Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Thalarch Kotlin

ASecurity

Project-aware Kotlin engineering for JVM, Android, server, and multiplatform code. Use for Kotlin source, coroutines/Flow, Gradle Kotlin projects, Compose when present, KMP boundaries, testing, performance, interoperability, and Kotlin-specific refactoring.

2 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsjavakotlintestingrefactoringapiperformance

Works with

api

Security Analysis

A100/100

Scanned 9/19/2026

$npx -y skills add LUC4N3X/antigravity-thalarch --skill thalarch-kotlin --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Thalarch Kotlin?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Thalarch Kotlin
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/luc4n3x-thalarch-kotlin/badge)](https://www.skillsdirectory.com/skills/luc4n3x-thalarch-kotlin)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: thalarch-kotlin
description: >
  Project-aware Kotlin engineering for JVM, Android, server, and multiplatform code. Use for
  Kotlin source, coroutines/Flow, Gradle Kotlin projects, Compose when present, KMP boundaries,
  testing, performance, interoperability, and Kotlin-specific refactoring.
---

# Thalarch Kotlin

Use the Kotlin version, target platforms, compiler options, and libraries declared by the
repository. Do not assume Android, Compose, KMP, coroutines, KSP, or a specific architecture.

## Preflight

Identify:

- Kotlin/compiler/plugin version;
- JVM/Android/Native/JS/multiplatform targets;
- Gradle wrapper and version catalogs;
- coroutine/serialization/Compose/KSP/KAPT usage;
- test libraries and configured lint/static-analysis tools;
- Java interoperability requirements.

Preserve the existing build model unless the task explicitly changes it.

## Idiomatic Kotlin

Prefer language features when they improve clarity rather than merely shorten code:

- null-safe operators and explicit boundary validation instead of routine `!!`;
- data/value classes for real value semantics;
- sealed types for closed state/result models;
- exhaustive `when` where it strengthens correctness;
- collection operators for clear transformations;
- sequences only when laziness materially avoids work/allocation;
- scope functions only when receiver/return semantics stay obvious.

Do not nest scope functions until ownership becomes difficult to read. Do not replace a
simple loop with a chain that hides control flow or allocates unnecessarily on a hot path.

## Coroutines and Flow

Structured concurrency is the default.

Review explicitly:

- scope owner and lifetime;
- dispatcher ownership/injection;
- cancellation propagation;
- exception supervision semantics;
- concurrent mutation/shared state;
- backpressure/buffering;
- hot vs cold stream semantics;
- replay and event-loss behavior;
- blocking work on inappropriate dispatchers.

Avoid `GlobalScope` and detached jobs unless the lifecycle is deliberately process-wide and
documented. Do not launch work from constructors/init blocks without a proven owner.

Never swallow `CancellationException`; if caught by a broad handler, rethrow it unless the
runtime/library contract requires a different explicit mechanism.

Use `async` only for genuine concurrency. An immediate `async { ... }.await()` is usually just
a suspending call with extra machinery.

For state, preserve atomic update semantics and understand whether the code needs `StateFlow`,
`SharedFlow`, Channel, or a cold Flow. Do not treat them as interchangeable.

## Android / Compose overlay

When Android or Compose is actually present, combine this skill with `thalarch-android` and
`thalarch-ui` as appropriate.

Review:

- state ownership/hoisting;
- lifecycle-aware collection;
- effect keys and cancellation;
- `remember`/`derivedStateOf` only where they provide real stability/work savings;
- lazy-list stable keys;
- snapshot state boundaries;
- unnecessary recomposition or expensive work during composition;
- semantics, touch targets, insets, adaptive layouts, localization.

Runtime UI claims require emulator/device/render evidence when possible.

## Multiplatform

For KMP projects:

- keep common code platform-neutral;
- inspect actual source-set hierarchy;
- use `expect/actual` only for true platform boundaries;
- avoid leaking Android/JVM APIs into common code;
- verify at least the affected target(s), not only the host target.

## Java interoperability

Use JVM annotations only when a Java caller/framework actually needs them. Preserve nullability,
SAM, overload, checked-exception, and binary-compatibility behavior across public boundaries.

## Testing

Use repository-native libraries. When present/appropriate:

- `runTest` for suspend/coroutine tests;
- virtual time instead of real sleeps;
- Flow assertions that prove ordering/cancellation/completion;
- Turbine only when it is already installed or justified;
- instrumentation/device tests for Android runtime behavior.

Avoid tests whose only proof is that a mocked collaborator returned the value configured in
the mock.

## Verification

Run the actual Gradle tasks/configured linters/tests for the affected module and target.
Report Kotlin/compiler/target context for any version-sensitive claim.

Attribution

LUC4N3XLUC4N3X
View sourceSee grades on GitHubMore from LUC4N3X →
SSkills Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1087401 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

697551 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →