subagent-driven-development
Orchestrate specialized subagents for different parts of a task
Orchestrate specialized subagents for different parts of a task
npx skills add https://github.com/obra/superpowers/tree/main/skills/subagent-driven-developmentOrchestrate specialized subagents for different parts of a task
This repo contains 13 individual skills — each has its own dedicated page.
Structured ideation and problem decomposition frameworks
Split work across parallel subagents and coordinate their outputs
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
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
See which Claude Code skills your team actually uses. Self-hosted, OTLP-native, no outbound telemetry.
Master your token pressure across Claude, Codex, OpenCode, Gemini, and Copilot (today). Live statusline gauges plus skills, agents, and commands that nudge Claude toward delegation and parallelization. Highly recommend customizing your CLAUDE.md to fit your workflow.
A collection of Claude Code skills for real-world development workflows
Public Codex skills maintained from local workflows
Coordinate AI agent swarms to think, work, and ship faster with ClawTeam, a Python CLI for collaborative agent workflows
MindForge: The Enterprise Agentic Framework for Claude Code & Antigravity. High-performance autonomous execution, wave-parallelism, and multi-tier governance for production-grade AI engineering.