Agent skill
memory-management
Install this agent skill to your Project
npx add-skill https://github.com/duc01226/EasyPlatform/tree/main/.claude/skills/memory-management
SKILL.md
[IMPORTANT] Use
TaskCreateto break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ask user whether to skip.
Quick Summary
Goal: Persist patterns, decisions, and task progress across sessions using two complementary memory systems.
Workflow:
- File Checkpoints — Save task-specific context to
plans/reports/checkpoint-*.mdevery 30-60 min - MCP Memory Graph — Store reusable knowledge (patterns, decisions, bug fixes) as typed entities with relations
- Recovery — On context loss, find latest checkpoint via Glob, read it, resume from documented next steps
Key Rules:
- Use file checkpoints for task-specific progress; MCP memory for cross-session knowledge
- Create checkpoints before expected context compaction and at key milestones
- Always include Recovery Instructions in checkpoint files
Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).
Memory Management & Knowledge Persistence
Build and maintain a knowledge graph of patterns, decisions, and learnings across sessions. Also provides external file-based checkpoints for long-running tasks.
Two Memory Systems
| System | Storage | Use Case | Persistence |
|---|---|---|---|
| MCP Memory Graph | In-memory graph database | Patterns, decisions, learnings | Cross-session |
| File Checkpoints | plans/reports/*.md |
Task progress, analysis | Permanent files |
Use MCP Memory for reusable knowledge. Use File Checkpoints for task-specific context.
Part 1: File-Based External Memory (Checkpoints)
When to Create File Checkpoints
- Starting complex multi-step tasks (investigation, planning, implementation)
- Every 30-60 minutes during long tasks
- At key milestones
- Before expected context compaction
- After completing significant analysis phases
Checkpoint File Location
Files saved to: plans/reports/checkpoint-{timestamp}-{slug}.md
CHECKPOINT_CREATE Protocol
Create a checkpoint file with this structure:
# Memory Checkpoint: {Task Description}
> Created: {ISO timestamp}
> Task Type: {investigation|planning|bugfix|feature|docs}
> Phase: {current phase number/name}
## Task Context
{What you're working on and why}
## Key Findings
{Critical discoveries and insights - be specific with file paths and line numbers}
## Files Analyzed
| File | Purpose | Status |
| ----------------- | ----------- | -------- |
| path/file.cs:line | description | ✅/🔄/⏳ |
## Progress
- [x] Completed items
- [ ] In-progress items
- [ ] Remaining items
## Important Context
{Information that must be preserved - decisions, assumptions, rationale}
## Next Steps
1. {Immediate next action}
2. {Following action}
## Recovery Instructions
{Exact steps to resume: which file to read, which line to continue from}
CHECKPOINT_RECOVER Protocol
When recovering from a checkpoint:
- Search for latest checkpoint:
Glob("plans/reports/checkpoint-*.md") - Read the checkpoint file
- Load any referenced analysis files
- Review Progress section
- Continue from documented Next Steps
- Create new checkpoint after resuming
Auto-Checkpoint (PreCompact Hook)
The system automatically creates checkpoints before context compaction. These auto-checkpoints are minimal - for better context preservation, create manual checkpoints using /checkpoint.
