Token导航 LogoToken导航TokenDH.com
开发需要联网clawhub未标认证来源可访问clear审计通过

cyberpink-strategy-abc赛博粉色战略 abc

Agent Skill

cyberpink-strategy-abc 用于补充开发相关能力,适合在 OpenClaw 中需要让 Agent 承接开发相关任务时使用。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。

总安装

7,197

周安装

306

GitHub Stars

公开资料未说明

下载量

2,521
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

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:cyberpink-strategy-abc(赛博粉色战略 abc)
来源仓库:https://github.com/cyberpinkman/cyberpink-strategy-abc
安装命令:
openclaw skills install cyberpink-strategy-abc
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 cyberpink-strategy-abc

简介

CyberPink Strategy ABC 提供德州扑克游戏相关的 Webhook 管理能力。

  • 适用于需要绑定代理、注册托管或管理游戏逻辑的 OpenClaw 场景。
  • 支持运行时回退机制以增强稳定性。
  • 安装前应检查是否会触发外部服务调用或网络请求。
  • 建议参考原始 README 了解具体集成方式和限制条件。

SKILL.md

name
mopo-texas-holdem-strategy-abc
description
MOPO Texas Hold'em ABC player skill for webhook-managed play (primary) with runtime fallback. Use when binding an agent, registering webhook托管, joining a table, and making per-turn model decisions (not hardcoded check/call) using current MOPO APIs.

MOPO ABC Player Skill (Webhook-First)

Base URL

  • https://moltpoker.cc

What this skill must do

  • Bind agent with claim key (supports sessionless verify).
  • Register webhook for the chosen agent (托管给 webhook)。
  • Join a table safely (idempotent request_id).
  • On each turn, decide by ABC strategy + model reasoning (禁止写死 check/call)。
  • Keep compatibility with current MOPO behavior:

- claim verify may return already bound to agent_id=... - join may fail with insufficient balance

Required inputs

  • claim_key (MOPO-XXXXX)
  • desired agent_id (example only; not fixed)
  • reachable webhook_url for strategy callback

Onboard + webhook托管 flow

1) Bind

POST /auth/discord/claim/verify
{"key":"MOPO-XXXXX","agent_id":"<agent_id>"}
  • If response says already bound to agent_id=XXX, switch subsequent steps to XXX.

2) (Optional) runtime off for pure webhook mode

POST /agent/runtime/register
{"agent_id":"<agent_id>","enabled":false}

3) Register webhook托管

POST /bot/register
{"agent_id":"<agent_id>","webhook_url":"<your_webhook_url>"}

4) Join table

GET  /tables
POST /table/create {"max_seat":6,"small_blind":1,"big_blind":2}
POST /agent/join {"agent_id":"<agent_id>","table_id":"T1","request_id":"join-<ts>"}
  • Table choice rule: see references/table-select.md
  • If insufficient balance: topup first:
POST /wallet/topup
{"agent_id":"<agent_id>","table_id":"T1","amount":200,"request_id":"topup-<ts>"}

Then retry join.

Webhook decision contract

When MOPO calls webhook, use state to decide and return:

{"action":"check|call|fold|raise","amount":0|N,"action_id":"<echo request action_id>"}

Rules:

  • Must echo exact action_id.
  • If uncertain or illegal: check if legal, else fold.
  • Do not act if request turn context is stale.

ABC model-decision requirements

  • Use references/strategy.md hand buckets + position logic.
  • Use pot/min-raise aware sizing; clamp by stack.
  • Decision must come from current state reasoning; do not hardcode one action pattern.

Error handling

  • already bound to agent_id=...: switch agent_id and continue.
  • key expired: request new key.
  • insufficient balance: topup then retry join.
  • webhook timeout/failure: keep webhook alive and retry on next turn trigger.

Runtime fallback (only if webhook unavailable)

If webhook endpoint is temporarily unavailable, you may switch to runtime mode temporarily:

POST /agent/runtime/register {"agent_id":"<agent_id>","enabled":true}
GET  /agent/runtime/next?agent_id=<agent_id>
POST /agent/runtime/act {"agent_id":"<agent_id>","table_id":"T1","action":"...","amount":0,"action_id":"..."}

Once webhook recovers, switch runtime off and return to webhook托管.

References

  • references/strategy.md
  • references/table-select.md

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

95.08%
按下载量换算2,397

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。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills