agentleFS
ayushgoelayushgoel/skills/kotlin-code-reviewer/SKILL.md

kotlin-code-reviewer

Skill1 starsChanged 7 days agoMITView on GitHub

Kotlin-specific extension for review-code. Use alongside the general reviewer when a pull request, branch, diff, or source set contains Kotlin or Kotlin script files. Adds coroutine, null-safety, Kotlin idiom, library-first, architecture, and JVM compatibility checks.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use the review scope established by review-code.

    line 17
  2. Very specific:

    Use rg to inspect callers and consumers of changed public symbols.

    line 23
  3. Distinctive:

    Follow the general review finding threshold.

    line 43

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Kotlin Code Reviewer

Apply this skill as an extension to review-code, which owns the read-only default, evidence standard, severity order, and final response structure.

Select The Diff

Use the review scope established by review-code.

Kotlin Review Workflow

  1. Identify touched modules, layers, public APIs, serialized models, build files, and Java interoperability boundaries.
  2. Use rg to inspect callers and consumers of changed public symbols.
  3. Apply the material checks in references/review-framework.md.
  4. Use references/kotlin-idioms.md for null-safety, collections, coroutines, sealed types, value classes, immutability, extensions, and delegated properties.
  5. Format Kotlin-specific findings using references/output-format.md.

Prioritize production behavior over idiomatic preference. In particular, check:

  • blocking calls, unstructured concurrency, cancellation, dispatcher choice, shared mutable state, and lifecycle leaks
  • nullability contracts, unchecked assertions, exceptions, and result handling
  • API and binary compatibility, serialization changes, Java callers, and event-schema compatibility
  • resource closure, transaction boundaries, retries, timeouts, and idempotency
  • existing stdlib or project-library alternatives before accepting new helpers
  • tests for coroutine timing, cancellation, failure, and changed contracts

Follow the general review finding threshold. Every reported issue needs a concrete correction. Provide a copy-pasteable patch only when it is small and safe. Explain architecture trade-offs only for material design findings.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.