Fleet Run — Productivity skill for Claude Code
Work one fleet brief, or a run's task queue, in this session and report by writing files.
How to install Fleet Run
Installs to ~/.claude/skills/makarasty-makarasty-claude-fleet-run/SKILL.md
mkdir -p ~/.claude/skills/makarasty-makarasty-claude-fleet-run && curl -fsSL https://raw.githubusercontent.com/makarasty/makarasty-claude/HEAD/commands/fleet-run.md -o ~/.claude/skills/makarasty-makarasty-claude-fleet-run/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Fleet Run does
description: Work one fleet brief, or a run's task queue, in this session and report by writing files. Use when this session was started on a brief under .fleet/. argument-hint:
The files named below (`docs/PROTOCOL.md`, `scripts/fleet.sh` and their siblings) live in this plugin's own directory, `${CLAUDE_PLUGIN_ROOT}`, not in the project you are working on. Use `$f` for every protocol boundary below: that bookkeeping done by hand cost one measured run 235 shell cal
Alternatives in Productivity
- Pi Subagents — Claude Code like Sub-Agents & Workflow Orchestration for Pi — parallel execution, live widget, fleet view, cus 967 ★
- MathModel Skill — Agent-native mathematical modeling workflow skills for Trae, Claude Code, and Codex, covering problem parsing 345 ★
- Download Report — You are a financial report download assistant 340 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Sovereign Fleet
Kernel-sandboxed task queue, Thompson-sampling router, deterministic quality gates, and mobile PWA for autonom
Report Worklog
Summarize the work done so far this session and log it to your worklog (time reporting)
Content Writer
Write a blog post for the user's site interactively, following the 5-step workflow (brief, research, outline,
Article Idea
Turn a raw topic or notes into a structured article brief — defines audience, angle, core argument, competitiv
Article Outline
Build a section-by-section article outline from a brief or topic. Each section gets a purpose, evidence slot,
Analyze Context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synt
Related Agents
Session Manager
Workflow coordinator for writing sessions, git integration, and task routing across the team. Use to orchestra
Task Dispatcher Agent
Multi-Task Queue Coordinator & Sequential Session Dispatcher. Ingests batches of tasks and runs each task thro
Ndv Flow
Fleet orchestrator. Use when the work is too large for one agent — PRDs, epics, multi-task workloads, anything