← 返回 Skills 市场

Double-Check-It Skill (再想想技能1.0)

Name: Double-Check-It Skill (再想想技能1.0)
Author: webray1983

作者 webray1983 · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ 安全检测通过

204

总下载

当前安装

版本数

在 OpenClaw 中安装

/install double-check-it

功能描述

自动记录交互信息，交付前复核任务与需求一致性，闲时回顾总结经验，确保长期记忆准确完整。

使用说明 (SKILL.md)

再想想 (Recall and Double Check)

概述

本技能帮助Agent建立长期记忆系统，支持自动记录、交付复核、主动回顾三大功能。

记忆文件系统

memory/                    # 记忆存储根目录
├── 日记/                  # 每日自动记录
│   └── YYYY-MM-DD.md
├── 文档/                  # 事实、方案
│   └── 股票/
└── 经验/                  # 经验总结

MEMORY.md 保持精简，只存规则/技术/永久性信息，其他以索引指向 memory/

功能1: 记住 (Auto-Memory)

触发时机

每次用户交互结束
执行动作完成后

记录规则

类型	记录方式	示例
普通信息	简洁总结	"用户要求检查已安装技能"
重要信息	详细记录	用户需求、方案、定时任务创建

执行命令

# 记录普通信息
./scripts/memory.sh record "对话摘要" --type normal

# 记录重要信息
./scripts/memory.sh record "详细记录..." --type important --tags "需求,股票"

功能2: 再想想 (Double Check)

触发时机

自动触发: 每次交付前
手动触发: 用户说"再想想"/"double check"/"dc it"

执行流程

调取相关记忆（memory/日记/ + memory/文档/）
对比本次任务与用户需求
判断是否符合要求
如不符合，自行寻找原因并修正

执行命令

# 触发复核
./scripts/memory.sh check "本次任务描述" "用户原始需求"

功能3: 主动回顾 (Idle Reflection)

触发时机

心跳空闲时（每5-10次随机触发）

执行流程

随机选取历史记忆
筛选高价值记忆（用户纠正/反馈、重大决策、错误修复）
提炼经验教训 → 写入 memory/经验/
更新索引

执行命令

# 触发回顾
./scripts/memory.sh reflect

索引系统

索引文件: memory/index.json

{
  "files": [
    {"path": "日记/2026-03-14.md", "keywords": ["技能清理"], "summary": "删除60+未使用技能"},
    {"path": "文档/股票/持仓.md", "keywords": ["中际旭创", "阳光电源"], "summary": "股票持仓信息"}
  ]
}

使用示例

场景1: 用户要求安装技能

执行安装操作
调用 memory.sh record "安装了skill-creator技能" --type important
交付完成

场景2: 用户说"再想想"

调用 memory.sh check "刚才安装了skill-creator" "用户要求安装skill-creator"
如有不符，自行修正
重新交付

场景3: 交付前自检

完成任务后
自动调用 memory.sh check 复核
确保符合需求后再交付

安全使用建议

This skill does what it says: it persistently records conversation summaries, performs pre‑delivery checks, and writes experience notes to files in the agent workspace. Before installing, consider: (1) Privacy — every recorded interaction will be stored long‑term (including sensitive info like credentials or financial data you might discuss); (2) Storage location — the script writes to /home/minimax/.openclaw/workspace/memory (hardcoded); change this path if you want a different location or permissions; (3) Access controls — ensure the workspace and backups are properly protected/encrypted and rotated or purged per your retention policy; (4) Autonomy — the agent can be configured to call these commands automatically, so decide whether you want automatic recording/auto checks or prefer manual triggers; (5) Audit the script if you plan to store highly sensitive data (it has simple file I/O and grep usage only). If any of these are unacceptable, do not install or modify the script to restrict what is recorded and where.

功能分析

Type: OpenClaw Skill Name: double-check-it Version: 1.0.0 The skill implements a local long-term memory system for the agent to record, review, and reflect on user interactions. It uses a bash script (scripts/memory.sh) to manage markdown files and a JSON index within the agent's workspace, with no evidence of data exfiltration, remote execution, or unauthorized system access.

能力评估

✓ Purpose & Capability

Name/description (long‑term memory, double‑check, reflection) align with the provided script and SKILL.md: the skill persists conversation summaries, runs checks, and performs periodic reflections. Required binaries/env/credentials are none, which is appropriate for a local file‑based memory system.

ℹ Instruction Scope

SKILL.md instructs the agent to record after interactions, run pre‑delivery checks, and periodically reflect; the included scripts implement those behaviors by reading/writing files under a workspace memory directory. This stays within the skill's stated scope, but it is broad in data collection: it records conversation content persistently and will search those files when checking/reflecting, which has privacy implications.

✓ Install Mechanism

No install spec or external downloads. The skill is instruction‑only with an included shell script; nothing is fetched from the network or written to arbitrary system paths during install.

✓ Credentials

The skill requests no environment variables or credentials. The script uses filesystem access only (a hardcoded workspace path). There are no secrets requested or network endpoints involved.

ℹ Persistence & Privilege

always:false (normal). The script persistently stores memory under /home/minimax/.openclaw/workspace/memory, so it gains durable presence in the agent workspace. It does not modify other skills or system settings, but persistent storage of all interactions increases exposure of sensitive data if the workspace is accessible to others.

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 double-check-it
安装完成后，直接呼叫该 Skill 的名称或使用 /double-check-it 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

v1.0.0

Initial release: introduces a long-term memory and self-review system for agents. Have you ever been shocked by an agent's stupidity? You asked for A, but they delivered B, and innocently said, "That's exactly what you arranged." And when you ask for evidence, they say they don't remember. This skill solves that problem. It makes the agent actively remember every conversation you have, proactively compare your original requirements when generating deliverables, and enter a three-round self-correction loop to ensure deliverables match requirements. And when you use the powerful Force to type "DC it", the agent will know something is wrong, carefully search its memory, find where it went wrong, and firmly record it in experience. - Adds auto-memory to record daily interactions, user needs, and important events. - Implements "double check" feature for pre-delivery and on-demand task review. - Enables idle reflection for periodic review and experience summarization. - Organizes memory with a structured directory and indexing for efficient recall. - Provides command line scripts for all major functions.

元数据

Slug double-check-it

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题