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 Android

ASecurity

Coordinates Android/Kotlin/Jetpack Compose/Gradle/Media3 work. Use for Android UI, playback, services, device behavior, build/toolchain, R8, Room/data access, testing, edge-to-edge, adaptive layout, localization, performance, or runtime debugging. Prefer official Google Android skills/CLI when installed and use device or emulator evidence for runtime-specific acceptance.

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

Works with

cliapi

Security Analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned 9/19/2026

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

Installs into .claude/skills of the current project.

Are you the author of Thalarch Android?

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

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

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-android
description: >
  Coordinates Android/Kotlin/Jetpack Compose/Gradle/Media3 work. Use for Android UI, playback,
  services, device behavior, build/toolchain, R8, Room/data access, testing, edge-to-edge, adaptive
  layout, localization, performance, or runtime debugging. Prefer official Google Android skills/CLI
  when installed and use device or emulator evidence for runtime-specific acceptance.
---

# Thalarch Android

## Android lens

Prefer official current Android skills/tooling available in the environment for version-sensitive
platform facts. Thalarch supplies scope control, regression safety, causal reasoning, routing, and
proof discipline around them.

## Preflight

Inspect:

- module graph;
- Gradle/AGP/Kotlin/version catalog;
- manifests;
- Compose/navigation/state patterns;
- Media3/session/service/player ownership when playback is involved;
- Room/repository/data-source boundaries when persistence is involved;
- locale/resource structure when user-facing text changes;
- CI build tasks;
- device/runtime requirements.

Do not upgrade toolchain or libraries unless the task requires it.

## Specialist routing

Use the smallest relevant stack rather than loading every Android skill.

- Media3, ExoPlayer, `MediaSession`, `MediaLibrarySession`, Android Auto, queue/timeline, audio/video
  track selection, cache/preload/recovery, or audio-processing pipeline → `thalarch-media3`;
- Compose redesign/product UI/settings/media surfaces → `thalarch-compose-ui`, plus
  `thalarch-design-system` when visual direction needs extraction or re-articulation;
- fuzzy title/artist/catalog/provider identity resolution → `thalarch-entity-matching`;
- user-facing strings, locale resources, RTL, placeholder parity, translation completeness →
  `thalarch-localization`;
- a working subsystem where a narrow change could break adjacent behavior → `thalarch-no-regression`;
- measured/suspected CPU, allocation, memory, cache, build, or hot-path cost → `thalarch-performance`;
- Room/SQL query-shape and persistence work → `thalarch-data-sql` as needed;
- version-sensitive deprecations/API migrations → `thalarch-source-grounding` plus the Android
  deprecation playbook below.

## No-Regression Contract

For playback, cache, persistence, sync, migration, concurrency, or other high-blast-radius surfaces,
use `thalarch-no-regression` before mutation.

Capture the local must-preserve behaviors, the suspected problem, evidence state, intended action
(`AUDIT ONLY` vs targeted mutation), and the verification needed.

A similar fix in another application is evidence to investigate, not evidence that this repository
has the same defect.

## Compose

Check:

- state ownership/stability;
- effects/lifecycle;
- recomposition-sensitive work;
- lazy keys;
- edge-to-edge/insets;
- adaptive behavior;
- touch targets/semantics;
- theme consistency;
- localization/truncation;
- RTL/AutoMirrored directional icons;
- font scaling;
- rendered behavior on the actual supported device classes.

For substantial Compose work, use `thalarch-compose-ui` rather than treating source review as visual
proof.

## Media/runtime

For Media3/playback/services inspect:

- lifecycle/session ownership;
- cancellation;
- buffering/retry;
- cache;
- queue/timeline invariants;
- audio focus;
- service process/state;
- resolver/network fallback ordering;
- audio-only vs video-capable selection;
- preload/recovery loops;
- DSP/audio-processor ordering when relevant.

Route substantial Media3 work to `thalarch-media3`.

Do not cure state bugs with arbitrary delays without evidence.

## Performance and cache

When the task touches memory, cache, hot paths, playback churn, jank, or repeated work, read:

- `references/android-performance.md`

Audit for concrete work such as repeated regex compilation, collection scans, Room N+1 queries,
full-cache enumeration, polling loops, listener/job leaks, oversized artwork, recomposition-heavy
work, native/media allocation churn, or unnecessary video decoding during audio-only playback.

For a cache that currently works, combine `thalarch-performance` with `thalarch-no-regression` and
presume its current semantics must be preserved until a defect/inefficiency is demonstrated.

## Room and pagination

When a caller exposes paging (`page` / `pageSize`) and the backing collection can be large, trace the
paging contract all the way to the data source. Read:

- `references/room-pagination.md`

Do not claim real pagination when the implementation loads the full dataset and truncates it after
the fact. Preserve ordering, identity, filtering, and browsing semantics; test empty, partial,
>1000-row, duplicate/ordering, and adjacent-page boundaries where relevant.

## Deprecation migration

For compiler deprecations or override-signature warnings, read:

- `references/deprecation-migration.md`

Ground the exact installed dependency version, prove the official replacement, migrate minimally,
and preserve runtime semantics. Do not use suppression as a substitute for a valid supported
migration.

## Localization

When new or changed user-facing text is introduced, use `thalarch-localization` to verify locale
inventory, key and placeholder parity, natural domain terminology, layout expansion, and RTL.

A default-locale build does not prove translation completeness or unclipped UI.

## Proof hierarchy

Compilation proves compilation only.

For runtime/UI behavior use, where available:

- targeted unit/integration tests;
- instrumentation;
- emulator/device interaction;
- Android Auto/head-unit/controller interaction when relevant;
- `adb`/log evidence;
- screenshots/recordings for visual claims;
- profiling/trace evidence for performance claims.

Keep unavailable runtime/device evidence explicitly `UNVERIFIED` rather than upgrading a source-only
inference into PASS.

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".

1074701 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', ...

696561 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.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, 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.

691 votes
View all in ai-agents →