Execute multiple independent tasks in parallel to improve workflow throughput.

Install

mkdir -p .claude/skills/ultrawork && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/840" && unzip -o skill.zip -d .claude/skills/ultrawork && rm skill.zip

Installs to .claude/skills/ultrawork

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Parallel execution engine for high-throughput task completion
61 charsno explicit “when” trigger
Advanced

Key capabilities

  • →Distributes tasks across multiple agents concurrently
  • →Manages dependency-aware task graphs for non-trivial work
  • →Routes specific tasks to optimal agent tiers
  • →Reduces total execution time through parallel processing
  • →Generates evidence-backed execution summaries

How it works

It fires concurrent calls to independent agents based on a task graph, routing each sub-task to the appropriate model tier to ensure efficiency.

Inputs & outputs

You give it
Task description containing parallel work items
You get back
Consolidated execution summary and task results

When to use ultrawork

  • →Run multiple code analysis tasks in parallel
  • →Parallelize independent data processing
  • →Execute simultaneous testing routines
  • →Distribute research tasks among agents

About ultrawork

Distributes concurrent tasks to multiple agents to reduce total execution time. It manages intent grounding and provides structured summaries for parallel workflows.

Parallel execution engine for high-throughput task completion

When not to use it

  • →Sequential tasks requiring strict ordering
  • →Workflows needing long-lived state or session persistence
  • →Single tasks without parallelism potential

Prerequisites

Access to multi-tier agent models

Limitations

  • →Not designed for persistent session state management
  • →Requires user-managed completion verification
  • →Potential for increased token costs if improperly routed

How it compares

It actively manages agent concurrency and routing for independent tasks, rather than executing commands sequentially.

Compared to similar skills

ultrawork side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
ultrawork (this skill)114moNo flagsAdvanced
using-superpowers955moNo flagsBeginner
clawhub254moReviewIntermediate
skill-installer293moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

using-superpowers

obra

Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists

95205

clawhub

openclaw

Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawhub CLI.

25151

skill-installer

openai

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

29141

continuous-learning

affaan-m

Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.

995

memory-keeper-proactive-context-maintenance

b4CU-R4U

Automatically detect and maintain memory freshness by monitoring context staleness, significant code changes, task completions, and phase transitions. Proactively suggests and executes memory sync operations with user confirmation. Use when the user says "sync memory", "update context", or when the Skill detects that context is stale (>2 hours), significant changes have occurred (new commits), tasks completed, or major milestones reached. Replaces passive "context is stale" warnings with active maintenance.

694

swift-executor

erichowens

Rapid task execution without hesitation or deterrence. Expert in overcoming blockers, making quick decisions, and maintaining forward momentum. Use for urgent tasks, breaking through impediments, decisive action. Activates on "swift", "execute quickly", "undeterred", "overcome blocker", "just do it". NOT for strategic planning, careful analysis, or research tasks.

1087

Search skills

Search the agent skills registry