wrap

Review session-end conversations and route corrections to memory tiers.

Updated Mar 7, 2026
One-click install
npx skills add https://github.com/eddowding/orion_cos --skill wrap-eddowding
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: wrap
Source: https://github.com/eddowding/orion_cos/tree/main/Operations/Claude/skills/operations/wrap
Command: npx skills add https://github.com/eddowding/orion_cos --skill wrap-eddowding

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the crucial end-of-session review process, ensuring that learnings, corrections, and new facts are systematically captured and integrated into the AI's knowledge base and operational rules.

Core Features & Use Cases

  • Self-Correction: Identifies and logs mistakes, failed approaches, and areas where user input was repeated or unclear.
  • Contextual Learning: Analyzes the session for missing context and successful patterns.
  • Memory Management: Routes identified updates to the correct scope (global, project-specific, vault) and formats them for persistence.
  • Use Case: After a complex coding session where the AI made a few errors and had to be redirected, running this skill will generate a concise debrief, propose specific rule updates (e.g., "when X, do Y instead of Z"), and extract key facts to update the AI's memory for future sessions.

Quick Start

Run the wrap skill to review the last session and update memory.

Frequently Asked Questions about wrap

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate AI session review and update memory after a coding task?

Automated session review identifies mistakes and missing context from conversations, then routes these updates to global, vault, or per-project memory tiers. This process converts session debriefs into persistent rule updates for future AI context.

What is contextual learning in AI knowledge management?

Contextual learning in AI knowledge management is the process of analyzing a session for missing context and successful patterns. It identifies where user input was repeated or unclear to extract key facts for memory updates and rule refinement.

How do I save AI self-corrections and failed approaches into persistent memory?

To save AI self-corrections, run an end-of-session debrief that logs mistakes and failed approaches. The review identifies errors and formats them as persistent memory entries, proposing specific rule updates like 'when X, do Y instead of Z' for future sessions.

Can I route AI context capture updates to different project memory tiers?

Yes, AI context capture updates can be routed to global, vault, or per-project memory tiers. The review process categorizes insights by scope to ensure updates are formatted and persisted at the correct hierarchical level.

What tools are required for comprehensive AI memory management and rule refinement?

Comprehensive AI memory management and rule refinement require read, write, edit, glob, and grep tools. These tools enable deep analysis and modification of skill files and memory entries during the session-end review.