← 返回 Skills 市场

cognitive-enhancement-engine

Name: cognitive-enhancement-engine
Author: chen-feng123

作者 CHEN-feng123 · GitHub ↗ · v1.0.2 · MIT-0

cross-platform ✓ 安全检测通过

总下载

当前安装

版本数

在 OpenClaw 中安装

/install cognitive-enhancement-engine

功能描述

AI Agent cognitive enhancement engine with working memory, TF-IDF vector memory, planning, reasoning, reflection, and metacognitive monitoring. Zero external...

使用说明 (SKILL.md)

Cognitive Enhancement Engine (认知力增强引擎)

Lightweight AI Agent cognitive engine with working memory, TF-IDF vector memory, planning, reasoning, reflection, and metacognitive monitoring. Zero external dependencies — pure Python standard library.

Quick Start

# Run built-in demo
python skills/cognitive-enhancement-engine/engine.py

# Or one-click setup
bash skills/cognitive-enhancement-engine/scripts/setup.sh     # Linux/macOS/WSL
skills\cognitive-enhancement-engine\scripts\setup.bat         # Windows

Core Usage

from engine import CognitiveEnhancer

# Create engine
brain = CognitiveEnhancer(long_term_capacity=1000)

# Learn
brain.memorize("Paris is the capital of France.", importance=0.9)
brain.perceive("User asked about French capital")

# Retrieve
results = brain.recall("capital of France", top_k=3)

# Plan
plan = brain.plan("Build a web application")

# Reason
answer = brain.reason("What is the capital of France?")

# Reflect
suggestions = brain.reflect()

# Full task execution
result = brain.execute_task("Calculate 15% tip on $200 bill")
print(result)

# Status
status = brain.get_status()

API Overview

Method	Description
`perceive(observation)`	Store perception into working memory
`recall(query, top_k)`	Search long-term memory
`memorize(content, importance)`	Store into long-term memory
`plan(goal)`	Decompose goal into actionable steps
`reason(problem)`	Memory-based reasoning
`reflect()`	Discover failure patterns, suggest improvements
`execute_task(goal, executor)`	End-to-end task execution
`get_status()`	Return engine runtime status

Configuration

Parameter	Default	Description
`long_term_capacity`	1000	Max long-term memories
`working_memory_size`	10	Working memory FIFO size
`similarity_threshold`	0.15	Recall similarity threshold

Features

TF-IDF Vector Memory — Inverted-index fast similarity search
Working Memory — FIFO short-term context cache
Planner — Goal decomposition + automatic task type detection (calculate/search/summarize/translate/write)
Reasoner — Memory-retrieval based Q&A
Reflector — Failure pattern tracking and root cause mining
Metacognitive Monitor — Task duration & error rate tracking, dynamic adjustment

Installation

Method	Command
One-click (Linux/macOS)	`bash scripts/setup.sh`
One-click (Windows)	`scripts\setup.bat`
Copy-only	Copy `engine.py` to your project
ClawHub	`clawhub install cognitive-enhancement-engine`

File Structure

cognitive-enhancement-engine/
├── SKILL.md
├── engine.py              # Core engine (~17KB)
├── index.js               # Node.js bridge
├── package.json
├── assets/
│   └── icon.svg
├── references/
│   ├── API_SPEC.md
│   └── USE_GUIDE.md
└── scripts/
    ├── setup.sh
    ├── setup.bat
    ├── test-basic.py
    └── test-client.js

License

MIT

安全使用建议

This skill looks reasonable for a local Python cognitive-memory helper. Before installing, make sure you are comfortable with Python-based local execution, avoid storing secrets in its memory, and inspect or skip setup.sh if you do not want it to edit your shell configuration. The provided engine.py artifact was truncated in the review prompt, so users needing high assurance should inspect the full file before running it.

功能分析

Type: OpenClaw Skill Name: cognitive-enhancement-engine Version: 1.0.2 The 'cognitive-enhancement-engine' skill bundle is a legitimate implementation of a memory and planning architecture for AI agents using the Python standard library. The core logic in engine.py uses TF-IDF and inverted indexing for memory retrieval without any external dependencies or high-risk system calls. While the setup.sh script modifies shell configuration files (.bashrc/.zshrc) to add a convenience alias, this behavior is transparently documented and aligned with the tool's purpose as a developer utility.

能力标签

crypto

能力评估

ℹ Purpose & Capability

The artifacts coherently describe a local cognitive/memory engine with planning, reasoning, reflection, and TF-IDF retrieval. The main user-relevant note is that it is designed to store and reuse user-provided text as memory.

✓ Instruction Scope

The instructions are user-directed examples and setup commands. They do not ask the agent to override user intent, hide behavior, force external tools, or perform unrelated actions.

ℹ Install Mechanism

There is no registry install spec and no declared required binary, but the docs and setup script require Python. The setup script is local, but it appends a persistent shell alias to .bashrc or .zshrc.

ℹ Credentials

The visible artifacts are proportionate to the stated local-library purpose and do not declare credentials or external APIs. The main environment change is the optional setup script modifying the user's shell configuration.

ℹ Persistence & Privilege

No background service or privileged access is shown. Persistence is limited to in-process memory during use and a shell alias added by setup.sh if the user runs it.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install cognitive-enhancement-engine
安装完成后，直接呼叫该 Skill 的名称或使用 /cognitive-enhancement-engine 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.2

Version 1.0.2 - No file changes detected; documentation and code remain unchanged. - No new features, fixes, or updates in this version.

v1.0.1

Version 1.0.0 – Initial Release - Introduces a pure Python cognitive enhancement engine for AI agents with no external dependencies. - Features include working memory, TF-IDF vector memory, planning, reasoning, reflection, and metacognitive monitoring. - Provides a simple API for memory management, planning, problem solving, task execution, and runtime status. - Includes setup scripts, Node.js bridge, and sample tests for multi-language compatibility. - Offers clear installation and configuration options for quick integration.

v1.0.0

- Initial release of the cognitive-enhancement-engine. - Pure Python implementation with zero external dependencies. - Provides working memory, TF-IDF vector-based long-term memory, planning, reasoning, reflection, and metacognitive monitoring. - Includes one-click setup scripts for Linux, macOS, and Windows. - Offers a simple API for memory, planning, reasoning, and execution tasks. - Lightweight design—ideal for integration and rapid prototyping.

元数据

Slug cognitive-enhancement-engine

版本 1.0.2

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 3

常见问题