Memory Bank
- 1 installs
- 404 repo stars
- Updated August 5, 2026
- aiskillstore/marketplace
memory-bank is a Claude Code skill that maintains a folder of structured Markdown files to preserve project context across sessions.
About
memory-bank is a Claude Code skill that keeps a structured set of Markdown files in a memory-bank/ folder so project context survives between sessions. A developer uses it to record project brief, product context, architecture patterns, tech stack, and progress, then reads them at the start of each task. It includes templates for all six core files.
- Maintains a memory-bank/ folder of Markdown files to persist project context across sessions
- Defines six core files: projectbrief, productContext, activeContext, systemPatterns, techContext, progress
- Read all files at session start; update activeContext and progress on 'update memory bank'
Memory Bank by the numbers
- 1 all-time installs (skills.sh)
- Ranked #1,366 of 1,879 Documentation skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
memory-bank capabilities & compatibility
- Capabilities
- context persistence · project documentation · progress tracking
- Use cases
- documentation · memory · planning
- Pricing
- Free
What memory-bank says it does
Persistent project documentation system that maintains context across sessions. Creates structured Memory Bank files to preserve project knowledge, decisions, and progress.
I MUST read ALL memory bank files at the start of EVERY task - this is not optional.
npx skills add https://github.com/aiskillstore/marketplace --skill memory-bankAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 1 |
|---|---|
| repo stars | ★ 404 |
| Last updated | August 5, 2026 |
| Repository | aiskillstore/marketplace ↗ |
What it does
Persist project context, decisions, and progress in structured Markdown across Claude Code sessions.
Who is it for?
Developers who want an agent to retain project knowledge and progress between sessions.
Skip if: Storing secrets or transient experiments; it is a documentation system, not a secret store.
When should I use this skill?
You want persistent, structured project documentation that survives context resets.
What you get
A maintained memory-bank/ folder of Markdown files capturing scope, architecture, and progress.
- memory-bank/ folder
- Six core Markdown context files
- Project progress log
By the numbers
- 6 required core Markdown files
- Files build in a defined hierarchy from projectbrief.md down to progress.md
Files
Memory Bank
I am Claude Code, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read ALL memory bank files at the start of EVERY task - this is not optional.
Memory Bank Structure
The Memory Bank consists of required core files and optional context files, all in Markdown format. Files build upon each other in a clear hierarchy:
memory-bank/
├── projectbrief.md # Foundation - core requirements and goals
├── productContext.md # Why this exists, problems it solves
├── activeContext.md # Current focus, recent changes, next steps
├── systemPatterns.md # Architecture, patterns, decisions
├── techContext.md # Tech stack, setup, constraints
└── progress.md # Status, what works, what's leftFile Hierarchy
projectbrief.md
├── productContext.md
├── systemPatterns.md
└── techContext.md
└── activeContext.md
└── progress.mdCore Files (Required)
1. projectbrief.md
- Foundation document that shapes all other files
- Created at project start if it doesn't exist
- Defines core requirements and goals
- Source of truth for project scope
2. productContext.md
- Why this project exists
- Problems it solves
- How it should work
- User experience goals
3. activeContext.md
- Current work focus
- Recent changes
- Next steps
- Active decisions and considerations
4. systemPatterns.md
- System architecture
- Key technical decisions
- Design patterns in use
- Component relationships
5. techContext.md
- Technologies used
- Development setup
- Technical constraints
- Dependencies
6. progress.md
- What works
- What's left to build
- Current status
- Known issues
Additional Context
Create additional files/folders within memory-bank/ when they help organize:
- Complex feature documentation
- Integration specifications
- API documentation
- Testing strategies
- Deployment procedures
Core Workflows
Starting a Session
1. Read ALL memory bank files in order:
- projectbrief.md (foundation)
- productContext.md (why)
- techContext.md (how)
- systemPatterns.md (architecture)
- activeContext.md (current state)
- progress.md (status)
2. Verify context is complete 3. Identify current work focus from activeContext.md 4. Continue from where we left off
During Work
1. Keep activeContext.md updated with current focus 2. Document significant decisions in systemPatterns.md 3. Update progress.md after completing features 4. Add new patterns or constraints to relevant files
Ending a Session
1. Update activeContext.md with:
- What was accomplished
- Current state of work
- Immediate next steps
- Any blockers or considerations
2. Update progress.md with:
- New completed items
- Changed status of in-progress items
- New known issues
Documentation Updates
Memory Bank updates occur when: 1. Discovering new project patterns 2. After implementing significant changes 3. When user requests with update memory bank (MUST review ALL files) 4. When context needs clarification
When triggered by update memory bank, I MUST review every memory bank file, even if some don't require updates. Focus particularly on activeContext.md and progress.md as they track current state.
Initializing Memory Bank
When starting a new project or if memory-bank/ doesn't exist:
mkdir -p memory-bankCreate projectbrief.md first by asking the user:
- What is this project?
- What are the core requirements?
- What are the main goals?
Then create remaining files based on discovered context.
File Templates
projectbrief.md
# Project Brief
## Overview
[One paragraph describing what this project is]
## Core Requirements
- [Requirement 1]
- [Requirement 2]
## Goals
- [Goal 1]
- [Goal 2]
## Scope
### In Scope
- [Item]
### Out of Scope
- [Item]productContext.md
# Product Context
## Problem Statement
[What problem does this solve?]
## Solution
[How does this project solve it?]
## User Experience
[How should users interact with this?]
## Success Criteria
- [Criteria 1]
- [Criteria 2]activeContext.md
# Active Context
## Current Focus
[What we're working on right now]
## Recent Changes
- [Change 1]
- [Change 2]
## Next Steps
1. [Step 1]
2. [Step 2]
## Active Decisions
- [Decision being considered]
## Blockers
- [Any blockers]systemPatterns.md
# System Patterns
## Architecture
[High-level architecture description]
## Key Patterns
### [Pattern Name]
- Purpose: [Why this pattern]
- Implementation: [How it's implemented]
## Component Relationships
[How components interact]
## Design Decisions
| Decision | Rationale | Date |
|----------|-----------|------|
| [Decision] | [Why] | [When] |techContext.md
# Tech Context
## Stack
- [Technology]: [Purpose]
## Development SetupSetup commands
## Dependencies
- [Dependency]: [Version] - [Purpose]
## Constraints
- [Constraint 1]
## Environment
- [Environment variable]: [Purpose]progress.md
# Progress
## Completed
- [x] [Feature/Task]
## In Progress
- [ ] [Feature/Task] - [Status]
## Planned
- [ ] [Feature/Task]
## Known Issues
- [Issue 1]
## Metrics
- [Metric]: [Value]Best Practices
1. Be Concise - Memory bank files should be scannable 2. Be Current - Update after significant changes 3. Be Accurate - Don't let documentation drift from reality 4. Be Complete - Include enough context to resume work 5. Be Structured - Use consistent formatting
REMEMBER
After every memory reset, I begin completely fresh. The Memory Bank is my only link to previous work. It must be maintained with precision and clarity, as my effectiveness depends entirely on its accuracy.
