skill

agent-management — Claude Code skill: what it does, how to install

Q: How do I install agent-management in Claude Code?

Run `npx claude-code-templates@latest --skill ai-maestro/agent-management`, then run `npx skills add davila7/claude-code-templates --skill agent-management -a claude-code`. The skill file will be available at `~/.claude/skills/agent-management/SKILL.md`.

Q: What does agent-management require?

AI Maestro must run locally with `tmux 3.0+`. Install its CLI from `ai-maestro-plugins` by running `./install-agent-cli.sh`.

This skill controls AI agents through the AI Maestro CLI, from creation and status checks to hibernation and plugin changes. Use it when several agents need lifecycle commands.

Install into Claude Code · claude-code-templates All methods and platforms ↓

npx claude-code-templates@latest --skill ai-maestro/agent-management

Open on GitHub

What agent-management does

The skill connects Claude Code to the AI Maestro command line and covers agent lifecycle tasks. It can create an agent with a directory, show agents and their details, change a task or tags, rename an agent, remove it, hibernate it, wake it, or restart it.

The same command set handles plugins: install or remove one for an agent, list installed plugins, and add a marketplace source. It can also export an agent configuration or import one from a file. Agent states include online, offline, and hibernated. AI Maestro must be running locally, and tmux 3.0+ is required, or these commands will not run.

Set up the CLI by cloning ai-maestro-plugins, entering that directory, and running ./install-agent-cli.sh. The skill then uses commands such as aimaestro-agent.sh create <name> --dir <path> and aimaestro-agent.sh hibernate <agent> to act on agents.

What it helps with

create an agent with a project directory
install a plugin for one agent
pause agents while saving their state
export configuration before risky changes
restore an agent from a file

Example prompts for the agent

Create backend-api in ~/projects/backend and assign it a TypeScript REST API task.
List every agent with its current state using aimaestro-agent.sh list.
Hibernate frontend-ui, then wake it and attach to its session.

How to install agent-management

1claude-code-templates

npx claude-code-templates@latest --skill ai-maestro/agent-management

2Skills CLI (Vercel)

npx skills add davila7/claude-code-templates --skill agent-management -a claude-code

3Manually: put the files in place

~/.claude/skills/agent-management/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/agent-management/

Manually: put the files in place

.agents/skills/agent-management/SKILL.md

For all projects use ~/.agents/skills/

Manually: put the files in place

.cursor/skills/agent-management/SKILL.md

Cursor also reads .agents/skills/ and .claude/skills/

1GitHub CLI

gh skill install davila7/claude-code-templates agent-management

2Manually: put the files in place

.github/skills/agent-management/SKILL.md

Platform CLI

gemini skills install https://github.com/davila7/claude-code-templates --path cli-tool/components/skills/ai-maestro/agent-management

Manually: put the files in place

.devin/skills/agent-management/SKILL.md

The legacy .windsurf/skills/ path still works

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about agent-management

How do I install agent-management in Claude Code?

Run npx claude-code-templates@latest --skill ai-maestro/agent-management, then run npx skills add davila7/claude-code-templates --skill agent-management -a claude-code. The skill file will be available at ~/.claude/skills/agent-management/SKILL.md.

What does agent-management do?

It operates AI Maestro agents from the CLI. The skill covers creation, inspection, updates, renaming, deletion, hibernation, wake-up, restart, plugin handling, and configuration transfer.

What does agent-management require?

AI Maestro must run locally with tmux 3.0+. Install its CLI from ai-maestro-plugins by running ./install-agent-cli.sh.

setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. 1,052,851installs ask-matt Matt Pocock Routes you to the right Matt Pocock skill or flow for the task at hand. Use it when you need a starting point for a feature, prototype, incoming issue, or hard bug. 766,587installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. 711,230installs writing-plans Jesse Vincent This skill turns requirements for a multi-step task into an implementation plan before code changes begin. It helps when another engineer needs exact files, interfaces, and checks. CX Codex 282,859installs caveman-review JuliusBrussee Turns code review comments into one line per finding: location, problem, fix. Useful when a diff or PR needs a fast pass without the filler. CX Codex +1 411,800installs caveman-compress JuliusBrussee Compresses CLAUDE.md, todo lists, and other prose files into a shorter format while retaining a readable backup. CX Codex +1 411,500installs

From the same set495

The whole set →

planning Keeps markdown files for goals, findings and session progress so an agent doesn't drift off the task mid-run. 712installs context7-auto-research This skill retrieves current library and framework references through the Context7 API. Use it when a Claude Code answer needs documentation for React, Next.js, Prisma, or another library. 709installs smart-contract-auditor Audits EVM and Solidity smart contracts for exploits, logic flaws, and economic attack vectors. Useful for pre-deployment reviews and vulnerability reports. 701installs nextjs-performance-audit This command checks a Next.js project’s Lighthouse results, bundle size, and runtime performance. Use it to find performance issues and get optimization suggestions. 694installs figma-implement-design Turns a Figma node into code that fits your project: pulls the design context, a screenshot and assets over Figma MCP, then maps them onto your components and tokens. 689installs security-audit A workflow skill that walks a web app or API through recon, vulnerability scanning, pentesting, hardening and reporting. 673installs moc-agent A Claude subagent that builds and maintains maps of content (MOCs) in an Obsidian vault. Useful once notes pile up in folders with no navigation. 666installs performance-audit Audits codebase performance, locating slow database queries, nested loops, and build bottlenecks. Prioritizes optimizations by system impact and implementation effort. 661installs