Part 2: MCP Memory Graph (Knowledge Persistence)
Memory Entity Types
| Entity Type | Purpose | Examples |
|---|---|---|
Pattern |
Recurring code patterns | CQRS, Validation, Repository |
Decision |
Architectural/design decisions | Why we chose X over Y |
BugFix |
Bug solutions for future reference | Race condition fixes |
ServiceBoundary |
Service ownership and responsibilities | Growth owns Employees |
SessionSummary |
End-of-session progress snapshots | Task progress, next steps |
Dependency |
Cross-service dependencies | Growth depends on Accounts |
AntiPattern |
Patterns to avoid | Don't call side effects in cmd |
Memory Operations
Create New Entity
mcp__memory__create_entities([
{
name: 'EmployeeValidationPattern',
entityType: 'Pattern',
observations: [
'Use project validation fluent API (see docs/project-reference/backend-patterns-reference.md)',
'Chain with .And() and .AndAsync()',
"Return validation result, don't throw",
'Location: {Service}.Application/UseCaseCommands/'
]
}
]);
Create Relationships
mcp__memory__create_relations([
{
from: 'ServiceA',
to: 'ServiceB',
relationType: 'depends_on'
},
{
from: 'EmployeeEntity',
to: 'UserEntity',
relationType: 'syncs_from'
}
]);
Add Observations
mcp__memory__add_observations([
{
entityName: 'EmployeeValidationPattern',
contents: [
'Also supports .AndNot() for negative validation',
'Use .Of<ICqrsRequest>() for type conversion (see docs/project-reference/backend-patterns-reference.md)'
]
}
]);
Search Knowledge
// Search by query
mcp__memory__search_nodes({ query: 'validation pattern' });
// Open specific entities
mcp__memory__open_nodes({
names: ['EmployeeValidationPattern', 'ServiceAModule']
});
// Read entire graph
mcp__memory__read_graph();
Delete Outdated Knowledge
// Delete entities
mcp__memory__delete_entities({ entityNames: ['OutdatedPattern'] });
// Delete specific observations
mcp__memory__delete_observations([
{
entityName: 'EmployeeValidationPattern',
observations: ['Outdated observation text']
}
]);
// Delete relations
mcp__memory__delete_relations([
{
from: 'OldService',
to: 'NewService',
relationType: 'depends_on'
}
]);
When to Save to Memory
Always Save
- Discovered Patterns: New code patterns not in documentation
- Bug Solutions: Complex bugs with non-obvious solutions
- Service Boundaries: Which service owns what
- Architectural Decisions: Why a particular approach was chosen
- Anti-Patterns: Mistakes to avoid
Save at Session End
// Session summary template
mcp__memory__create_entities([
{
name: `Session_${taskName}_${date}`,
entityType: 'SessionSummary',
observations: [
`Task: ${taskDescription}`,
`Completed: ${completedItems.join(', ')}`,
`Remaining: ${remainingItems.join(', ')}`,
`Key Files: ${keyFiles.join(', ')}`,
`Discoveries: ${discoveries.join(', ')}`,
`Next Steps: ${nextSteps.join(', ')}`
]
}
]);
Memory Retrieval Patterns
Session Start Protocol
// 1. Search for related context
const results = mcp__memory__search_nodes({
query: 'current feature or task keywords'
});
// 2. Load relevant entities
mcp__memory__open_nodes({
names: results.entities.map(e => e.name)
});
// 3. Check for incomplete sessions
mcp__memory__search_nodes({ query: 'SessionSummary Remaining' });
Before Implementation
// Check for existing patterns
mcp__memory__search_nodes({ query: 'CQRS command pattern' });
// Check for anti-patterns
mcp__memory__search_nodes({ query: 'AntiPattern command' });
// Check for related decisions
mcp__memory__search_nodes({ query: 'Decision validation' });
After Bug Fix
// Save the fix
mcp__memory__create_entities([
{
name: `BugFix_${bugName}`,
entityType: 'BugFix',
observations: [
`Symptom: ${symptomDescription}`,
`Root Cause: ${rootCause}`,
`Solution: ${solution}`,
`Files: ${affectedFiles.join(', ')}`,
`Prevention: ${preventionTip}`
]
}
]);
Knowledge Graph Structure
┌─────────────────────────────────────────────────────────────┐
│ Project Knowledge │
├─────────────────────────────────────────────────────────────┤
│ Services │
│ ├── ServiceA ──depends_on──> AccountsService │
│ ├── ServiceB ──depends_on──> AccountsService │
│ └── ServiceC ──depends_on──> AccountsService │
│ │
│ Patterns │
│ ├── CQRSCommandPattern │
│ ├── CQRSQueryPattern │
│ ├── EntityEventPattern │
│ └── ValidationPattern │
│ │
│ Entities │
│ ├── Employee ──syncs_from──> User │
│ ├── Company ──syncs_from──> Organization │
│ └── LeaveRequest ──owned_by──> ServiceA │
│ │
│ Sessions │
│ ├── Session_LeaveRequest_2025-01-15 │
│ └── Session_EmployeeImport_2025-01-14 │
└─────────────────────────────────────────────────────────────┘
Importance Scoring
When saving observations, prioritize:
| Score | Criteria |
|---|---|