{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-01-16T12:15:39.073Z",
"slug": "0xkynz-memory-bank",
"source_url": "https://github.com/0xkynz/codekit/tree/main/templates/skills/memory-bank",
"source_ref": "main",
"model": "claude",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "86ba837f83b8a111d09042a2c71986b58c1fa74d558c95ccf0a44d4b6589efcc",
"tree_hash": "d162000aadd7ce3236ea0bc2b541ed603995d71b350e7dee4d6429f6920300b7"
},
"skill": {
"name": "memory-bank",
"description": "Persistent project documentation system that maintains context across sessions. Creates structured Memory Bank files to preserve project knowledge, decisions, and progress.",
"summary": "Persistent project documentation system that maintains context across sessions. Creates structured M...",
"icon": "📚",
"version": "1.0.0",
"author": "0xkynz",
"license": "MIT",
"category": "documentation",
"tags": [
"memory",
"context",
"documentation",
"project-management",
"persistence"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"network",
"external_commands"
]
},
"security_audit": {
"risk_level": "safe",
"is_blocked": false,
"safe_to_publish": true,
"summary": "Pure prompt-based documentation skill. Contains only markdown templates and instruction prompts. No executable code, file I/O operations, network calls, or system command execution. All static findings are false positives from scanner misinterpreting documentation patterns.",
"risk_factor_evidence": [
{
"factor": "network",
"evidence": [
{
"file": "skill-report.json",
"line_start": 6,
"line_end": 6
}
]
},
{
"factor": "external_commands",
"evidence": [
{
"file": "SKILL.md",
"line_start": 15,
"line_end": 23
},
{
"file": "SKILL.md",
"line_start": 23,
"line_end": 27
},
{
"file": "SKILL.md",
"line_start": 27,
"line_end": 34
},
{
"file": "SKILL.md",
"line_start": 34,
"line_end": 133
},
{
"file": "SKILL.md",
"line_start": 133,
"line_end": 135
},
{
"file": "SKILL.md",
"line_start": 135,
"line_end": 147
},
{
"file": "SKILL.md",
"line_start": 147,
"line_end": 167
},
{
"file": "SKILL.md",
"line_start": 167,
"line_end": 170
},
{
"file": "SKILL.md",
"line_start": 170,
"line_end": 185
},
{
"file": "SKILL.md",
"line_start": 185,
"line_end": 188
},
{
"file": "SKILL.md",
"line_start": 188,
"line_end": 207
},
{
"file": "SKILL.md",
"line_start": 207,
"line_end": 210
},
{
"file": "SKILL.md",
"line_start": 210,
"line_end": 228
},
{
"file": "SKILL.md",
"line_start": 228,
"line_end": 231
},
{
"file": "SKILL.md",
"line_start": 231,
"line_end": 238
},
{
"file": "SKILL.md",
"line_start": 238,
"line_end": 240
},
{
"file": "SKILL.md",
"line_start": 240,
"line_end": 250
},
{
"file": "SKILL.md",
"line_start": 250,
"line_end": 253
},
{
"file": "SKILL.md",
"line_start": 253,
"line_end": 270
}
]
}
],
"critical_findings": [],
"high_findings": [],
"medium_findings": [],
"low_findings": [],
"dangerous_patterns": [],
"files_scanned": 2,
"total_lines": 461,
"audit_model": "claude",
"audited_at": "2026-01-16T12:15:39.073Z"
},
"content": {
"user_title": "Maintain project context across sessions",
"value_statement": "Claude loses context between sessions. Memory Bank creates structured documentation that preserves project knowledge, decisions, and progress so you never lose your place.",
"seo_keywords": [
"memory bank",
"Claude Code",
"Claude",
"project documentation",
"context preservation",
"persistent context",
"project memory",
"Codex",
"Claude Code documentation",
"session persistence"
],
"actual_capabilities": [
"Creates 6 structured Memory Bank files for project documentation",
"Updates activeContext.md and progress.md during sessions",
"Maintains file hierarchy from projectbrief.md to progress.md",
"Provides templates for all documentation files",
"Reads all Memory Bank files at session start",
"Documents technical decisions and system patterns"
],
"limitations": [
"Does not auto-detect project structure or requirements",
"Requires user to provide initial project information",
"Does not integrate with external documentation tools",
"Memory Bank exists only in local memory-bank directory"
],
"use_cases": [
{
"target_user": "Software Developers",
"title": "Resume interrupted work",
"description": "Pick up exactly where you left off in complex projects across sessions without re-explaining context."
},
{
"target_user": "Technical Leads",
"title": "Document architectural decisions",
"description": "Record why technical decisions were made so future team members understand the reasoning."
},
{
"target_user": "Team Collaborators",
"title": "Knowledge transfer",
"description": "Share complete project context with new team members or between different AI assistants."
