Overview
- Skill Key
- bombfuock/super-self-improving
- Author
- bombfuock
- Source Repo
- openclaw/skills
- Version
- -
- Source Path
- skills/bombfuock/super-self-improving
- Latest Commit SHA
- 7e6ef6dae0e34ea8f1a8310c7968ab16d4cd3afb
超级自我优化智能体 - 多模态记忆、反馈循环、元学习、置信度校准 / Super Self-Improving Agent - Multi-modal Memory, Feedback Loops, Meta-Learning, Confidence Calibration
Stars
0
Installs
0
Status
ACTIVE
Visibility
PUBLIC
直接复制以下提示词,发送给你的 AI 助手即可完成安装。
请先检查是否已安装 SkillHub 商店,若未安装,请根据 https://skillhub-1388575217.cos.ap-guangzhou.myqcloud.com/install/skillhub.md 安装 SkillHub 商店,然后安装 super-self-improving 技能。 若已安装,则直接安装 super-self-improving 技能。
# 超级自我优化智能体 / Super Self-Improving Agent
基于原有self-improving的增强版,增加多模态记忆、元学习、置信度校准等功能。
Enhanced version with multi-modal memory, meta-learning, confidence calibration and more.
## 🆕 相比原版新增功能
### 1. 多模态记忆 / Multi-modal Memory
- 📝 文本偏好 (Text preferences)
- 💻 代码模式 (Code patterns)
- 🎨 风格偏好 (Style preferences)
- 🔧 工具使用习惯 (Tool usage habits)
- 📊 性能指标 (Performance metrics)
### 2. 反馈循环 / Feedback Loops
- ✋ 显式反馈 (Explicit feedback) - 用户直接纠正
- 👁️ 隐式反馈 (Implicit feedback) - 从行为推断
- 🤖 合成反馈 (Synthetic feedback) - 自我评估
### 3. 元学习 / Meta-Learning
- 学习如何学习 (Learn how to learn)
- 识别最佳策略 (Identify best strategies)
- 动态调整方法 (Dynamic method adjustment)
### 4. 置信度校准 / Confidence Calibration
- 预测准确度追踪 (Track prediction accuracy)
- 校准评分 (Calibration score)
- Uncertainty quantification
### 5. 错误分析 / Error Analysis
- 错误分类 (Error categorization)
- 根因分析 (Root cause analysis)
- 预防模式 (Prevention patterns)
---
## 📁 目录结构 / Directory Structure
```
~/.super-self-improving/
├── memory/
│ ├── hot.md # 始终加载 (<100行)
│ ├── preferences.md # 用户偏好
│ ├── patterns.md # 行为模式
│ └── metrics.md # 性能指标
├── projects/ # 项目级记忆
├── domains/ # 领域级记忆
├── archive/ # 归档
├── feedback/
│ ├── explicit.md # 显式反馈
│ ├── implicit.md # 隐式反馈
│ └── synthetic.md # 自我评估
├── errors/ # 错误分析
│ ├── categories.md # 错误分类
│ ├── root_causes.md # 根因分析
│ └── prevention.md # 预防模式
└── meta/
├── strategy.md # 学习策略
├── calibration.md # 置信度校准
└── stats.json # 统计信息
```
---
## 🔄 工作流程 / Workflow
```
用户输入 → 意图识别 → 上下文匹配 → 执行 → 反馈收集
↓ ↓
记忆检索 ←──────────────── 自我评估
↓...
# 超级自我优化智能体 / Super Self-Improving Agent 基于 self-improving 的增强版,增加多模态记忆、反馈循环、元学习、置信度校准等功能。 ## 功能对比 | 特性 | 原版 | 增强版 | |------|------|--------| | 记忆类型 | 文本 | 多模态 | | 反馈来源 | 显式 | 显式+隐式+合成 | | 错误处理 | 记录 | 分析+预防 | | 置信度 | 无 | 完整校准 | | 性能追踪 | 无 | 完整指标 | ## 快速开始 ```bash # 查看统计 python super_self_improving.py stats # 添加反馈 python super_self_improving.py feedback --explicit "偏好列表而非表格" # 查看指标 python super_self_improving.py metrics # 校准 python super_self_improving.py calibrate ``` ## 目录结构 ``` ~/.super-self-improving/ ├── memory/ # 记忆存储 ├── feedback/ # 反馈收集 ├── errors/ # 错误分析 └── meta/ # 元数据 ``` ## 安全 - 不存储敏感信息 - 不修改系统配置 - 定期清理过期数据
capt-marbles
Task Router
capncoconut
Register, communicate, and earn on the x402hub AI agent marketplace. Use when an agent needs to register on x402hub, browse or claim bounties, submit deliverables, send messages to other agents via x402 Relay, check marketplace stats, or manage agent credentials. Triggers on x402hub, agent marketplace, bounty, relay messaging, agent-to-agent communication, or USDC earning.
capevace
Real-time event bus for AI agents. Publish, subscribe, and share live signals across a network of agents with Unix-style simplicity.
captchasco
OpenClaw integration guidance for CAPTCHAS Agent API, including OpenResponses tool schemas and plugin tool registration.
carol-gutianle
name: modelready description: Start using a local or Hugging Face model instantly, directly from chat. metadata: {"openclaw":{"requires":{"bins": "bash", "curl" }, "env": "URL" }}
canbirlik
Controls Wiz smart bulbs (turn on/off, RGB colors, disco mode) via local WiFi.