Goodvibes Memory
This AI remembers positive interactions and affirmations to boost your mood and reinforce helpful conversations.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add goodvibes-memory npx -- -y @trustedskills/goodvibes-memory
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"goodvibes-memory": {
"command": "npx",
"args": [
"-y",
"@trustedskills/goodvibes-memory"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The Goodvibes Memory skill enables AI agents to retain information across sessions, preventing repeated errors, reinforcing proven approaches, and ensuring consistency in architectural decisions and project preferences. It captures these learnings in structured JSON files (.goodvibes/memory/) and human-readable markdown logs (.goodvibes/logs/). The agent must read from this memory before starting work and write updates after completing tasks to facilitate cross-session learning.
When to use it
- When you want an AI agent to avoid repeating past failures encountered during a task.
- To ensure the consistent application of established patterns and approaches in its work.
- To maintain adherence to prior architectural decisions made on a project.
- When needing to consistently apply project-specific preferences across multiple interactions.
Key capabilities
- Memory Storage: Stores decisions, patterns, failures, and preferences in JSON files.
- Keyword-Based Search: Allows agents to search memory entries using keywords related to their current task.
- Precision Read: A method for reading specific memory files with a defined verbosity level.
- Failure Prevention: Logs past errors along with resolutions and prevention strategies.
- Pattern Reuse: Provides access to proven approaches that can be applied consistently.
- Decision Tracking: Records architectural decisions, their rationale, and scope.
Example prompts
- "Before I start fetching data from the API, check
failures.jsonfor any authentication errors." - “Read
patterns.jsonfor examples of how to handle config updates.” - "Review
decisions.jsonto see if there are any architectural guidelines related to building this feature."
Tips & gotchas
- Mandatory Read Phase: The agent must read the memory files before starting any task.
- Keyword Precision: Use specific keywords when searching memory entries for relevant information.
- Active Decisions Only: When reviewing
decisions.json, only consider decisions with a status of "active."
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.