}
],
"prompt_templates": [
{
"title": "Initialize Memory Bank",
"scenario": "Start a new project",
"prompt": "Start a new memory bank for this project."
},
{
"title": "Update Progress",
"scenario": "Complete a task",
"prompt": "Update memory bank. I completed the user authentication module."
},
{
"title": "Check Status",
"scenario": "Review project state",
"prompt": "What is the current state of the project from the memory bank?"
},
{
"title": "Full Documentation Review",
"scenario": "Synchronize context",
"prompt": "Update memory bank with all changes from this session."
}
],
"output_examples": [
{
"input": "Start a new memory bank for my React e-commerce project",
"output": [
"Created memory-bank/projectbrief.md - Please provide: project description, core requirements, main goals",
"Created memory-bank/productContext.md - Please describe the problem and your solution",
"Created memory-bank/techContext.md - Stack, setup, dependencies",
"Created memory-bank/systemPatterns.md - Architecture and patterns",
"Created memory-bank/activeContext.md - Current focus",
"Created memory-bank/progress.md - Tracking status"
]
},
{
"input": "Update memory bank. I fixed the login bug and added user profile settings.",
"output": [
"Updated activeContext.md - Added completed task: login bug fix, added in-progress: user profile settings",
"Updated progress.md - Marked login bug as completed, added user profile settings to in-progress"
]
},
{
"input": "What is the current state of the project?",
"output": [
"Project: React e-commerce application",
"Current focus: User profile settings implementation",
"Recent: Fixed login bug, completed user authentication module",
"Next: Complete user profile settings, then work on checkout flow",
"Status: 3 of 8 features completed, 2 in progress"
]
}
],
"best_practices": [
"Keep files scannable with clear headers and bullet points",
"Update activeContext.md and progress.md at the end of every session",
"Include just enough context to resume work without overwhelming detail"
],
"anti_patterns": [
"Treating Memory Bank as a to-do list instead of context documentation",
"Letting documentation drift from actual implementation state",
"Including implementation details that belong in code comments instead"
],
"faq": [
{
"question": "What is Memory Bank?",
"answer": "Memory Bank is a documentation system that preserves project context across Claude sessions using six structured markdown files."
},
{
"question": "Does this work with all Claude products?",
"answer": "Yes, Memory Bank works with Claude, Codex, and Claude Code. Files are stored locally in your project."
},
{
"question": "How do I share context with my team?",
"answer": "Commit the memory-bank folder to version control. Team members can read the files to understand project context."
},
{
"question": "What happens to my data?",
"answer": "All Memory Bank files are stored locally in your project directory. No data is sent to external servers."
},
{
"question": "Can I use this with other AI assistants?",
"answer": "Yes, Memory Bank uses plain markdown files. Any AI or human can read and understand the documentation."
},
{
"question": "How is this different from regular documentation?",
"answer": "Memory Bank is specifically designed for Claude's session structure with mandatory read order and update workflows."
}
]
},
"file_structure": [
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 283
}
]
}
Related skills
Lark MarkdownInstantly turn any markdown file into clean, formatted Lark/Figma-compatible documents without manual reformatting.488k
Lark DocCreate, read, update, summarize, rewrite and manage Feishu/Lark cloud documents directly from agent workflows.401k16.1kLark WikiCreate, organize, query, and manage documents, spaces, and members inside Lark (Feishu) knowledge bases directly from AI agent workflows.397k16.1k
Domain ModelingBuild and sharpen a project's domain model: pin down domain terminology in a glossary and record architectural decisions as ADRs.318k202k
Opensource Guide CoachGet expert, attribution-safe guidance on launching and sustaining an open-source project.270k71Readme I18nMaintain consistent, updatable language selector blocks across every README variant in a multilingual repository.270k71FAQ
What files does memory-bank create?
Six core Markdown files: projectbrief.md, productContext.md, activeContext.md, systemPatterns.md, techContext.md, and progress.md, plus optional context files.
When are the files updated?
On discovering new patterns, after significant changes, and when the user says 'update memory bank', which triggers a review of all files.