Skip to content

Instantly share code, notes, and snippets.

View sing1ee's full-sized avatar
🏠
Working from home

William sing1ee

🏠
Working from home
  • Billions Tech
  • HK
View GitHub Profile

Hunter Eyes — Product Introduction

Built around the hunter eyes label—a shorthand for a certain eye-area look and presence—Hunter Eyes is an AI-powered eye-area evaluation product: upload a photo and, within seconds, get an overall score, tier rank, sub-scores on multiple dimensions, and practical improvement tips. It is for people who want to understand their eye-area presentation, compare results over time, and manage habits. It turns the “hunter vs. prey” talk common in online and looksmax communities into clear, repeatable metrics.


How the product relates to the hunter eyes keyword

  • Hunter eyes (the concept): usually describes a predator-leaning mix of eye-area traits—e.g. positive or neutral canthal tilt, less upper eyelid exposure, deeper-set sockets, tighter brow–eye distance, a more almond-shaped aperture. That look comes from how anatomy, genetics, and online aesthetic language interact; it is not

freqz: Photo Puzzles, AI Puzzles, and a Workflow That Actually Ships

If you are looking for a single place to combine photo puzzles, AI puzzle aesthetics, and K-style creative output, start with freqz. Plenty of tools either ship empty templates or overload you with knobs. freqz is different: it compresses the whole loop—upload, choose a direction, generate, export—into something you can repeat every day without burning mental energy.

This matters because “good once” is not the same as “good on demand.” Creators need consistency. Teams need predictability. Casual users need speed. freqz is built around that triangle: results you can trust, steps you can remember, and outputs you can actually publish.


Why people keep coming back to freqz

SBTI Personality Test & Claude Skill: A Complete Guide

What is SBTI?

SBTI (Super-Big Personality Test) is a humorous personality test originated from Chinese creator @蛆肉儿串儿 on Bilibili. Unlike traditional personality frameworks like MBTI, SBTI takes a irreverent, meme-laden approach to self-discovery — making it both entertaining and surprisingly insightful.

The test maps responses across 15 psychological dimensions organized into 5 models:

Model Dimensions

Dreaming Guide: Background Memory Consolidation

A practical guide to understanding, enabling, and tuning OpenClaw's dreaming system — the automatic background process that turns short-term memory signals into durable long-term knowledge.

Why Dreaming Exists

OpenClaw agents accumulate memory throughout the day: daily notes, session transcripts, recall traces from searches. Most of this material is useful in the moment but doesn't belong in long-term storage. Without a consolidation step, you face one of two bad outcomes:

  • Too aggressive: every fleeting detail lands in MEMORY.md, bloating it with noise.
  • Too conservative: nothing ever gets promoted, and genuinely important patterns are lost.

Openclaw Lossless Context Management (LCM) Plugin Guide

A comprehensive guide to installing, configuring, and using the lossless-claw plugin for OpenClaw — a DAG-based context engine that never throws away your conversation history.

What Problem Does It Solve?

By default, OpenClaw uses a legacy context engine that truncates or slides old messages out of the context window when conversations get long. Once those messages are gone, the agent loses access to earlier context entirely.

Lossless-claw replaces this with a fundamentally different approach:

Build a CBT Therapy Agent with OpenClaw

A step-by-step guide to creating a personal Cognitive Behavioral Therapy (CBT) agent that you can talk to whenever you need support — no code required.

What You Will Build

A dedicated AI agent that acts as a CBT-informed conversational companion. It can:

  • Help you identify and challenge negative automatic thoughts
  • Guide you through cognitive restructuring exercises

OpenClaw imageModel 配置指南

一、什么是 imageModel

imageModel 是 OpenClaw 中专门用于视觉理解的模型配置,独立于主对话模型(model)。当对话涉及图片或视觉内容时,OpenClaw 会自动切换到 imageModel 指定的模型来处理。

二、为什么需要单独配置

主模型(model.primary)不一定支持视觉输入。例如:

  • MiniMax-M2.5-highspeed 是纯文本模型,无法处理图片

配置步骤:

# 1. 安装 acpx 插件
openclaw plugins install @openclaw/acpx

# 2. 配置 OpenClaw(.OPENCLAW 是你的 config 目录)
openclaw config set plugins.entries.acpx.enabled true
openclaw config set plugins.entries.acpx.config.permissionMode approve-all
openclaw config set acp.enabled true

推荐完整配置

agents: {
  defaults: {
    memorySearch: {
      enabled: true,
      provider: "gemini",
 model: "gemini-embedding-001",
@sing1ee
sing1ee / gist:e3e95c7deafc3be885f0a29e19177d1f
Created September 14, 2022 03:18
key steps for install osmosis full node for pocket network
1. install
```shell
cd ~/chain_bin/
wget https://github.com/osmosis-labs/osmosis/releases/download/v11.0.1/osmosisd.tar.gz
wget https://github.com/cosmos/cosmos-sdk/releases/download/cosmovisor%2Fv1.3.0/cosmovisor-v1.3.0-linux-amd64.tar.gz