Obra
Agentic engineering practices
Skills for debugging, reviews, planning, testing, and parallel execution.
Featured skills
systematic-debugging
Used when encountering any bug, test failure, or unexpected behavior, before proposing fixes
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying...
dispatching-parallel-agents
Used when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
executing-plans
Used when you have a written implementation plan to execute in a separate session with review checkpoints
finishing-a-development-branch
Used when implementation is complete, all tests pass, and you need to decide how to integrate the work
receiving-code-review
Used when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or...
requesting-code-review
Used when completing tasks, implementing major features, or before merging to verify work meets requirements
subagent-driven-development
Used when executing implementation plans with independent tasks in the current session
test-driven-development
Used when implementing any feature or bugfix, before writing implementation code
using-git-worktrees
Used when starting feature work that needs isolation from current workspace or before executing implementation plans -...
using-superpowers
Used when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY...
verification-before-completion
Used when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running...
OpenAI
Codex developer tools
OpenAI skills for code review, pull requests, testing, and Codex extensions.
OthmanAdi
Persistent planning tools
File-based planning tools for long-running agent work and reliable recovery.
Paperclipai
Agent team orchestration
Skills for operating, diagnosing, and extending teams of AI agents.