skills.rest
CornFedKratos
CornFedKratosCOMMUNITY
Explore all skills by this author →
GitHub

session-close

Export and vectorize AI-DLC session context into the project knowledge base.

Updated Apr 11, 2026
Search Tags:#ai-dlc#session-close#kb-vectorization#knowledge-dump#replay-anchor#fce
One-click install
npx skills add https://github.com/CornFedKratos/s3-aidlc --skill session-close-cornfedkratos
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: session-close
Source: https://github.com/CornFedKratos/s3-aidlc/tree/main/plugins/s3-aidlc/skills/session-close
Command: npx skills add https://github.com/CornFedKratos/s3-aidlc --skill session-close-cornfedkratos

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Use when an agent ends a work session on any AI-DLC project. Trigger on /session-close, /session_close, "knowledge dump", or when the orchestrator signals end of session. Two paths: Desktop/Browser agents (CPO, CRO) generate a downloadable session context and hand off to the CLI agent for vectorization. CLI agents (CTO, Engineering) prompt for the CPO context, merge into a combined export, and automatically vectorize into the project's KB. Includes FCE (FORGE'd Context Engine) enhancements: conflict detection, session fingerprinting, decision decay scoring, dependency tracking, and replay anchors. Works with any KB level (markdown through hosted vector DB) and any project tracker ( Linear, Jira, GitHub Issues, etc.). Ensures institutional memory persists across sessions — no knowledge dies when a chat window closes.

Core Features & Use Cases

  • Desktop/Browser path: generate a downloadable session context export for handoff to the CLI.
  • CLI path: merge CPO context with CTO context and vectorize into the KB as the single source of truth.
  • Replay anchors, decay scoring, dependency tracking, and conflict detection to preserve memory integrity.

Quick Start

Make sure you have an active session, then export the session context using the standard template and hand it to Codey for KB vectorization.

Frequently Asked Questions about session-close

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

FAQPage Schema
How do I persist AI-DLC session context for knowledge vectorization after closing a chat?▼

You can persist AI-DLC session context by exporting a complete session context at close, merging desktop and CLI agent data, and vectorizing it into your project knowledge base to maintain institutional memory.

What's the best way to hand off session context from a browser agent to a CLI agent?▼

The best way to hand off session context is generating a downloadable export from the Desktop or Browser agent, then passing it to the CLI agent to merge and vectorize into the knowledge base.

Does session context export work with hosted vector databases and project trackers like Jira?▼

Yes, session context export works with any knowledge base level from markdown to hosted vector databases, and integrates with any project tracker including Linear, Jira, and GitHub Issues.

How does conflict detection and decision decay scoring work in session memory exports?▼

Conflict detection and decision decay scoring are FCE enhancements applied during session memory exports to evaluate context integrity, track dependencies, and fingerprint sessions for accurate knowledge base replay.

When do I need to trigger a session knowledge dump in an AI-DLC workflow?▼

You need to trigger a session knowledge dump when an agent ends a work session on any AI-DLC project, using commands like /session-close or when the orchestrator signals the end of session.

Can I use replay anchors to restore a previous AI development session state?▼

Yes, replay anchors are included in the session context export to preserve memory integrity, allowing you to restore and reference previous AI development session states across the knowledge base.

Related Skills

Explore More Software Engineering Skills→
Human-Frontier-Labs-IncHuman-Frontier-Labs-Inc

AgentDB Memory Patterns

Persist session memory and retrieve contextual patterns with AgentDB.

Official
Advanced
Kling0012Kling0012
1

AgentDB Vector Search

Index and query vector representations for semantic search across document collections.

Community
Intermediate
ma08ma08
28

save-status

Persist task status files and reconcile session metadata across machines.

Community
Advanced
Renzo-TognellaRenzo-Tognella

Temporal & Episodic Memory

Manage temporal and episodic memory with decay and hierarchical organization.

Community
Advanced