| 10 | Critical bug fixes, security issues |
| 8-9 | Architectural decisions, service boundaries |
| 6-7 | Code patterns, best practices |
| 4-5 | Session summaries, progress notes |
| 1-3 | Temporary notes, exploration results |
Memory Maintenance
Weekly Cleanup
// Find old session summaries (> 30 days)
mcp__memory__search_nodes({ query: 'SessionSummary' });
// Delete outdated sessions
mcp__memory__delete_entities({
entityNames: ['Session_OldTask_2024-12-01']
});
Consolidation
When multiple observations cover same topic:
// 1. Read existing entity
mcp__memory__open_nodes({ names: ['PatternName'] });
// 2. Delete fragmented observations
mcp__memory__delete_observations([
{
entityName: 'PatternName',
observations: ['Fragment 1', 'Fragment 2']
}
]);
// 3. Add consolidated observation
mcp__memory__add_observations([
{
entityName: 'PatternName',
contents: ['Consolidated comprehensive observation']
}
]);
Quick Reference
Create: mcp__memory__create_entities / mcp__memory__create_relations
Read: mcp__memory__read_graph / mcp__memory__open_nodes / mcp__memory__search_nodes
Update: mcp__memory__add_observations
Delete: mcp__memory__delete_entities / mcp__memory__delete_observations / mcp__memory__delete_relations
Part 3: Integration with Workflows
Long-Running Task Memory Pattern
All long-running workflows should follow this pattern:
┌─────────────────────────────────────────────────────────┐
│ TASK START │
│ └── Create initial checkpoint with task context │
│ └── Initialize todo list │
│ │
│ EVERY 20-30 OPERATIONS │
│ └── Update checkpoint with progress │
│ └── Update todo list status │
│ │
│ MILESTONE REACHED │
│ └── Create detailed checkpoint │
│ └── Save key findings to MCP memory (if reusable) │
│ │
│ BEFORE COMPACTION (auto via PreCompact hook) │
│ └── Auto-checkpoint created by system │
│ │
│ AFTER COMPACTION / SESSION RESUME │
│ └── Read latest checkpoint │
│ └── Search MCP memory for relevant context │
│ └── Continue from documented Next Steps │
│ │
│ TASK COMPLETE │
│ └── Final checkpoint with summary │
│ └── Save reusable patterns to MCP memory │
│ └── Clean up temporary checkpoints │
└─────────────────────────────────────────────────────────┘
Checkpoint Naming Convention
| Type | Format | Example |
|---|---|---|
| Manual checkpoint | checkpoint-{YYMMDD}-{HHMM}-{slug}.md |
checkpoint-250106-1430-user-auth.md |
| Auto checkpoint | memory-checkpoint-{timestamp}.md |
memory-checkpoint-20250106-143000.md |
| Analysis notes | {type}-{date}-{slug}.md |
analysis-250106-payment-flow.md |
| Task notes | .ai/workspace/analysis/{slug}.analysis.md |
Used by feature-implementation |
Related Commands & Skills
| Command/Skill | Purpose |
|---|---|
/checkpoint |
Create manual memory checkpoint |
/context |
Load project context |
/compact |
Manually trigger context compaction |
/watzup |
Generate progress summary |
feature-implementation |
Uses task analysis notes pattern |
debug-investigate |
Uses investigation logs |
feature-investigation |
Uses analysis report pattern |
Memory Decision Matrix
| Context Type | Storage | Why |
|---|---|---|
| Task progress | File checkpoint | Specific to current task |
| Code patterns | MCP memory | Reusable across sessions |
| Bug solutions | MCP memory | Helps future debugging |
| Service boundaries | MCP memory | Architectural knowledge |
| Investigation findings | File checkpoint | Task-specific analysis |
| Architectural decisions | MCP memory | Long-term knowledge |
Related
learncontext-optimization
Closing Reminders
- MUST break work into small todo tasks using
TaskCreateBEFORE starting - MUST search codebase for 3+ similar patterns before creating new code
- MUST cite
file:lineevidence for every claim (confidence >80% to act) - MUST add a final review todo task to verify work quality
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
fix-parallel
[Implementation] Analyze & fix issues with parallel fullstack-developer agents
ask
[Utilities] Answer technical and architectural questions.
claude-code
[Utilities] Claude Code CLI setup, configuration, troubleshooting, and feature guidance. Triggers on claude code setup, hook not firing, MCP connection, context limit, skill creation, slash command setup.
workflow-deployment
[Workflow] Trigger Deployment & Infrastructure workflow — CI/CD pipelines, Docker, Kubernetes setup and deployment.
workflow-idea-to-pbi
[Workflow] Trigger Idea to PBI workflow — po/ba workflow: capture idea, refine to pbi, create stories, prioritize.
easy-claude-help
[Utilities] Configuration guide for the easy-claude framework — explain settings, guide users through configuring .ck.json.
Didn't find tool you were looking for?