Use when packages, services, ownership boundaries, entrypoints, tests, commands, or dependencies changed and the compact repository map needs a focused update.
Scanned 9/6/2026
Install to Claude Code
npx -y skills add ihabkhaled/AI-Psychiatry --skill repository-map-update --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Repository Map Update?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/ihabkhaled-repository-map-update)More formats (shields.io, HTML) on the badges page.
---
name: repository-map-update
description: Use when packages, services, ownership boundaries, entrypoints, tests, commands, or dependencies changed and the compact repository map needs a focused update.
---
# Repository Map Update
## Core principle
Update only affected map sections so agents can locate authoritative sources cheaply.
## Procedure
1. Identify the architectural change and affected boundary.
2. Verify new paths, ownership, commands, and relationships from source.
3. Edit only related map entries.
4. Remove or mark stale entries.
5. Keep detail at navigation level and link to deeper sources.
6. Validate links and context index references.
## Required output
Affected map entries, evidence, removed stale facts, and validation result.
## Limits
The map is compact navigation, not a repository dump.
## Common mistakes
Do not regenerate unrelated architecture prose or record temporary task state.
## Stop condition
Stop when changed boundaries are accurately discoverable and all references resolve.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.