dispatching-parallel-agents
Split work across parallel subagents and coordinate their outputs
Split work across parallel subagents and coordinate their outputs
npx skills add https://github.com/obra/superpowers/tree/main/skills/dispatching-parallel-agentsSplit work across parallel subagents and coordinate their outputs
This repo contains 13 individual skills — each has its own dedicated page.
Structured ideation and problem decomposition frameworks
Execute a plan step-by-step with checkpoints and verification at each stage
Branch close checklist: tests, commit message, pull request, and review request
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Prepare code for review: self-review, test coverage, and pull request description
Orchestrate specialized subagents for different parts of a task
Hypothesis-driven debugging loop: observe, hypothesize, test, verify
TDD loop: write the failing test first, implement the minimal change, verify, then refactor
Use git worktrees to run parallel agent sessions on separate branches
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
Force a verification pass before any task is marked done
Write structured implementation plans before starting complex tasks
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Capture and replay every AI agent tool call, prompt, and response to trace sessions and debug complex workflows with full observability.
Local Codex skills for Lark and Feishu workflows
Superpowers-style repository for agent skills and productivity extensions.
Claude Code skills for solopreneurs: structured workflow (standard-process), external repo evaluation (repo-eval), AI model benchmarking (model-bench), + always-on rules for evidence, security, parallel-agent safety, and commits
Shared Claude Code skills and configuration for the Goodtribes team
Reusable MCP-driven E2E harness for agent workflows