The engineering loop

Runs ahead of building a feature or a component and digs into what is actually wanted. It exists because the most expensive agent mistake is building the wrong thing correctly.

npx skills add https://github.com/obra/superpowers --skill brainstorming

Gives the agent language for the thing most architecture conversations lack: where a seam belongs, what makes a module deep rather than wide, and why a narrow interface over real work is easier for both people and agents to navigate.

npx skills add https://github.com/mattpocock/skills --skill codebase-design

Triggers on finishing a task, landing a significant feature or preparing to merge, and frames the request around what the work was meant to do rather than what changed.

npx skills add https://github.com/obra/superpowers --skill requesting-code-review

Fires on any bug, failing test or surprise, and it fires before the agent is allowed to suggest a change. The order is the whole point: understand the failure, then propose. It is the counterweight to an agent that is eager to be helpful.

npx skills add https://github.com/obra/superpowers --skill systematic-debugging

Test-first for features and bug fixes, with integration tests rather than mocks where the integration is the risk. The discipline it adds is writing the failing test before the agent is allowed near the implementation.

npx skills add https://github.com/mattpocock/skills --skill tdd

Fires the moment the agent is about to say something is done, fixed or passing. It has to run the verification and read the output first. If you have ever been told the build is green when it is not, this is the skill for that.

npx skills add https://github.com/obra/superpowers --skill verification-before-completion

For multi-step work, where the failure mode is an agent that starts confidently in the wrong place. It produces a plan you can read and correct while correcting it is still cheap.

npx skills add https://github.com/obra/superpowers --skill writing-plans