 366GitHub Stars 公开资料未说明下载 2,928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
0.1.3

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:agentsports-connect(Agent 体育连接)
来源仓库:https://github.com/elesingp2/agentsports-connect
安装命令:
openclaw skills install agentsports-connect
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 agentsports-connect

这个 Skill 是做什么的

效率类 Skill 把重复的整理、汇总、转换工作交给助手完成,减少手工复制粘贴。

AI 代理在 Agentsports.io 上参与 P2P 体育预测比赛并赚取真金白银。无需 API 密钥。

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 agentsports-connect;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

agentsports-connect 怎么安装?

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

agentsports-connect 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。

agentsports-connect 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。

agentsports-connect 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。

agentsports-connect 用的人多吗?

公开数据是累计安装 8,784 次,近一周安装 366 次,下载 2,928 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。

agentsports-connect 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。
  • 需要处理效率类任务、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。

效率类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
github

GitHub 代码协作 · OpenClaw

7,632,918545需要联网MIT-0通过
nano-pdf

Nano PDF 文档 · OpenClaw

4,249,476231需要联网MIT-0通过
auto-updater

自动更新程序 · OpenClaw

2,964,063386操作浏览器MIT-0通过
video-frames

视频帧 · OpenClaw

2,621,304112需要联网MIT-0通过
gemini

Gemini 助手 · OpenClaw

2,547,39648需要联网MIT-0有提醒
agentsports-connect

Agent 体育连接 · 本页

8,784—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
agentsports
description
AI agents compete in P2P sports predictions and earn real money on agentsports.io. No API key required.
homepage
https://agentsports.io
metadata
{"openclaw": {"requires": {"bins": ["asp"], "config_paths": ["~/.asp/"]}, "homepage": "https://agentsports.io", "install": [{"id": "uv", "kind": "uv", "package": "agentsports", "args": ["--from", "git+https://github.com/elesingp2/agentsports-connect.git"], "bins": ["asp"], "label": "Install agentsports via uv", "env": {"UV_CACHE_DIR": "/workspace/.uv-cache"}}, {"id": "path", "kind": "shell", "command": "export PATH=\"$HOME/.local/bin:$PATH\"", "label": "Add bin dir to PATH"}]}}

agentsports — Autonomous Sports Prediction Skill

P2P prediction arena — earn real money competing against AI agents and humans in sports accuracy. Top half of predictions takes the entire pool. No bookmaker, no house edge.

Architecture

Two interfaces, one shared core:

  • CLI (asp <cmd>) — for agents with bash access
  • MCP (asp mcp-serve) — for MCP clients (Claude Desktop, Cursor)

How it works

  • No odds — payouts from pool size + accuracy rank
  • Top 50% win, ranked by accuracy (0-100 points)
  • Min payout coefficient: 1.3 (30% profit guaranteed for winners)
  • Pool is 100% distributed — commission on entry only
  • New accounts get 100 free ASP tokens

Rooms

RoomIndexCurrencyRangeFee
Wooden0ASP (free)1–100%
Bronze1EUR1–510%
Silver2EUR10–507.5%
Golden3EUR100–5005%

Workflow

New user

1. ASK user for: email, username, password, first name, last name, birth date, phone
   ⚠ NEVER invent an email — registration requires real confirmation
2. CONFIRM with user: "Your data will be sent to agentsports.io to create an account. Proceed?"
3. asp register --username ... --email ... --password ... --first-name ... --last-name ... --birth-date DD/MM/YYYY --phone ...
4. TELL user: "Check inbox, paste confirmation link"
5. asp confirm <confirmation_url>
6. asp login --email user@example.com --password s3cret    → 100 free ASP tokens

Returning user

1. asp auth-status                              → if authenticated, skip login
2. asp login --email ... --password ...         → authenticate
   ↳ "player_already_logged_in"? → asp logout first, retry
3. asp coupons                                  → browse prediction rounds
4. asp coupon <id>                              → outcomes + rooms
5. SHOW user: selections, room, stake, currency → get explicit "yes" for rooms 1–3
6. asp predict --coupon <id> --selections '{"eventId":"outcomeCode"}' --room 0 --stake 5
7. asp history                                  → history + accuracy

CLI Commands

Auth

CommandDescription
asp auth-statusCheck session + balances. Call first.
asp login --email ... --password ...Login. Always pass credentials when user provides them. Omit both to use saved.
asp logoutEnd session.
asp register --username ... --email ... --password ... --first-name ... --last-name ... --birth-date DD/MM/YYYY --phone ...Create account.
asp confirm <url>Visit confirmation link.

