Parallel Subagents — Productivity skill for Claude Code
Launch parallel agents to accomplish a task.
How to install Parallel Subagents
Installs to ~/.claude/commands/kkarpushin-personal-brand-agent-parallel_subagents.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/kkarpushin/personal-brand-agent/HEAD/.claude/commands/parallel_subagents.md -o ~/.claude/commands/kkarpushin-personal-brand-agent-parallel_subagents.md Restart Claude Code, or start a new session, for it to be picked up.
What Parallel Subagents does
description: Launch parallel agents to accomplish a task. argument-hint: [prompt request] [count]
Parallel Subagents
Follow the `Workflow` below to launch `COUNT` agents in parallel to accomplish a task detailed in the `PROMPT_REQUEST`.
Variables
PROMPT_REQUEST: $1 COUNT: $2
Workflow
Parse Input Parameters
- Extract PROMPT_REQUEST to understand the task
- Determine COUNT (use provided value or infer from task complexity)
Design Agent Prompts
- Create detaile
Alternatives in Productivity
- Epic Decompose — Break an epic into task children without creating task branches 243.5k ★
- Worktree Status Check — Verify the current worktree environment and show task details 23.4k ★
- P7 — PUA P7 骨干模式 — 方案驱动执行 19.5k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Accomplish
Compatibility alias for /implement-task --multi.
Gsc Insight
Launch the gsc-insight agent to handle this task. Use the Task tool with subagent_type "gsc-insight" and pass
SEO Article Writer
Launch the seo-article-writer agent to handle this task. Use the Task tool with subagent_type "seo-article-wri
Auto Pilot
Launch an unattended auto-pilot run — an interactive pre-flight, then spawn a detached orchestrator that advan
Background
Launch one self-contained task in the background and stop
Launch A Product
Workflow recipe — go from competitive landscape to a fully checklisted launch and press release by chaining 5
Related Agents
Task Decomposition Expert
Use this agent when you need to break down complex user goals into actionable tasks and identify the optimal c
Agentic Search Optimizer
Expert in WebMCP readiness and agentic task completion — audits whether AI agents can actually accomplish task
Lite Checker
Independent behavior validator for the lite (/build) flow. Spawned by lite-orchestrator on a fresh context aft