Token导航 LogoToken导航TokenDH.com
效率只读clawhub未标认证来源可访问clear审计提醒

clear-mind-skill头脑清晰的技巧

Agent Skill

clear-mind-skill 用于补充效率相关能力,适合在 OpenClaw 中需要让 Agent 承接效率相关任务时使用。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

7,532

周安装

317

GitHub Stars

公开资料未说明

下载量

2,637
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:clear-mind-skill(头脑清晰的技巧)
来源仓库:https://github.com/webray1983/clear-mind-skill
安装命令:
openclaw skills install clear-mind-skill
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 clear-mind-skill

简介

clear-mind-skill 同样用于 MEMORY.md 文件的维护与优化,支持投资组合与项目细节管理。

  • 适合在 OpenClaw 中需要结构化记忆辅助的场景下使用。
  • 通过 clawhub 安装,命令为 openclaw skills install clear-mind-skill。
  • 使用前需确认本地文件路径与读写权限,注意备份以防数据丢失。
  • 建议结合来源仓库和 README 文档进一步核验具体功能和使用细节。

SKILL.md

name
clear-mind
description
Memory file maintenance and optimization system. Use when factual information (portfolio, projects, technical details) accumulates in MEMORY.md, or when periodic memory cleanup is needed. Migrates factual content to separate files, keeps only core rules and indexes in MEMORY.md, maintains Quick Index table for navigation. Size/line count is NOT a trigger — only factual bloat matters.

Clear-Mind Skill

Memory hygiene system to prevent MEMORY.md bloat.

When to Use

Activate this skill when:

  • Factual information (portfolio, projects, technical details) accumulates in MEMORY.md — Primary trigger condition
  • Memory cleanup is requested
  • Periodic maintenance (recommended monthly)

Important: Do NOT use file size (lines/tokens) as the trigger. A large MEMORY.md with only core rules is fine. Only act when factual bloat is detected.

Pre-Flight: First-Run User Check

Before starting the first clear-mind task:

"Note: The following categories will be kept in MEMORY.md for quick access: - Installed Skills list — needed for every task - Technical Setup — agent capabilities and frequent-use configs Only factual information used for specific scenarios (projects, portfolio, historical events) will be migrated. Are there any other factual categories you'd like to keep in MEMORY.md?"

Wait for user confirmation before proceeding to Core Workflow.

Content Migration Rules

KEEP in MEMORY.md

  • Core behavioral rules (Honesty, Temporal Verification, etc.) — immutable principles
  • Task index (name + path only) — for navigation
  • Quick Index table — for factual information access
  • Minimal architecture notes — essential system structure
  • All Technical Setup — agent capabilities, installed skills, configs, tools that are frequently accessed. If it's about "what I can do," it stays.
  • Any information that defines the agent's identity or capabilities — this is core functionality

MOVE to facts/

  • Historical events and incidents — specific past occurrences
  • Project details and statuses — concrete project information
  • Portfolio holdings — specific investment data
  • User preference lists — specific user choices
  • Scenario-specific information — data relevant only to particular situations

DELETE

  • Redundant summaries — information already captured elsewhere
  • Outdated temporary notes — expired or irrelevant information
  • Information already in other systems — duplicate data

Clear Distinction Guidelines

DEFINITELY KEEP in MEMORY.md (NO EXCEPTIONS)

  • Rules that define agent behavior
  • Instructions for how the agent should operate
  • Capabilities and limitations
  • Installed skills list
  • Tool descriptions and usage guidelines
  • System architecture fundamentals

DEFINITELY MOVE to facts/

  • Specific dates and events
  • Project names, deadlines, and statuses
  • Financial data and investment holdings
  • User-specific preferences (e.g., "I prefer blue themes")
  • Historical interactions and their outcomes

Migration Principle: Only move facts that are scenario-specific (this project, that stock, past events). Capabilities stay, specifics go.

Critical Safeguard: When in doubt, KEEP in MEMORY.md. It's safer to retain information in the core memory than to risk losing important capabilities.

Core Workflow

Phase 1: Analyze Current State

  1. Read current MEMORY.md
  2. Check for factual bloat: Are there sections containing specific data that belongs elsewhere?
  3. Identify content categories:

- Core Rules (keep in MEMORY.md) - Factual Information (migrate to facts/) - Task Indexes (keep minimal version) - Redundant Content (consolidate or remove)

Skip if: MEMORY.md contains only core rules and indexes — even if the file is large.

Phase 2: Create facts/ Directory Structure

Ensure /memory/facts/ exists with these files:

memory/facts/
├── critical-events.md    # Important incidents and lessons
├── projects.md           # Active project statuses
├── technical-setup.md    # DEPRECATED — technical configs now stay in MEMORY.md
├── portfolio.md          # Stocks, investments, strategies
└── user-directives.md    # User preferences and instructions

Note: technical-setup.md is kept for backward compatibility. New technical content goes to MEMORY.md.

