This does exactly what it says: you point it at a markdown plan file with sprints and tasks, type /parallel-task, and it spins up multiple Claude subagents to work on independent tasks simultaneously. It parses your plan structure, figures out dependencies, and won't launch agents for tasks that would step on each other's toes. The prompt template it uses is thoughtfully designed with context, acceptance criteria, and validation steps baked in. Worth noting that it keeps looping until the whole plan is done or hits a blocker, so you're not babysitting each task. If you're working from detailed plan files and tired of serializing work that could happen in parallel, this makes that automatic.
npx -y skills add jdrhyne/agent-skills --skill parallel-task --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
sickn33/antigravity-awesome-skills
moizibnyousaf/ai-agent-skills
github/awesome-copilot