Token导航 LogoToken导航TokenDH.com
运维需要联网clawhub未标认证来源可访问clear审计提醒

smart-memory-trigger-system智能记忆触发系统

Agent Skill

smart-memory-trigger-system 用于整理文档、README、Markdown 和说明材料,适合在 OpenClaw 中需要把零散信息整理成结构清晰的文档时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

7,144

周安装

289

GitHub Stars

公开资料未说明

下载量

2,243
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:smart-memory-trigger-system(智能记忆触发系统)
来源仓库:https://github.com/daddy-sun/smart-memory-trigger-system
安装命令:
openclaw skills install smart-memory-trigger-system
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install smart-memory-trigger-system

简介

智能记忆触发系统可自动判断何时创建结构化文档,适用于整理零散信息为清晰文档。

  • 适合在 OpenClaw 中处理 README、Markdown 等材料的归纳与归档任务。
  • 通过分析任务复杂度与用户意图,自动触发文档创建工作流并生成规范格式。
  • 安装前需确认权限范围及是否涉及文件读写或命令执行操作。
  • 建议结合原始仓库与 README 进一步验证具体功能与使用边界。

SKILL.md

name
intelligent-memory-trigger-system
displayName
Intelligent Memory Trigger System
description
Intelligent system that automatically determines when to create workflow documentation based on task complexity, repetition patterns, and user intent. Transforms from 'passively waiting for instructions' to 'actively providing help'.
version
2.0.0
type
skill
tags
memory, workflow, automation, intelligence, decision-making

🧠 Intelligent Memory Trigger System

🎯 Skill Overview

An intelligent system that automatically determines when to create workflow documentation based on task complexity, repetition patterns, and user intent. Transforms agents from "passively waiting for instructions" to "actively providing help."

📋 Usage Scenarios

Automatically triggers this skill when encountering the following situations:

Mandatory Trigger Conditions (Hard Requirements)

  1. Steps ≥ 3: Task contains 3 or more operational steps
  2. Cross-system ≥ 2: Task involves 2 or more system components
  3. Configuration Changes: Modifying core configuration files or system settings
  4. Repetition Occurrence: Same or similar task appears for the 2nd time
  5. User Explicit Request: User indicates "remember", "summarize", "process"

Recommended Trigger Conditions

  1. Complexity Score ≥ 6 points (see evaluation algorithm)
  2. Potential Reuse: User mentions "next time", "in the future"
  3. Team Collaboration Tasks: Involving multiple agent collaboration
  4. Error Risk: Complex operations prone to errors

🧠 Core Decision Logic

Complexity Evaluation Algorithm

function evaluateComplexity(taskDescription) {
  let score = 0;
  
  // 1. Step Count Evaluation
  if (taskDescription contains "first step" and "second step") score += 2;
  if (taskDescription contains "third step") score += 2;
  if (taskDescription contains "fourth step" or "finally") score += 2;
  
  // 2. System Involvement Evaluation
  if (taskDescription contains "configuration file" or ".json") score += 1;
  if (taskDescription contains "command line" or "command") score += 1;
  if (taskDescription contains "restart" or "gateway") score += 1;
  if (taskDescription contains "Feishu" or "WeChat" or "platform") score += 1;
  
  // 3. Configuration Impact Evaluation
  if (taskDescription contains "configuration" or "settings") score += 1;
  if (taskDescription contains "modify" or "edit") score += 1;
  if (taskDescription contains "add" or "delete") score += 1;
  
  // 4. Collaboration Requirement Evaluation
  if (taskDescription contains "team" or "collaboration") score += 1;
  if (taskDescription contains "multiple" or "several") score += 1;
  
  return score;
}

Decision Thresholds

  • Total Score ≥ 8 points → Must create memory trigger
  • Total Score 6-7 points → Recommend creating memory trigger
  • Total Score ≤ 5 points → No need to create memory trigger

🔍 Repetition Pattern Detection

Task Type Identification Keywords

System Configuration: ["configuration", "settings", "install", "deploy"]
File Operations: ["create", "edit", "delete", "move"]
Command Line: ["execute", "run", "command", "script"]
Platform Integration: ["Feishu", "WeChat", "API", "integration"]

Repetition Detection Logic

When similarity between current task and historical tasks > 0.7, treat as repetition pattern and should create or reference existing workflow.

🎯 User Intent Analysis

Explicit Request Keywords

Recording Requests: ["remember", "record", "save", "memo"]
Summary Requests: ["summarize", "organize", "arrange", "sort"]
Process Requests: ["process", "steps", "method", "operation"]
Future Use: ["next time", "in the future", "later", "repeat"]

When detecting these keywords, proactively ask if workflow documentation is needed.

