IamTheLovish

Improve.SKILL — Security skill for Claude Code

Security community

Use to audit a codebase or branch and write self-contained, gated implementation plans that cheaper agents execute; modes: quick, deep, a category, branch, plan, review-plan, execute, reconcile.

How to install Improve.SKILL

Installs to ~/.claude/skills/iamthelovish-command-center-improve.skill/SKILL.md

Terminal
mkdir -p ~/.claude/skills/iamthelovish-command-center-improve.skill && curl -fsSL https://raw.githubusercontent.com/IamTheLovish/command-center/HEAD/skills/improve.SKILL.md -o ~/.claude/skills/iamthelovish-command-center-improve.skill/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Improve.SKILL does

name: "improve" description: "Use to audit a codebase or branch and write self-contained, gated implementation plans that cheaper agents execute; modes: quick, deep, a category, branch, plan, review-plan, execute, reconcile." disable-model-invocation: true

improve - audit, then plans other agents execute

Adapted from shadcn's `improve` skill (github.com/shadcn/improve, MIT licence, (c) shadcn) for Beyond and Tabs and the Command Center. Core idea: **the plan is the product.** The adv

Alternatives in Security

  • Review Artifact — Creates one polished, self-contained HTML artifact from review findings, audit notes, PR feedback, code review 652 ★
  • Maestro Odyssey — Long-running iterative cycle — one entry, seven modes (debug improve planex review security defensive ui) 530 ★
  • Migration Agent — Plans a token migration (format, tool, naming or tier): chains token-audit and naming-audit, builds the transf 194 ★

Full documentation available on GitHub

View Source Repository

Related Skills

Open Skills — Security skill for Claude Code

Open Skills

The improve- family: senior-advisor Claude Code skills that audit a codebase (copy, prompts, error handling, a

Security community
Skills Repo — Security skill for Claude Code

Skills Repo

Five self-contained agent skills for Claude — interview before building, restructure brain dumps, coach beginn

Security community
Npl Reflect — Security skill for Claude Code

Npl Reflect

Appends a self-review reflection block to the end of every response. Reviews for errors, security issues, pitf

Security community
Horde Test Skill — Security skill for Claude Code

Horde Test Skill

Execute comprehensive testing plans using horde-swarm to dispatch parallel test agents across multiple test ca

Security community
Cc User Autopsy — Security skill for Claude Code

Cc User Autopsy

Honest, evidence-traceable peer-review skill for Claude Code users. Rule-based 8-dim scoring + LLM peer review

Security community
AI OS Self — Security skill for Claude Code

AI OS Self

MaiKS is a microkernel-inspired governance layer that runs inside your project workspace. It adds rules, a pre

Security community

Related Agents

POC Engineer — Security agent for Claude Code

POC Engineer

Given a confirmed finding + its context worksheet, produces the smallest self-contained crate that reproduces

Security community
Cmp Orchestrator — Project Management agent for Claude Code

Cmp Orchestrator

Coordinator for multi-step Kotlin/Compose Multiplatform harness work — plans, writes self-contained briefs, de

Project Management community
Gsdf Planner — Development agent for Claude Code

Gsdf Planner

Writes the roadmap, or decomposes one phase into self-contained executable plans.

Development community