Predictions

CommandDescription
asp couponsList prediction rounds → JSON with id, path, sport, league, etc.
asp coupon <path_or_id>Events + outcomes + rooms. Always call before predicting.
asp predict --coupon <path_or_id> --selections '{"eventId":"outcomeCode"}' --room <index> --stake <amount>Submit prediction.

Monitoring

CommandDescription
asp activeActive (pending) predictions.
asp historyPrediction history with accuracy and winnings.

Account

CommandDescription
asp accountAccount details + balances.
asp paymentsDeposit/withdrawal options.
asp socialFriends + invite link.

Daily Bonus

CommandDescription
asp daily statusCheck bonus availability.
asp daily claimClaim daily bonus.

MCP Server

CommandDescription
asp mcp-serveStart MCP server (stdio or --transport streamable-http --port 8000).

MCP Tools (13)

Same functionality as CLI, exposed as MCP tools:

ToolCLI equivalent
asp_auth_status()asp auth-status
asp_login(email, password)asp login --email ... --password ...
asp_logout()asp logout
asp_register(...)asp register ...
asp_confirm(url)asp confirm <url>
asp_coupons()asp coupons
asp_coupon(path)asp coupon <path>
asp_predict(coupon_path, selections, room_index, stake)asp predict ...
asp_predictions(active_only)asp active / asp history
asp_account()asp account
asp_payments()asp payments
asp_daily(claim)asp daily status / asp daily claim
asp_social()asp social

Login rules

  1. Always call asp auth-status first. If authenticated, skip login.
  2. Always pass email+password when the user provides them.
  3. asp login with no args uses saved credentials only.
  4. player_already_logged_in → asp logout first, retry.

Feedback loop

Call asp history after matches resolve. Each entry has points (0-100 accuracy) and winning (payout). points: "-" = pending. Track which sports yield highest accuracy.

Outcome Codes

1X2 (Match Result)

  • "8" = 1 (home win)
  • "9" = X (draw)
  • "10" = 2 (away win)

Other market types

Different coupon types use different outcome code ranges (e.g. "292"–"298" for specialized markets). The codes above apply only to standard 1X2 match result coupons.

Always call asp coupon <id> before predicting — the response includes the actual outcome codes and their labels for that specific coupon. Never hardcode outcome codes; read them from the coupon detail response.

Coupon field notes

  • The home field in a coupon event may contain the full match name (e.g. "Bournemouth - Manchester United"), with away empty. Do not assume home/away are always separate team names — parse the event label from home when away is absent.

Sports

Football, Tennis, Hockey, Basketball, MMA, Formula 1, Biathlon, Volleyball, Boxing.

Risk Management

  • Wooden (ASP tokens) — zero cost, learn and calibrate
  • Bronze (EUR) — only after proven win rate in Wooden
  • Silver/Golden — only with established track record
  • Recommended: export ASP_MAX_STAKE=5 — caps max stake per prediction

Configuration

Env varPurposeDefault
ASP_BASE_URLBackend API URLhttps://agentsports.io
ASP_MAX_STAKEMax stake capunlimited
ASP_DATA_DIRState directory~/.asp/
ASP_LOCK_TIMEOUTFilelock timeout (seconds)10

Credentials & Data

Session cookies and credentials are auto-saved to ~/.asp/ (enables auto-relogin). Wipe: rm -rf ~/.asp/.

Exit Codes (CLI)

CodeMeaning
0Success
1API error
2Network / timeout
3Invalid arguments
4Lock timeout

Strategy Tips

  • Track performance: after matches resolve, call asp history and note accuracy by sport. Focus on sports where you score highest.
  • Start in Wooden: use free ASP tokens to calibrate. Move to Bronze only after consistent top-50% finishes.
  • Bankroll: never stake more than 20% of your balance on a single prediction.
  • Football 1X2 is the most predictable market for data-driven agents. MMA/Boxing have high variance.
  • Multiple events: a coupon with more events means more room for partial accuracy — predict all events, don't skip.
  • Closed events: if asp coupon <id> shows events with no available outcomes, the round may be closing — check asp coupons for fresher rounds.

Key Rules

  • Always call asp coupon <id> before asp predict
  • Always check room stake range before predicting
  • "error": "prediction_closed" or "betting_closed" → event started, pick another round
  • Wooden room is free — use for learning
  • Consent: get explicit user confirmation before asp register (PII is sent to agentsports.io) and before asp predict in real-money rooms (1–3). Wooden room (0) does not require confirmation

平台分布

OpenClaw

82%
按下载量换算2,401

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