Overview
- Skill Key
- aroooooy/xiaohua-self-improving
- Author
- aroooooy
- Source Repo
- openclaw/skills
- Version
- -
- Source Path
- skills/aroooooy/xiaohua-self-improving
- Latest Commit SHA
- 6dcf3cfbafc6f13b66d519739d197ca51d23b0cd
Official OpenClaw
rules
36%
xiaohua-self-improving
小花专用自我迭代技能 - 基于 self-improving-agent 增强，集成 OpenClaw 工作流、MEMORY.md、百度千帆、看想做找四部曲。专为国内部署优化。
Stars
0
Installs
0
Status
ACTIVE
Visibility
PUBLIC
安装方式
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 xiaohua-self-improving 技能。 若已安装，则直接安装 xiaohua-self-improving 技能。
Extracted Content
SKILL.md excerpt
# 小花自我迭代 (HuaNiu Enhanced)
> 🌸 **小花定制版**: 基于 `self-improving-agent` fork，专为 OpenClaw + 国内环境优化。集成 MEMORY.md、看想做找工作流、百度千帆 API、生产环境实战模式。
## 快速开始
```bash
# 安装
npx clawhub install xiaohua-self-improving
# 使用后记录
# 1. 错误 → .learnings/ERRORS.md
# 2. 修正 → .learnings/LEARNINGS.md
# 3. 功能请求 → .learnings/FEATURE_REQUESTS.md
# 4. 通用知识 → 提升到 MEMORY.md
```
## 核心增强
### 1. OpenClaw 原生集成
- ✅ 自动加载到 `~/.openclaw/workspace/`
- ✅ 与 `AGENTS.md`、`SOUL.md`、`TOOLS.md` 联动
- ✅ 支持 `memory/YYYY-MM-DD.md` 日常记录
- ✅ 与 `WORKFLOW_AUTO.md` 看想做找流程整合
### 2. MEMORY.md 提升工作流
```
.learnings/LEARNINGS.md (详细上下文)
↓
MEMORY.md (团队通用知识)
↓
SOUL.md (行为准则/人格)
↓
TOOLS.md (工具使用模式)
```
### 3. 国内友好配置
- 🔍 **搜索**: 百度千帆 API (`baidu-search` 技能)
- 🧠 **记忆**: local-file-rag-basic 或 scripts/memory_search.py
- 🤖 **模型**: 阿里云千帆 / Ollama 本地
- 🌐 **部署**: 无需 VPN，全国内服务
### 4. 生产环境模式
- 上下文窗口修复流程 (配置→验证→重启)
- 技能安装测试规范 (装一个→测一个→记一个)
- 错误追踪模板 (标准化 ERR-XXX 格式)
- 日常记忆追加协议 (APPEND only)
## 文件结构
```
~/.openclaw/workspace/
├── AGENTS.md # 多智能体工作流
├── SOUL.md # 人格/行为准则
├── TOOLS.md # 工具能力/坑点
├── MEMORY.md # 长期记忆 (主会话)
├── memory/ # 日常记忆 (YYYY-MM-DD.md)
├── WORKFLOW_AUTO.md # 看想做找四部曲
├── HEARTBEAT.md # 状态监控
├── USER.md # 主人偏好
└── .learnings/ # 本技能日志
├── LEARNINGS.md
├── ERRORS.md
└── FEATURE_REQUESTS.md
```
## 使用示例
### 记录错误
```markdown
### [ERR-20260302-002] ChromaDB 不兼容 Python 3.14
**Logged**: 2026-03-02T15:45:00+08:00
**Priority**: high
**Status**: workaround
**Area**: dependencies
### Summary
ChromaDB 1.5.2 与 Python 3.14 不兼容 (Pydantic v1 问题)
### Error
```
py...
Related Claw Skills
heyixuan2
bambu-studio-ai
Bambu Lab 3D printer control and automation. Activate when user mentions: printer status, 3D printing, slice, analyze model, generate 3D, AMS filament, print monitor, Bambu Lab, or any 3D printing task. Full pipeline: search → generate → analyze → colorize → preview → open BS → user slice → print → monitor. Supports all 9 Bambu Lab printers (A1 Mini, A1, P1S, P2S, X1C, X1E, H2C, H2S, H2D).
capt-marbles
geo-optimization
Generative Engine Optimization (GEO) for AI search visibility. Optimize content to appear in ChatGPT, Perplexity, Claude, and Google AI Overviews. Use when optimizing websites, pages, or content for LLM discoverability and citation.
carlulsoe
parakeet-stt
Local speech-to-text with NVIDIA Parakeet TDT 0.6B v3 (ONNX on CPU). 30x faster than Whisper, 25 languages, auto-detection, OpenAI-compatible API. Use when transcribing audio files, converting speech to text, or processing voice recordings locally without cloud APIs.
carlzhao007
feishu-process-feedback
飞书消息自动处理与进度反馈技能。安装后后台运行，监听飞书任务消息并自动创建独立进程处理。 在处理前后发送实时进度反馈（任务确认、进度百分比、完成通知）。 支持任务类型识别、智能解析、错误重试、并发控制、状态持久化。 使用场景：飞书自动化工作流、任务进度追踪、批量任务处理、需要实时反馈的场景。
cartoonitunes
bottyfans
BottyFans agent skill for autonomous creator monetization. Lets AI agents register, build a profile, publish posts (public, subscriber-only, or pay-to-unlock), upload media, accept USDC subscriptions and tips on Base, send and receive DMs, track earnings, and appear on the creator leaderboard. Use this skill when an agent needs to monetize content, interact with fans, manage a creator profile, handle payments in USDC, or operate as an autonomous creator on the BottyFans platform.
camopel
ddgs-search
Free multi-engine web search via ddgs CLI (DuckDuckGo, Google, Bing, Brave, Yandex, Yahoo, Wikipedia) + arXiv API search. No API keys required. Use when user needs web search, research paper discovery, or when other skills need a search backend. Drop-in replacement for web-search-plus.