adaptationio/memory-manager
.claude/skills/memory-manager/SKILL.md
External persistent memory for cross-session knowledge. Use when storing error patterns, retrieving learned solutions, managing causal memory chains, or persisting project knowledge.
$ install --global
skillsauthnpx skillsauth add adaptationio/skrillz memory-managerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Mar 31, 2026, 12:43 AM57.0s5 files scanned
SKILL.md
- name:
- memory-manager
- description:
- External persistent memory for cross-session knowledge. Use when storing error patterns, retrieving learned solutions, managing causal memory chains, or persisting project knowledge.
- version:
- 1.0.0
- category:
- autonomous-coding
- layer:
- context-engineering
Memory Manager
External persistent memory system for maintaining knowledge across autonomous coding sessions.
Quick Start
Store a Memory
from scripts.memory_manager import MemoryManager
memory = MemoryManager(project_dir)
memory.store(
key="auth_solution",
value="Added User-Agent header to fix 403",
memory_type="causal"
)
Store Causal Chain (Error→Solution)
memory.store_causal_chain(
error="403 Forbidden on API call",
solution="Add User-Agent header to requests"
)
Retrieve Similar Errors
solutions = memory.get_similar_errors("403 error calling API")
# Returns: [{"error": "403 Forbidden...", "solution": "Add User-Agent..."}]
Memory Types
┌─────────────────────────────────────────────────────────────┐
│ MEMORY TYPES │
├─────────────────────────────────────────────────────────────┤
│ │
│ EPISODIC │
│ ├─ Past events and outcomes │
│ ├─ "Last time we deployed, X happened" │
│ └─ Session summaries │
│ │
│ PROCEDURAL │
│ ├─ Learned skills and patterns │
│ ├─ "How to set up database migrations" │
│ └─ Working code patterns │
│ │
│ SEMANTIC │
│ ├─ Factual knowledge about project │
│ ├─ "Database uses PostgreSQL" │
│ └─ Architecture decisions │
│ │
│ CAUSAL │
│ ├─ Error → Solution chains │
│ ├─ "403 error → Add User-Agent header" │
│ └─ Self-healing patterns │
│ │
└─────────────────────────────────────────────────────────────┘
Storage Location
project/
└── .claude/
└── memory/
├── episodic.json
├── procedural.json
├── semantic.json
└── causal.json
Causal Memory Pattern
# Traditional error handling:
# Error occurs → Unclear response
# Causal memory:
# Error: 403 Forbidden
# Memory: [403] → [missing User-Agent] → [added header] → [success]
# Response: "Adding User-Agent header (learned from previous error)"
Integration Points
- error-recoverer: Uses causal memory for self-healing
- context-compactor: Stores summaries in episodic memory
- coding-agent: Stores procedural patterns
References
references/MEMORY-TYPES.md- Detailed type documentationreferences/RETRIEVAL-PATTERNS.md- Search patterns
Scripts
scripts/memory_manager.py- Core MemoryManagerscripts/semantic_store.py- Keyword-based storagescripts/causal_memory.py- Error→Solution chainsscripts/knowledge_base.py- Project knowledge
Related Skills
adaptationio/ttyd-remote-terminal-wsl2
development
VerifiedTrustedCommunity
Setup secure web-based terminal access to WSL2 from mobile/tablet via ttyd + ngrok/Cloudflare/Tailscale. One-command install, start, stop, status. Use when you need remote terminal access, web terminal, browser-based shell, or mobile access to WSL2 environment.
6SKILL.mdUpdated Mar 28, 2026
adaptationio/tri-ai-collaboration
development
VerifiedTrustedCommunity
Complete development workflows where Claude writes the code while Gemini and Codex provide research, planning, reviews, and different perspectives. Claude remains the main developer. Use for complex projects requiring expert planning and multi-perspective reviews.
6SKILL.mdUpdated Mar 28, 2026
adaptationio/todo-management
development
VerifiedTrustedCommunity
Systematic progress tracking for skill development. Manages task states (pending/in_progress/completed), updates in real-time, reports progress, identifies blockers, and maintains momentum. Use when tracking skill development, coordinating work, or reporting progress.
6SKILL.mdUpdated Mar 28, 2026
adaptationio/testing-workflow
testing
VerifiedTrustedCommunity
Comprehensive testing workflow orchestrating functional testing, example validation, integration testing, and usability assessment. Sequential workflow for complete skill testing from examples through scenarios to integration validation. Use when conducting thorough testing, pre-deployment validation, ensuring skill functionality, or comprehensive quality checks.
6SKILL.mdUpdated Mar 28, 2026