Skip to content

Instantly share code, notes, and snippets.

View discountry's full-sized avatar
📕
Learning

Disney discountry

📕
Learning
View GitHub Profile
# ============================================================
# Claude Code <-> Codex native session handoff (bash / zsh)
#
# claude-to-codex
# codex-to-claude
# claude-to-codex "focus on the failing tests" # optional note
#
# The prompt tells the agent how to work, step by step; session
# discovery is spelled out as runnable commands.
# ============================================================
#!name=AI 服务分流 · JP
#!desc=将 Claude / Anthropic / OpenAI / ChatGPT / Gemini 等主流 AI 服务,以及 Google 全线服务(搜索 / YouTube / Drive / Play / Firebase 等)分流至名为「JP」的节点。使用前请确认 Shadowrocket 中存在名称完全相同的服务器或代理组(区分大小写)。
#!category=Proxy
#!system=ios
[Rule]
# ======================================================
# OpenAI / ChatGPT / Sora
# ======================================================
#!name=X (Twitter) 分流 → HK
#!desc=将 X / Twitter 及其相关服务(图片、视频、短链、广告、直播、xAI Grok 等)全部分流至名为 HK 的代理策略
#!category=分流规则
#!system=ios
[Rule]
# ============ 主站与核心域名 ============
DOMAIN-SUFFIX,x.com,HK
DOMAIN-SUFFIX,twitter.com,HK
DOMAIN-SUFFIX,twttr.com,HK
// ==UserScript==
// @name Variational Omni — 分红预估 (Dividend Estimator)
// @namespace https://omni.variational.io/
// @version 2.1.0
// @description 在 omni.variational.io 永续合约页面的 Dividends 字段旁展示下次除息日 / 每股金额 / 年化股息率,并根据持仓表中的当前仓位预估应收或应付的分红金额。数据来自 Business Quant Dividends API。
// @author -
// @match https://omni.variational.io/perpetual/*
// @grant GM_xmlhttpRequest
// @grant GM_getValue
// @grant GM_setValue

RootData 团队成员项目状态自动尽调面板安装教程

一、安装 Tampermonkey 插件

Tampermonkey 也常被称为“油猴”,用于安装和运行浏览器用户脚本。

Chrome、Edge、Brave 浏览器

  1. 打开 Tampermonkey 官方网站
  2. 选择自己使用的浏览器

aiship 使用说明(macOS)

暂存全部改动 → 用 AI 生成提交信息 → 提交 → 推送。AI 不可用时自动用兜底信息,保证总能提交。

依赖

  • git、python3:装一次 Xcode 命令行工具即可:xcode-select --install
  • AI CLI(可选):脚本自动探测 claudecodex;两者都没有时用兜底信息,或用 AISHIP_MSG_CMD 指定任意命令。
  • timeout(可选):macOS 默认没有,AI 步骤就不设时限(不影响功能)。要启用:brew install coreutils,再把 "$(brew --prefix)/opt/coreutils/libexec/gnubin" 加进 PATH。
#!/bin/bash
# 确保脚本以 root 权限运行
if [ "$EUID" -ne 0 ]; then
echo "请使用 sudo 权限运行此脚本。命令: sudo bash $0"
exit 1
fi
SWAP_FILE="/swapfile"
SWAP_SIZE="2G"
{
"mcpServers": {
"codex": {
"command": "codex",
"args": ["mcp-server"],
"type": "stdio"
}
}
}
name get-kline-prediction
description Fetch and summarize K-line prediction reports from http://localhost:3000. Use when the user asks for a token price prediction, forecast, K-line prediction, price outlook, market forecast, or mentions 'prediction report', 'forecast report', 'kline prediction', 'price prediction', or wants to know the predicted price movement for a specific token. Covers fetching the latest AI+algorithmic forecast, summarizing outlook, drivers, risks, theory notes, and predicted candlestick data.

Get K-line Prediction Report

Fetch the latest AI-powered K-line prediction report for a token from http://localhost:3000 and present a clean, structured summary.

API Endpoint

Shame on you Figma.... Here is a workaround without having to install a fork

Register the client:

curl -X POST https://api.figma.com/v1/oauth/mcp/register \
  -H "Content-Type: application/json" \
  -d '{
    "client_name": "Claude Code (figma)",
 "redirect_uris": ["http://127.0.0.1:19876/mcp/oauth/callback"],