skill

agent-manager-skill · davila7 — Claude Code skill: what it does, how to install

Q: How to install agent-manager-skill in Claude Code?

Run `npx skills add davila7/claude-code-templates --skill agent-manager-skill -a claude-code` in your terminal.

Q: What prerequisites are needed to run agent-manager-skill?

Your environment must provide `tmux` and `python3`. You also have to clone `https://github.com/fractalmind-ai/agent-manager-skill.git` into the project root and place agent profiles inside `agents/`.

Runs multiple CLI agents concurrently inside isolated tmux sessions. It handles background task dispatch, log inspection, and cron scheduling.

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

npx claude-code-templates@latest --skill ai-research/agent-manager-skill

Open on GitHub

What agent-manager-skill does

This skill gives Claude Code control over background processes on your machine. Each helper runs inside its own tmux session, driven by Python scripts located in agent-manager/scripts/main.py. Agent configurations live in the agents/ folder.

You can verify dependencies using the doctor command, inspect active processes, and spin up specific workers such as EMP_0001. The CLI feeds task descriptions into sessions via assign and tracks live terminal feeds with --follow. Because sessions run detached, cron jobs can trigger them repeatedly.

Without python3 and tmux installed locally, none of the execution scripts work. You also need to clone https://github.com/fractalmind-ai/agent-manager-skill.git into your workspace before launching agents.

What it helps with

Dispatch background workflows to isolated tmux terminal sessions
Stream live agent output using --follow log monitoring
Feed instructions directly to workers with the assign command
Trigger periodic assistant tasks through standard cron schedules

Example prompts for the agent

Run agent-manager doctor and display all configured agents
Start agent EMP_0001 and monitor the output stream
Assign the maintenance workflow from teams/fractalmind-ai-maintenance.md to EMP_0002

How to install agent-manager-skill

1claude-code-templates

npx claude-code-templates@latest --skill ai-research/agent-manager-skill

2Skills CLI (Vercel)

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

3Manually: put the files in place

~/.claude/skills/agent-manager-skill/SKILL.md

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

Manually: put the files in place

.agents/skills/agent-manager-skill/SKILL.md

For all projects use ~/.agents/skills/

Manually: put the files in place

.cursor/skills/agent-manager-skill/SKILL.md

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

1GitHub CLI

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

2Manually: put the files in place

.github/skills/agent-manager-skill/SKILL.md

Platform CLI

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

Manually: put the files in place

.devin/skills/agent-manager-skill/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-manager-skill

How to install agent-manager-skill in Claude Code?

Run npx skills add davila7/claude-code-templates --skill agent-manager-skill -a claude-code in your terminal.

What does agent-manager-skill do?

It orchestrates local CLI assistants across separate tmux sessions. It handles starting workers, assigning job instructions, and following process output.

What prerequisites are needed to run agent-manager-skill?

Your environment must provide tmux and python3. You also have to clone https://github.com/fractalmind-ai/agent-manager-skill.git into the project root and place agent profiles inside agents/.

agent-manager-skill by other authors comes first.

agent-manager-skill sickn33 A procedure for driving several local CLI agents in tmux sessions: start, stop, tail logs, hand out tasks. Useful when work runs in parallel. CX Codex +1 933installs 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 set804

The whole set →

market-research-reports Generates 50+ page market analysis documents in LaTeX, compiled directly to PDF. Helpful for sizing market opportunities and writing investment theses. 433installs session-learning-capture A slash command that pulls lessons out of the current Claude session and writes them into the project's memory files, so the next run starts informed. 425installs architecture-scenario-explorer Walks an agent through architecture choices under load, growth and failure scenarios, then lays out the trade-offs between quality attributes. 423installs cleanup-cache Cleans npm, Homebrew, Yarn, browser, and ML caches to free up drive space. Helps recover storage using three different cleaning modes. 416installs screenshot-interaction-analyzer A subagent that reads a UI screenshot and maps what can be clicked, where navigation leads and which states change. Useful when you have a screen image but no spec. 414installs create-pull-request This command generates draft pull requests using GitHub CLI aligned with repository conventions. It structures descriptions from templates and enforces emoji conventional commits. 411installs ci-setup Inspects your project structure and generates CI/CD configurations for automated testing, builds, and deployment. 411installs podcast-metadata-specialist This subagent turns podcast content into episode metadata, timed chapters, show notes, and platform-specific descriptions. Provide the recording or its transcript first. 410installs