Loading...
Loading...
Found 36 Skills
Use when dealing with 2 or more independent tasks that have no shared state or sequential dependencies
Orchestrate multiple code-writing agents in parallel when the work contains 3 or more genuinely independent build tasks. Use for execution lanes with disjoint write scope, clear task boundaries, and no dependency edges that would force sequencing.
Independence-validated parallel fleet that runs each worker (claude -p or codex exec) in its own git worktree. Use when tasks touch non-overlapping files and you need merge-safe isolation (each worker on its own branch). For DAG-ordered one-shot workers with budgets, use dag-fleet. For headless iteration with a reviewer loop, use iterative-fleet.
Analyze an existing codebase with parallel mapper agents, creating codebase documentation, understanding brownfield projects, or mapping code structure. Triggers include "map codebase", "analyze codebase", "create project context", "document codebase", "understand code", and "codebase map".
Launch 3 research agents in parallel — market, users, tech — fast answers
Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".
Show status of all features in .dev/. Scans feature folders using parallel agents, generates a status report, and offers to archive completed features.
explore — Deep codebase exploration with parallel agents. Use when exploring a repo or discovering architecture.
Parallel Agent Type Contracts
Fixes GitHub issues with parallel analysis. Use to debug errors, resolve regressions, fix bugs, or triage issues.
Enhance a plan with parallel research agents for each section to add depth, best practices, and implementation details
Launch N parallel subagents in isolated git worktrees to compete on the session task.