memory-bank — for Claude Code memory-bank, claude-code-deprecated, community, for Claude Code, ide skills, architecture.md, decisions.md, patterns.md, troubleshooting.md, api-surface.md

v1.0.0

이 스킬 정보

적합한 상황: Ideal for AI agents that need skill: memory bank — structured project knowledge sync. 현지화된 요약: Acts as a long-term knowledge layer that survives context compaction and session resets. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

기능

Skill: Memory Bank — Structured Project Knowledge Sync
Build and maintain a structured memory bank at .claude/memory/ that stays
synchronized with code changes. Acts as a long-term knowledge layer that survives
context compaction and session resets.
Inspired by russbeye/claude-memory-bank.

# 핵심 주제

Wellux Wellux
[1]
[0]
업데이트: 4/6/2026

Skill Overview

Start with fit, limitations, and setup before diving into the repository.

적합한 상황: Ideal for AI agents that need skill: memory bank — structured project knowledge sync. 현지화된 요약: Acts as a long-term knowledge layer that survives context compaction and session resets. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

이 스킬을 사용하는 이유

추천 설명: memory-bank helps agents skill: memory bank — structured project knowledge sync. Acts as a long-term knowledge layer that survives context compaction and session resets. This AI agent skill supports Claude Code

최적의 용도

적합한 상황: Ideal for AI agents that need skill: memory bank — structured project knowledge sync.

실행 가능한 사용 사례 for memory-bank

사용 사례: Applying Skill: Memory Bank — Structured Project Knowledge Sync
사용 사례: Applying Build and maintain a structured memory bank at .claude/memory/ that stays
사용 사례: Applying synchronized with code changes. Acts as a long-term knowledge layer that survives

! 보안 및 제한 사항

  • 제한 사항: Use /context-diff first to understand what changed, then update only the relevant warm-tier files.
  • 제한 사항: Requires repository-specific context from the skill documentation
  • 제한 사항: Works best when the underlying tools and dependencies are already configured

About The Source

The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Labs 데모

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ 및 설치 단계

These questions and steps mirror the structured data on this page for better search understanding.

? 자주 묻는 질문

memory-bank은 무엇인가요?

적합한 상황: Ideal for AI agents that need skill: memory bank — structured project knowledge sync. 현지화된 요약: Acts as a long-term knowledge layer that survives context compaction and session resets. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

memory-bank은 어떻게 설치하나요?

다음 명령을 실행하세요: npx killer-skills add Wellux/claude-code-deprecated. Cursor, Windsurf, VS Code, Claude Code와 19개 이상의 다른 IDE에서 동작합니다.

memory-bank은 어디에 쓰이나요?

주요 활용 사례는 다음과 같습니다: 사용 사례: Applying Skill: Memory Bank — Structured Project Knowledge Sync, 사용 사례: Applying Build and maintain a structured memory bank at .claude/memory/ that stays, 사용 사례: Applying synchronized with code changes. Acts as a long-term knowledge layer that survives.

memory-bank 와 호환되는 IDE는 무엇인가요?

이 스킬은 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer 와 호환됩니다. 통합 설치에는 Killer-Skills CLI를 사용하세요.

memory-bank에 제한 사항이 있나요?

제한 사항: Use /context-diff first to understand what changed, then update only the relevant warm-tier files.. 제한 사항: Requires repository-specific context from the skill documentation. 제한 사항: Works best when the underlying tools and dependencies are already configured.

이 스킬 설치 방법

  1. 1. 터미널 열기

    프로젝트 디렉터리에서 터미널 또는 명령줄을 여세요.

  2. 2. 설치 명령 실행

    npx killer-skills add Wellux/claude-code-deprecated 를 실행하세요. CLI가 IDE 또는 에이전트를 자동으로 감지하고 스킬을 설정합니다.

  3. 3. 스킬 사용 시작

    스킬이 이제 활성화되었습니다. 현재 프로젝트에서 memory-bank을 바로 사용할 수 있습니다.

