AI Partner Chat

基于用户画像和向量化笔记提供个性化对话。当用户需要个性化交流、上下文感知的回应,或希望 AI 记住并引用其之前的想法和笔记时使用。

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add hhhh124hhhh/LangGraph-Partner --skill ai-partner-chat
Manual install
git clone --depth 1 https://github.com/hhhh124hhhh/LangGraph-Partner.git /tmp/LangGraph-Partner
mkdir -p ~/.claude/skills
cp -r /tmp/LangGraph-Partner/.claude/ai-partner-chat ~/.claude/skills/ai-partner-chat

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# AI Partner Chat

## Overview

Provide personalized, context-aware conversations by integrating user persona, AI persona, and vectorized personal notes. This skill enables AI to remember and reference the user's previous thoughts, preferences, and knowledge base, creating a more coherent and personalized interaction experience.

## Prerequisites

Before first use, complete these steps in order:

1. **Create directory structure**
   ```bash
   mkdir -p config notes vector_db scripts
   ```

2. **Set up Python environment**
   ```bash
   python3 -m venv venv
   ./venv/bin/pip install -r .claude/skills/ai-partner-chat/scripts/requirements.txt
   ```
   Note: First run will download embedding model (~4.3GB)

3. **Generate persona templates**
   Copy from `.claude/skills/ai-partner-chat/assets/` to `config/`:
   - `user-persona-template.md` → `config/user-persona.md`
   - `ai-persona-template.md` → `config/ai-persona.md`

4. **User adds notes**
   Place markdown notes in `notes/` directory (any format/structure)

5. **Initialize vector database** (see section 1.2 below)

Now proceed to Core Workflow →

## Core Workflow

### 1. Initial Setup

Before using this skill for the first time, complete the following setup:

#### 1.1 Create Persona Files

Create two Markdown files to define interaction parameters:

**User Persona** (`user-persona.md`):
- Define user's background, expertise, interests
- Specify communication preferences and working style
Read the full skill on GitHub

Details

Skill name
ai-partner-chat
Path
.claude/ai-partner-chat/SKILL.md
License
MIT
Repo updated
14 November 2025

FAQ

What does the AI Partner Chat skill do?

基于用户画像和向量化笔记提供个性化对话。当用户需要个性化交流、上下文感知的回应,或希望 AI 记住并引用其之前的想法和笔记时使用。

How do I install the AI Partner Chat skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add hhhh124hhhh/LangGraph-Partner --skill ai-partner-chat. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is AI Partner Chat popular?

It lives in hhhh124hhhh/LangGraph-Partner, which has 5 GitHub stars and 0 forks.

Related skills

Langgraph Development

5

hhhh124hhhh/LangGraph-Partner

专业的LangGraph AI应用开发技能,提供从概念到生产的完整开发指导。基于Context7最新调研,涵盖StateGraph设计、多代理协作、RAG系统实现、生产部署等核心场景。使用此技能构建有状态、多参与者、长期运行的AI代理应用。

AI, LLMs & Agents

Create Real Estate Worlds

5

felipealmeidasid/Pack-skills-for-archviz

Create cinematic real estate world bibles, world databases, visual DNA systems, reference-grounded architectural universes, scene libraries, realistic personas, prompt packs, and handoff packets for architecture, archviz, property launches, luxury homes, apartments, towers, condominiums, resorts, hotels, interiors, amenities, branded real estate campaigns, AI image/video generation, and future world-model systems. Use when the user wants a reusable AI-ready source of truth for realistic real estate storytelling. Ask the aspect ratio at the beginning of each new project and use 9:16 for Reels/s

AI, LLMs & Agents

Token Optimizer

8

GPire/claude-skills-swarm

Ottimizzazione ultra-avanzata dei token: prompt engineering al microsecondo, cache dei prompt (Anthropic prompt caching), riduzione token senza perdita qualità, compressione semantica, batch processing intelligente, architettura multi-agente token-efficiente, streaming ottimizzato, context window management, orchestrazione intelligente agenti, risparmio costi API. Attiva quando l'utente vuole ottimizzare i token, ridurre costi API, migliorare prompt, gestire context window, orchestrare agenti.

AI, LLMs & Agents

Singularity

8

GPire/claude-skills-swarm

SINGULARITY — Architettura definitiva finale. Mesh Orchestration (non hub-spoke), Self-Assembling Agent Swarm, Speculative Pre-Execution, Character-Level Token Crystallography, Semantic Tensor Decomposition, Cognitive Bandwidth Multiplexing, Research Agent Ultra-Specializzato, Analysis Agent con causal reasoning, Recursive Agent Self-Assembly, Attention Flow Optimizer, Emergent Specialization Protocol, Zero-Latency Pre-computation, Intelligence Gradient Amplifier, Sub-Agent DNA Injection, Async Mesh Communication, Swarm Consensus Engine, Deep Research Orchestrator, Causal Analysis Engine, Toke

AI, LLMs & Agents

Bozai Script

9

miaqu766520-a11y/ai-line-skills

把用户口述(文字或录音)整理成符合用户个人风格的口播稿——整理模式保真改写(信息零新增、口头禅保留、去AI味),共创模式辅助写稿(事实数字标存疑)。当用户说「整理成口播稿」「我口述你整理」「把这段顺成稿子」「写个口播稿」「口播稿」「帮我把这段话变成能念的稿」时使用。也用于把改稿反馈回流风格档案(迭代机制)。

AI, LLMs & Agents

Resonance Orchestrator

8

GPire/claude-skills-swarm

Orchestratore adattivo con architettura Adaptive Resonance: ottimizzazione predittiva token, routing intelligente per impedance-matching cognitivo, cascade intelligence (modelli piccoli comprimono per modelli grandi), entropy-based quality scoring, micro-burst parallelism, budget adattivo, predizione complessità pre-esecuzione. Attiva quando l'utente vuole orchestrare agenti in modo ottimale, massimizzare qualità per token, architettura multi-modello intelligente, sistema predittivo, ottimizzazione automatica risorse AI.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.