verification-before-completion
Force a verification pass before any task is marked done
Force a verification pass before any task is marked done
npx skills add https://github.com/obra/superpowers/tree/main/skills/verification-before-completionForce a verification pass before any task is marked done
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
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
Write structured implementation plans before starting complex tasks
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Provision cloud infrastructure from AI agents using TypeScript instead of manual dashboards.
Framework to run full atdd cylce with Claude Code and other coding agents
Build Claude Code–style deep agents in Python: tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, and unlimited context — all on Pydantic AI.
Simulate university counselor interactions to practice communication, navigate school policies, and roleplay professional conversations through a personal agent.
Personal collection of AI-agent skills (flush, init, ...). Each folder is one skill; SKILL.md inside is the source of truth. AI-agnostic output.
Personal Claude Code plugin marketplace