Development skills

A full software development workflow for coding agents, built from composable skills for brainstorming, planning, TDD, debugging and review.

Creates new skills, improves existing ones and measures how well they perform with evals and benchmarks.

Works out why a superpowers session went wrong: repeated work, ignored plans or a skill that did not fire.

Splits two or more independent tasks across parallel agents when they share no state.

Executes an implementation plan in the current session, step by step.

Guides the choice of how to integrate finished work once tests pass: merge, pull request or cleanup.

Handles code review feedback with technical rigour, verifying suggestions before implementing them.

Requests a code review to verify that completed work meets its requirements before merging.

Executes an implementation plan by handing independent tasks to subagents within the current session.

Makes the agent find the root cause of a bug, test failure or unexpected behaviour before it proposes a fix.

Makes the agent write a failing test before any implementation code, for features and bug fixes alike.

Sets up an isolated workspace with git worktrees before feature work or plan execution begins.

Requires the agent to run verification commands and confirm the output before it claims that work is complete or passing.

Writes a step-by-step implementation plan from a spec or requirements before any code is touched.

Guides creating, editing and testing skills before they are deployed.

Reviews the changes since a commit or branch on two axes: the repo's coding standards and the originating spec.

Gives the agent a shared vocabulary for designing deep modules, deciding interfaces and making code easier to test.

Runs a diagnosis loop for hard bugs and performance regressions.

Builds and sharpens a project's domain model through a glossary and ADRs.

Implements in code what the to-spec and to-tickets skills produced.

Implements a piece of work in code, working from a spec or a set of tickets.

Scans a codebase for chances to deepen modules, shows them in an HTML report, then interviews you about the one you pick.

Writes the body of a pull request so that reviewers can follow the change.

Builds a throwaway prototype to answer a design question about a state model, logic or UI.