! Source Notes

This page is still useful for installation and source reference. Before using it, compare the fit, limitations, and upstream repository notes above.

Upstream Repository Material

The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Upstream Source

memory-bank

Acts as a long-term knowledge layer that survives context compaction and session resets. This AI agent skill supports Claude Code, Cursor, and Windsurf

SKILL.md
Readonly
Upstream Repository Material
The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.
Upstream Source

Skill: Memory Bank — Structured Project Knowledge Sync

Role

Build and maintain a structured memory bank at .claude/memory/ that stays synchronized with code changes. Acts as a long-term knowledge layer that survives context compaction and session resets. Inspired by russbeye/claude-memory-bank.

Memory Bank Structure

.claude/memory/
├── hot/
│   └── hot-memory.md          # Always loaded (≤50 lines, key active context)
├── warm/
│   ├── architecture.md        # System design, component relationships
│   ├── decisions.md           # Key decisions with rationale
│   ├── patterns.md            # Recurring code patterns, idioms
│   ├── troubleshooting.md     # Known issues, workarounds, gotchas
│   └── api-surface.md         # Public API contracts and conventions
└── glacier/
    └── YYYY-MM-DD-<slug>.md   # Archived decisions + historical context

When to invoke

  • After a major refactor (sync architecture.md)
  • After resolving a tricky bug (sync troubleshooting.md)
  • After adding a new API endpoint (sync api-surface.md)
  • After making an architectural decision (sync decisions.md)
  • Periodically to keep memory current

Instructions

Full sync

  1. Read all source files in scope (or all of src/ for full sync)
  2. Compare against existing warm-tier files
  3. Update each warm-tier file with what's changed:
    • architecture.md: component diagram, module responsibilities, data flow
    • decisions.md: key choices with WHY, not just what
    • patterns.md: recurring idioms, anti-patterns seen
    • troubleshooting.md: tricky bugs, gotchas, workarounds
    • api-surface.md: endpoint signatures, request/response models
  4. Update hot-memory.md with any critical new facts (keep ≤50 lines)
  5. Archive stale but important context to glacier

After a specific change

Use /context-diff first to understand what changed, then update only the relevant warm-tier files.

Query mode

/memory-bank query "src/auth/**" — surface relevant warm-tier documentation for a path

Path-Filtered Query

When given a path argument:

  1. Identify which warm-tier file covers that domain
  2. Return the relevant section
  3. Note if it's stale (last updated >2 weeks ago)

Output

## Memory Bank Sync: <scope>

### Updated
- warm/architecture.md → added FastAPI middleware order diagram
- warm/decisions.md → logged setuptools.build_meta decision
- warm/troubleshooting.md → added exc_info filtering gotcha

### Hot memory: updated active_feature key

### No changes needed
- warm/api-surface.md (current)
- warm/patterns.md (current)

### Archived to glacier
- Old routing design (pre-v0.9.0) → glacier/2026-04-05-routing-v1.md

관련 스킬

Looking for an alternative to memory-bank or another community skill for your workflow? Explore these related open-source skills.

모두 보기

openclaw-release-maintainer

Logo of openclaw
openclaw

현지화된 요약: 🦞 # OpenClaw Release Maintainer Use this skill for release and publish-time workflow. It covers ai, assistant, crustacean workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

333.8k
0
인공지능

widget-generator

Logo of f
f

현지화된 요약: Generate customizable widget plugins for the prompts.chat feed system # Widget Generator Skill This skill guides creation of widget plugins for prompts.chat . It covers ai, artificial-intelligence, awesome-list workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf

149.6k
0
인공지능

flags

Logo of vercel
vercel

현지화된 요약: The React Framework # Feature Flags Use this skill when adding or changing framework feature flags in Next.js internals. It covers blog, browser, compiler workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

138.4k
0
브라우저

pr-review

Logo of pytorch
pytorch

현지화된 요약: Usage Modes No Argument If the user invokes /pr-review with no arguments, do not perform a review . It covers autograd, deep-learning, gpu workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

98.6k
0
개발자