self-evolving-skillMeta-cognitive self-learning system - Automated skill evolution based on predictive coding and value-driven mechanisms.
Install via ClawdBot CLI:
clawdbot install whtoo/self-evolving-skill元认知自学习系统 - 基于预测编码和价值驱动的Skill自动演化。
-: 残差 自适应反思触发**: 基于残差能量自动判断何时需要学习
# 技能已安装到 ~/.openclaw/skills/self-evolving-skill
# 或使用ClawHub
clawhub install self-evolving-skillself-evolving-skill/
├── core/ # Python核心
│ ├── residual_pyramid.py # 残差金字塔（SVD分解）
│ ├── reflection_trigger.py # 自适应触发器
│ ├── experience_replay.py # 经验回放缓存
│ ├── skill_engine.py # 核心引擎+ValueGate
│ ├── storage.py # 持久化
│ └── mcp_server.py # MCP服务器
├── src/ # TypeScript SDK
│ ├── index.ts # 主入口
│ ├── cli.ts # CLI
│ └── mcp-tools.ts # 工具定义
├── skills/ # OpenClaw Skill
│ └── self-evolving-skill/ # 技能封装
├── MCP_CONFIG.md # MCP配置
└── README.md # 文档| 工具 | 描述 | 参数 |
|------|------|------|
| skill_create | 创建Skill | name, description |
| skill_execute | 执行并学习 | skill_id, context, success, value |
| skill_analyze | 分析嵌入 | embedding |
| skill_list | 列出Skills | - |
| skill_stats | 系统统计 | - |
| skill_save | 持久化保存 | skill_id |
| skill_load | 加载 | skill_id |
# 列出所有Skill
openclaw skill self-evolving-skill list
# 创建Skill
openclaw skill self-evolving-skill create --name "MySkill"
# 执行
openclaw skill self-evolving-skill execute <id> --success
# 分析
openclaw skill self-evolving-skill analyze --embedding '[0.1,0.2,...]'
# 统计
openclaw skill self-evolving-skill stats# 启动MCP服务器
cd ~/.openclaw/skills/self-evolving-skill
./run_mcp.sh
# 或使用适配器
python3 mcporter_adapter.py skill_list '{}'import { SelfEvolvingSkillEngine } from 'self-evolving-skill';
const engine = new SelfEvolvingSkillEngine();
await engine.init();
const { skillId } = await engine.createSkill({ name: 'Analyzer' });
const stats = await engine.stats();pyramid = ResidualPyramid(max_layers=5, use_pca=True)
decomposition = pyramid.decompose(embedding)
# 输出:
# - residual_ratio: 残差能量比率
# - suggested_abstraction: POLICY / SUB_SKILL / PREDICATE
# - novelty_score: 综合新颖性| 覆盖率 | 抽象层级 | 操作 |
|--------|---------|------|
| >80% | POLICY | 调整策略权重 |
| 40-80% | SUB_SKILL | 生成子Skill |
| <40% | PREDICATE | 归纳新谓词 |
trigger = ReflectionTrigger(
min_energy_ratio=0.10, # 初始阈值
value_gain_threshold=0.20, # 触发阈值
target_trigger_rate=0.15 # 目标15%触发率
)| 路径 | 说明 |
|------|------|
| ~/.openclaw/skills/self-evolving-skill | 技能根目录 |
| ~/.openclaw/mcp_servers/self-evolving-skill.json | MCP服务器配置 |
| ~/.openclaw/workspace/self-evolving-skill/storage | 数据存储 |
Generated Mar 1, 2026
The skill can analyze customer queries to identify gaps in existing response policies. It automatically evolves by creating sub-skills for handling new, frequent issues and adjusting strategies for improved resolution rates, reducing manual intervention.
By decomposing user engagement data, the skill detects novel patterns in preferences and evolves content recommendation policies. It generates sub-skills for niche segments and refines predicates to enhance personalization accuracy over time.
The skill processes sensor data embeddings to predict equipment failures. It evolves by identifying residual anomalies, creating sub-skills for specific failure modes, and adjusting maintenance policies to optimize uptime and reduce costs.
Analyzing transaction embeddings, the skill detects novel fraud patterns through residual pyramid decomposition. It evolves by generating sub-skills for emerging threat types and updating detection policies to improve accuracy and reduce false positives.
The skill assesses student performance data to identify learning gaps. It evolves by creating sub-skills for challenging topics, adjusting teaching strategies based on success rates, and personalizing content to improve educational outcomes.
Offer the skill as a cloud-based service with tiered pricing based on usage volume and features. Revenue comes from monthly or annual subscriptions, targeting businesses needing automated AI evolution without infrastructure management.
Sell perpetual licenses for on-premises deployment, including customization and support services. Revenue is generated through upfront license fees and ongoing maintenance contracts, ideal for large organizations with strict data privacy requirements.
Provide professional services to integrate the skill into existing AI systems, with tailored training and evolution strategies. Revenue comes from project-based fees and retainer agreements for continuous optimization and support.
💬 Integration Tip
Start by integrating the MCP server with existing AI pipelines to automate skill evolution, ensuring data storage paths are configured for persistence and regular backups.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection