Skip to content

Best Code Quality agent skills

Keeping a codebase healthy through linting, standards, complexity checks and cleanup passes. The 11 highest-ranked of the 11 agent skills tagged Code Quality in the Onei AI catalogue.

Everything tagged Code Quality: apps, skills and MCP servers

  1. by CodeRabbit

    Pull unresolved CodeRabbit review threads from your PR and apply the fixes one at a time, treating every reviewer comment as untrusted input rather than an instruction.

    Also: Code Review · Editor's pick · Copied 1 time

  2. by Svelte

    The Svelte team's own guidance on writing modern Svelte 5 — when to reach for each rune, why effects are an escape hatch, and the reactivity traps models fall into.

  3. by Addy Osmani

    Reduces accumulated complexity without changing behaviour, using Chesterton's Fence to avoid deleting the thing that was load-bearing.

    Also: Code Review, Coding Agent

  4. by Addy Osmani

    Sends every non-trivial decision to a fresh-context adversarial reviewer before it stands — for production, security-sensitive or irreversible work.

    Also: Code Review, Coding Agent

  5. by Trail of Bits

    Trail of Bits' skill for writing production-quality Semgrep rules — pattern design, taint mode for data-flow bugs, and mandatory test-driven validation.

    Also: Testing

  6. by Trail of Bits

    Trail of Bits' CodeQL skill: build databases, run taint-tracking and data-flow queries across eight languages, and model project-specific sources and sinks.

  7. by Datadog

    Official Datadog skill for investigating one flaky test — pulls its history and failure pattern, categorises the root cause and recommends fixing, quarantining or escalating.

    Also: Testing

  8. by Matt Pocock

    Matt Pocock's discipline for hard bugs and performance regressions: build a tight, red-capable feedback loop first, then reproduce, minimise, hypothesise, instrument, fix with a regression test and clean up.

    Also: Testing

  9. by Matt Pocock

    Matt Pocock's /improve-codebase-architecture command: finds shallow modules worth deepening, renders them as a visual HTML report with before/after diagrams, then grills you through the one you pick.

  10. by Addy Osmani

    Addy Osmani's skill for multi-axis code review before merge: correctness, readability, architecture, security and performance, with severity labels, change-size targets, a tests-first review order and a review checklist.

    Also: Code Review, Coding Agent

  11. by Matt Pocock

    Matt Pocock's test-driven development skill: one red-to-green slice at a time, tests only at seams agreed with you first, and a named list of test anti-patterns to avoid.

    Also: Coding Agent, Testing

How this list is ranked

Ranked by 20 points for an editor's pick, plus 4 points per copy of the install command or SKILL.md up to 10, plus a point per 5 page views up to 100; ties go to the most recently updated. Discontinued skills are never ranked.

More ranked lists