Deft
Ask AI

Search

Search skills, authors and topics

Code quality

Maintainability reviews, abstraction cleanup, and deep code health work.

  • unlazy

    Anti-laziness execution discipline that finishes substantial tasks through gate files and runnable checks instead of premature done reports.

  • simple-english

    Write or rewrite technical text with ASD-STE100 Simplified Technical English for clear, unambiguous, translation-friendly documentation and interface copy.

  • gh-stack

    Manage stacked branches and dependent pull requests with the gh stack GitHub CLI extension.

  • interface-review

    Interface review of a change rather than a screen: uncommitted work, the current branch, or a pull request. Covers interface quality, not correctness, tests, or security.

  • linear-discipline

    Keep Linear tracking honest during development with search-before-create, lifecycle updates, and close-the-loop discipline.

  • improve

    Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or take the project next, or generate handoff plans for another agent to implement.

  • write-swift

    How to write modern Swift well — modeling with value types, Swift 6 data-race safety and approachable concurrency (@concurrent, main-actor-by-default, actors, task groups), protocols and generics (some vs any), API design, performance and ARC, Swift Testing, macros, and the modern language features agents don't know about yet. Use when writing, reviewing, or migrating Swift, or when a concurrency error, a hang, a data race, a retain cycle, or a performance problem needs fixing.

  • rams

    Design review for UI code. Reviews React, Vue, Svelte, CSS, and SwiftUI for accessibility, typography, spacing, color, and component quality, with severity-rated findings, concrete fixes, and a 0-100 score.

  • improve-react

    Survey a React codebase using React Doctor's findings, then produce prioritized audits and self-contained implementation plans without modifying source code.