← 返回 Skills 市场

Claude Code Memory Kit

Name: Claude Code Memory Kit
Author: abhinas90

作者 abhinas90 · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ 安全检测通过

157

总下载

当前安装

版本数

在 OpenClaw 中安装

/install claude-code-memory-kit

功能描述

Stop Claude Code from repeating mistakes — enforce guardrails, preserve context, maintain consistency across sessions

使用说明 (SKILL.md)

Claude Code Memory Kit — Stop Repeating Mistakes

Tagline

Go from "correcting the same error 10 times" to "zero-repeat mistakes" in one afternoon.

Problem

Claude Code users hit the same wall every day:

Mistakes repeat across sessions (force pushes, untested edits, style violations)
CLAUDE.md isn't enough — preferences ≠ enforcement
Memory leaks — context gets lost between sessions
No guardrails for high-risk actions
Corrections don't stick — you're teaching the same lesson daily

Solution

A structured memory system that enforces rules, preserves context, and prevents repeat mistakes.

What's Inside

1. Memory Architecture Template

CLAUDE.md — project rules & preferences (template)
memory.md — learned patterns & recurring decisions (template)
mistakes.md — mistakes to avoid (auto-promoted from corrections) (template)
bootstrap.md — session initialization context (template)

2. Pre-Tool Gates

Block force-push to main
Require tests before edits in specific repos
Confirm destructive commands
Validate code style before commit

3. Cross-Session Persistence

Structured context bootstrapping (no chat history dumping)
Mistake → rule automation (3 corrections = new policy)
Project-specific memory that actually sticks

4. Real-World Templates

JavaScript/TypeScript project setup
Python data science workflow
Multi-repo coordination
Team coding standards enforcement

5. Installation & Troubleshooting

INSTALL.md — Step-by-step setup guide
TROUBLESHOOTING.md — Common issues and solutions
Pre-tool gate configurations
Team deployment guide

Who This Is For

Developers using Claude Code full-time (6+ months experience)
Teams needing consistent code style across members
Anyone tired of repeating the same corrections
Projects with safety/security requirements

What You'll Achieve

Zero-repeat mistakes within 48 hours
80% reduction in manual corrections
Consistent code quality across sessions
Auditable decision trails for team reviews

Price & Value

Launch price: $99 (regular $149)
Comparable value: Saves 10+ hours/month of correction time
ROI: 1-2 days for full investment recovery

Quick Start

Install the templates
Configure project-specific rules
Set up pre-tool gates for high-risk actions
Start tracking corrections → auto-promote to rules
Enjoy consistent, reliable Claude Code sessions

Based on analysis of 7 high-priority leads where memory/reliability was the #1 pain point (score 9/10).

安全使用建议

This is a documentation-and-template package, not executable code — that lowers risk. Before installing or committing the templates: 1) Review the templates (CLAUDE.md, memory.md, mistakes.md, bootstrap.md) for any hardcoded secrets, API keys, or DB credentials and never commit secrets to the repository. 2) When following INSTALL.md and TROUBLESHOOTING.md, avoid blindly running global installs from unknown packages and avoid using --unsafe-perm unless you understand the implications. 3) The kit suggests adding preToolGates and permission entries to ~/.claude/settings.json — check what those settings do in your Claude Code client and confirm you’re comfortable granting the listed permissions. 4) Test the guardrails in a safe environment (non-production repo) to ensure they behave as expected. Overall the package appears consistent with its stated purpose, but practice standard review and secret-management hygiene before deploying team-wide.

功能分析

Type: OpenClaw Skill Name: claude-code-memory-kit Version: 1.0.0 The Claude Code Memory Kit is a collection of Markdown templates and configuration guides designed to improve the reliability and safety of AI coding sessions. It provides structured templates (CLAUDE.md, memory.md, mistakes.md) to help the agent follow project rules and avoid repeating errors. The instructions actually promote security best practices, such as recommending the use of 'preToolGates' in settings.json to require manual confirmation for destructive commands like 'rm -rf' or 'git push --force'. No malicious code, data exfiltration, or harmful prompt injections were identified.

能力评估

✓ Purpose & Capability

The name/description (prevent repeat mistakes, enforce guardrails) matches the actual contents: templates (CLAUDE.md, memory.md, mistakes.md, bootstrap.md), installation guidance, and guardrail configuration suggestions. There are no unexpected binaries, credentials, or network dependencies declared.

ℹ Instruction Scope

SKILL.md, INSTALL.md, and templates only instruct the agent/user to copy template files, configure ~/.claude/settings.json, run the 'claude' CLI, and keep small memory files. That is within scope. Two items to be aware of: (1) bootstrap.md mentions 'Database: [connection details if needed]' and 'API endpoints: [base URLs]' — these are placeholders but could encourage storing sensitive connection strings in project or bootstrap files if users are not careful; (2) TROUBLESHOOTING.md suggests settings like {"permissions":{"allow":["Read"]}} and gives an npm global install example with --unsafe-perm=true — these are benign guidance in context but should be handled cautiously. Overall the instructions do not read or exfiltrate data and do not reference unexpected external endpoints.

✓ Install Mechanism

No install spec and no code files that will be executed. This is instruction-only (templates and docs) so nothing will be downloaded or written by an installer. Low install risk.

✓ Credentials

The skill declares no required env vars, no credentials, and no config paths beyond recommending user-managed locations (project root files and optional ~/.claude/settings.json). The requested scope is proportional to the stated functionality.

✓ Persistence & Privilege

The skill is not always-enabled and does not request elevated platform privileges. It suggests local configuration of Claude Code (per-user config and project files) which is appropriate for persistent behavior. Nothing indicates modification of other skills or system-wide settings beyond the user-editable Claude config.

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 claude-code-memory-kit
安装完成后，直接呼叫该 Skill 的名称或使用 /claude-code-memory-kit 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

元数据

Slug claude-code-memory-kit

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