Phase 3: Migrate Content

Move factual details from MEMORY.md to appropriate facts/ files:

Source SectionTarget FileMigration Rule
Critical Eventscritical-events.mdMove full details, keep index link
Projectsprojects.mdMove all project details
Technical Setuptechnical-setup.mdKEEP in MEMORY.md — agent capabilities stay; only move niche/deprecated configs if requested
Portfolio/Tradingportfolio.mdMove holdings, strategies
User Directivesuser-directives.mdMove preferences, quotes

Phase 4: Rewrite MEMORY.md

New structure:

# MEMORY.md - Long-Term Memory

_Curated rules and index. Detailed facts stored separately._

---

## Tasks, Plans and Missions

### [Task Name]
**Current Plan**: /memory/YYYY-MM-DD.md

---

## Quick Index (Factual Information)

| Category        | Location                              |
|-----------------|---------------------------------------|
| Critical Events | /memory/facts/critical-events.md      |
| Active Projects | /memory/facts/projects.md             |
| Technical Setup | **MEMORY.md** (agent capabilities)    |
| Portfolio       | /memory/facts/portfolio.md            |
| User Directives | /memory/facts/user-directives.md      |

---

## Core Principles (Immutable)

[Keep only essential rules - max 6-8 items]

---

## Cognitive Memory System

[Minimal reference to architecture]

Phase 5: Verify

Check results:

  • [ ] All facts/ files created with migrated content
  • [ ] No information lost
  • [ ] Quick Index table complete
  • [ ] Core Principles preserved
  • [ ] Factual bloat removed (not line count reduced)

Rollback Mechanism

When to Use Rollback

Activate rollback when:

  • User requests to restore specific categories of information
  • Migration resulted in unintended data loss
  • User wants to revert to previous memory structure

Rollback Workflow

  1. Assessment: Determine which categories need to be restored
  2. Backup Current State: Create backup of current MEMORY.md and facts/ directory
  3. Selective Restoration:

- Specific Category: Copy content from facts/ file back to MEMORY.md - Entire Memory: Restore from backup or rebuild from facts/ files

  1. Update Quick Index: Adjust links based on new structure
  2. Verification: Ensure all content is properly restored

Rollback Scenarios

ScenarioAction
Restore specific categoryCopy content from facts/[category].md back to MEMORY.md
Rollback entire memoryRebuild MEMORY.md from all facts/ files and core rules
Undo recent migrationRestore from pre-migration backup if available

Success Metrics

  • Factual bloat removed — all migrated content is factual, not core rules
  • All factual information preserved in facts/ files
  • Quick Index enables fast navigation between core memory and facts
  • Core rules and capabilities remain intact in MEMORY.md
  • Rollback capability maintained with proper backups
  • User verification completed at key decision points
  • No critical information lost during the process

Critical Safety Metrics:

  • 100% of core behavioral rules remain in MEMORY.md
  • 100% of capability definitions are preserved
  • 100% of tool descriptions remain unchanged
  • 100% of installed skills information is retained

Anti-Goal: Reducing line count is NOT the goal. Removing factual bloat while preserving core capabilities IS.

Template: facts/ Files

critical-events.md

# Critical Events Record

## YYYY-MM-DD: Event Name
- **What happened**: [Description]
- **Root cause**: [Analysis]
- **Lesson**: [Key takeaway]
- **Status**: [Resolved/Ongoing]

projects.md

# Active Project Status

## Project: [Name]
- **Status**: [PENDING/ACTIVE/COMPLETED]
- **User role**: [Role]
- **My role**: [Role]
- **Constraints**: [Any limitations]

technical-setup.md

# Technical Setup & Configuration (ARCHIVE)

> **DEPRECATED**: Technical configurations and installed skills are now kept in MEMORY.md for quick access.
> This file is maintained for historical reference only.

## Archived Content
[Any legacy technical notes from before the migration]

portfolio.md

# Portfolio & Strategies

## Holdings
- **Symbol**: [Ticker]
- **Quantity**: [Number]
- **Purchase price**: [Amount]
- **Current price**: [Amount]
- **Status**: [HOLD/SELL/BUY]

## Strategies
- **Strategy name**: [Name]
- **Description**: [Details]
- **Performance**: [Metrics]

user-directives.md

# User Directives & Preferences

**Last Updated**: YYYY-MM-DD

> "[User quote or directive]"

## Preferences
- [Preference 1]
- [Preference 2]

## Instructions
- [Instruction 1]
- [Instruction 2]

Remember

MEMORY.md is for rules and navigation, not storage.

Factual details belong in specialized files.

Rollback capability is essential — always maintain backups and ensure the ability to restore information when requested.

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

73.19%
按下载量换算1,930

安全审计

VirusTotal

通过

ClawScan

可疑

Static analysis

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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