LeoYeAI/agent-master-skills / skills/anima-aios
anima-aios
VerifiedAn AI Agent cognitive growth system built on the native OpenClaw architecture. It provides agents with persistent memory management, visual intimacy progression, a 5-dimensional cognitive profile, gamified daily quests, team leaderboards, and a 5-layer memory architecture with Knowledge Palace, Pyramid thinking, and Ebbinghaus decay function. 基于 OpenClaw 原生架构的 AI Agent 认知成长体系,为 Agent 提供五层记忆架构、知识宫殿、金字塔知识组织、记忆衰减函数、LLM 智能处理、永久化记忆管理、可视化亲密度成长、五维认知画像、游戏化每日任务和团队排行榜。
docs/EXAMPLES.md
View on GitHub# Anima-AIOS 使用示例
**版本:** v6.0.0
---
## 基础功能
### 写记忆(自动同步)
```
你:记住:今天完成了 Anima v6.0 的五层记忆架构开发
Agent:✅ 记忆已保存,+2 EXP(semantic)
```
背后自动发生:
1. OpenClaw 写入 memory/2026-03-24.md
2. memory_watcher 检测到变化 → 同步到 L2
3. EXP +1(自动)
4. 每日任务"写一条记忆"自动完成
### 搜索记忆
```
你:搜索记忆"架构设计"
Agent:找到 3 条相关记忆:
1. [L3] v6 选择 Python 统一技术栈(强度: 0.95)
2. [L3] 五层记忆模型设计(强度: 0.87)
3. [L2] Phase 3 宫殿开发记录(强度: 0.72)
```
搜索结果按 `相关性 × 记忆强度` 排序。
### 查看认知画像
```
你:查看我的认知画像
🧠 认知画像 — 清禾
Lv.5 🌱 Novice 新手
[████████░░] 68.5/100
━━━ 五维评估 ━━━
📚 知识内化 ████████░░ 78.2 (#1)
🔧 知识应用 ███████░░░ 65.3 (#2)
💡 知识创造 ██████░░░░ 58.1 (#3)
🤔 元认知 █████░░░░░ 52.4 (#2)
🤝 协作认知 ████████░░ 75.6 (#1)
```
### 每日任务
```
你:今天的任务
📋 今日任务(2/3 完成)
✅ 写一条记忆 (+5 EXP)
✅ 搜索记忆 3 次 (+10 EXP)
⬜ 分享知识到团队 (+20 EXP)
```
### 团队排行
```
你:团队排行榜
🏆 团队认知排名
🥇 日安 Lv.8 82.5 📈 +3.2
🥈 清禾 Lv.5 68.5 📈 +5.1
🥉 枢衡 Lv.4 55.2 ➡️ 0.0
```
---
## 高级功能
### 健康检查
```
你:Anima 健康检查
🏥 健康报告 — 清禾
Overall: healthy ✅
完整性: 0 issues
重复: 1 条
衰减: healthy=15, weakening=3, needs_review=1
宫殿: 5 rooms, 23 items
金字塔: instances=12, rules=3, patterns=1
```
### 手动触发进化
```
你:运行每日进化
🔄 每日进化完成
提炼: 5 条 L2 → 3 条 L3
分类: 3 条知识归入宫殿
金字塔: 1 个主题提炼到 rules 层
```
---
**版本:** v6.0.0
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |