Skip to content
SkillCheatSheet Sign in

improve-codebase-architecture

An AI agent skill from LibreChat-AI/LibreChat, scored 52 out of 100 by code.

52/ 100D

Code score by group

  • Spec20/20
  • Description7/20
  • Procedure4/15
  • Done criteria0/15
  • Resources6/10
  • Scripts5/8
  • Safety7/7
  • Upkeep3/5

It loses the most points in Done criteria (15), the group that checks whether there is a checklist and a step that verifies the work.

What the author says it does

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

This is the description in the skill's own SKILL.md, written by its author, not by SkillCheatSheet.

Repository
LibreChat-AI/LibreChat
Folder
.claude/skills/improve-codebase-architecture
License
MIT
GitHub stars
47,029
SKILL.md lines
72
Other files
3

Add improve-codebase-architecture to your agent

npx skills add LibreChat-AI/LibreChat --skill improve-codebase-architecture

The command uses the open skills CLI. A skill is instructions and scripts your agent will follow, so read it first: open the folder on GitHub at the commit that was scored.

More skills from LibreChat-AI/LibreChat

  1. codebase-design

    Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code…

    60C

All skills in LibreChat-AI/LibreChat

Scores come from a snapshot of 300 public GitHub repositories taken on 12 November 2026. Every score is the result of fixed checks run by code; no AI is involved. How scoring works.