💬 Proactive Inquiry Templates

Based on Complexity

"Teacher Sun, this task appears to be relatively complex (score: X points) and may be reused. Would you like me to create a workflow document?"

Based on Repetition Pattern

"Teacher Sun, this task is very similar to the previous [similar task]. Should I reference the previous workflow?"

Based on User Intent

"Teacher Sun, you mentioned needing to [record/summarize/process]. Should I create the document now?"

Based on Configuration Importance

"Teacher Sun, this configuration change may affect system stability. Should I record the detailed steps?"

📝 Workflow Document Creation

Document Naming Convention

  • [task-type]-workflow.md
  • Example: feishu-bot-configuration-workflow.md

Document Structure Requirements

  1. Workflow Overview: Task objectives and value
  2. Configuration Steps: Detailed operational steps (clearly numbered)
  3. Verification Methods: How to verify successful configuration
  4. Common Issues: Potential problems and solutions
  5. Related Files: Involved configuration files and documents

Storage Location

  • Main Directory: C:\Users\sjh65\.openclaw\workspace\workflows\
  • Quick Access: Dedicated documents in root directory

🔧 System Maintenance

Regular Checks

  • Weekly: Check task history, identify high-complexity tasks without workflows
  • Monthly: Optimize complexity scoring standards
  • Quarterly: Review and update all workflow documents

Optimization Mechanism

  • Adjust trigger conditions based on user feedback
  • Optimize keywords based on actual usage
  • Improve workflow documents based on task execution effectiveness

📈 Effectiveness Evaluation Metrics

Quantitative Metrics

  1. Workflow Coverage: Proportion of high-complexity tasks with established workflows
  2. Proactive Inquiry Rate: Proportion of proactively asking to create workflows when needed
  3. User Reminder Rate: Proportion needing user reminders to provide workflows (goal: reduce)
  4. Workflow Usage Rate: Frequency of workflow documents being actually referenced

Quality Metrics

  1. Workflow Completeness: Whether steps are complete and clear
  2. Trigger Accuracy: Whether keyword triggers are accurate
  3. User Satisfaction: Whether workflows truly help with work

🎯 Practical Application Cases

Case 1: Feishu Bot Configuration

  • Complexity Score: 9 points (steps 4 + cross-system 3 + system impact 2)
  • Trigger Conditions: Cross-system ≥ 2, configuration changes, repetition occurrence
  • Result: Created feishu-bot-configuration-workflow.md
  • Trigger Keywords: ["Feishu bot", "configure bot", "channel configuration", "pairing"]

Case 2: File Reading

  • Complexity Score: 3 points
  • Trigger Conditions: None
  • Result: No need to create workflow document

Case 3: Model Testing

  • Complexity Score: 6 points
  • Trigger Conditions: Complexity score ≥ 6 points
  • Result: Asked "Would you like me to create a workflow document?"

🔄 Complete Workflow

Start Task
    ↓
Analyze Task Description
    ↓
Evaluate Complexity (step count, system involvement, configuration impact)
    ↓
Check Task History (is it a repetitive type?)
    ↓
Analyze User Intent (are there "remember", "summarize" keywords?)
    ↓
    ┌─────────────────────┐
    │ Need to create memory trigger? │
    └─────────────────────┘
            ↓
    ┌─────────────────────┐
    │ Yes → Proactively ask user │
    │ No → Execute task normally │
    └─────────────────────┘

📋 Quick Reference

Must Create Workflow Situations

  1. Steps ≥ 3
  2. Cross-system ≥ 2
  3. Configuration changes
  4. Task repeats for 2nd time
  5. User explicit request
  6. Complexity score ≥ 8 points

Recommend Inquiry Situations

  1. Complexity score 6-7 points
  2. Potential reuse
  3. Team collaboration tasks
  4. Error risk

No Need for Workflow Situations

  1. Complexity score ≤ 5 points
  2. Clearly one-time operations
  3. Simple queries or information retrieval
  4. Exploratory trial-and-error operations

*Skill Creation Time: 2026-03-18* *Upgraded to English Version: 2026-03-20* *Original Creator: Commander (based on Shrimp Assistant's design)* *Upgraded By: Shrimp Assistant (main agent)* *Goal: Achieve systematic, automated memory trigger decision-making*

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

86.62%
按下载量换算1,943

安全审计

VirusTotal

通过

ClawScan

可疑

Static analysis

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills