brainstorming
Clarify requirements and design options before starting implementation.
npx skills add obra/superpowers --skill brainstormingBrowse selected engineering workflow skills from the Superpowers project.
Use brainstorming for open design questions and a written plan for a change that spans several steps.
Clarify requirements and design options before starting implementation.
npx skills add obra/superpowers --skill brainstormingFollow evidence from a reproducible failure to its root cause.
npx skills add obra/superpowers --skill systematic-debuggingTurn an approved design into an implementation plan with verification steps.
npx skills add obra/superpowers --skill writing-plansPrepare context and verification results so a reviewer can assess a change.
npx skills add obra/superpowers --skill requesting-code-reviewDrive application changes with a failing test before implementing the fix.
npx skills add obra/superpowers --skill test-driven-developmentCollect fresh verification output before reporting that the work is finished.
npx skills add obra/superpowers --skill verification-before-completionNo skill in this category has a full write-up yet.
Superpowers (obra/superpowers) is not a tool collection. It is a discipline for how an agent should behave on engineering work: understand first, plan second, change third, verify last. Every skill on this page enforces one step of that loop.
The reason it matters is boring and specific: an agent that skips the loop does plausible work fast. It writes a fix for a bug it has not reproduced, touches four files nobody asked about, then reports success without running anything. These six skills exist to make each of those failures harder.
brainstorming — before implementation. It asks what the requirement is and what the options are, and it refuses to accept “just make it work”.writing-plans — turns an approved design into steps with a verification step attached to each. This is the artifact the rest of the loop reads.test-driven-development — a failing test first, then the change. The test is the proof that the change does something; without it, “fixed” is an opinion.systematic-debugging — when a failure is real and unexplained: reproduce, reduce, hypothesise, test the hypothesis. It stops the pattern where each attempt is a fresh guess.requesting-code-review — assembles the context and the verification output a reviewer needs. The point is that the reviewer should not have to reconstruct your reasoning.verification-before-completion — the last gate: collect fresh output before claiming the work is finished. Stale test output is not evidence.Install all six from one repo, or install the ones that match your bottleneck:
npx skills add obra/superpowers --skill systematic-debugging
Coding skills covers the same work at the level of individual tools — reviews, refactors, test gaps. Agent workflow covers how skill files are written if you want to extend this discipline to your own team's rules.
Gather current test output and compare the implementation with the agreed requirements.
Rerun the tests yourself, paste the output, and compare what changed with the requirements the plan was written against. Output from before the change does not count.
Use the command beside the skill, select a supported agent, then reload the agent and confirm it can see the skill in your project.
This page lists six skills from obra/superpowers. Start with the individual skill that matches your task. For a full workflow, use brainstorming to define requirements, writing-plans to break down the work, test-driven-development to write tests, and verification-before-completion to check the result.
After a failing test exists, use it to hold the behaviour of the workspace, then work on the skill file itself with the same loop: reproduce, fix, verify. The same workflow applies to any file you edit.
Your own tests plus the plan's acceptance criteria. Ask for the command that was run and its output, and confirm the output is newer than the last edit.
Forgot to reproduce the failure first. Changing code until the symptom disappears leaves the cause in place and the bug usually returns within days.
systematic-debugging if you fight repeated failed fixes. verification-before-completion if the agent reports success too often. writing-plans if work drifts mid-task.
It can. These are workflow instructions, and two workflows telling the agent different things about review or testing produces muddle. Pick one owner per step.
It adds a step and saves the rework. The measurable difference is how often a “fix” has to be reopened.