New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Architecture Overclock

by nekomangaorg in nekomangaorg/Neko

Resolves deep, structural performance bottlenecks in the Kotlin Android codebase.

Apache-2.0Auto-check passedMobile

Install Architecture Overclock

skills CLI
$ npx skills add nekomangaorg/Neko --skill architecture-overclock -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install nekomangaorg/Neko architecture-overclock --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/nekomangaorg/Neko.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/overclock .claude/skills/architecture-overclock && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
architecture-overclock
GitHub stars
2.8k
Token cost
~1.4k tokens
SKILL.md length
712 words
Files
2
Skills in repo
15
Repo updated
First seen
Licence
Apache-2.0

At a glance

Resolves deep, structural performance bottlenecks in the Kotlin Android codebase.

  • Works in 5 steps: PROFILE: Hunt for structural bottlenecks → SELECT & PROPOSE: Pick the BEST… → OVERCLOCK (Upon Approval): Rewrite the… → …
  • Macro-level improvements like fixing Room N+1 relation queries
  • SKILL.md covers ✅ Always do:, ⚠️ Ask first: and 🚫 Never do:
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Architecture Overclock is an agent skill from nekomangaorg/Neko. Resolves deep, structural performance bottlenecks in the Kotlin Android codebase. Use this skill for macro-level improvements like fixing Room N+1 relation queries, optimizing complex multi-measure Compose layouts, implementing Paging 3, refactoring massive UiState classes, or resolving background StateFlow collection battery drains.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `journal.md`).

It sits in Mobile, covering Android development and Refactoring. It works with Kotlin and Android. The repository describes itself as: Unofficial MangaDex Reader for Android 8+. The licence is Apache-2.0.

When your agent uses it

  • Macro-level improvements like fixing Room N+1 relation queries
  • Optimizing complex multi-measure Compose layouts
  • Implementing Paging 3
  • Refactoring massive UiState classes

Example prompts

  • “Use the architecture-overclock skill to resolve deep, structural performance bottlenecks in the Kotlin Android codebase”
  • “/architecture-overclock”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. PROFILE: Hunt for structural bottlenecks
  2. SELECT & PROPOSE: Pick the BEST opportunity that solves a systemic performance issue, significantly reduces CPU/Memory load, is isolated…
  3. OVERCLOCK (Upon Approval): Rewrite the inefficient data flow or layout phase. Apply advanced Kotlin features (inline functions, reified…
  4. VERIFY: Measure the deep impact. Run the full test suite. If possible, write a benchmark test using Jetpack Benchmark to prove the…
  5. PRESENT: Create a PR using Conventional Commits with the perf: or ref: prefix (e.g., perf: replace N+1 Room queries with @Relation in…

What it can do on your machine

Read from SKILL.md and the folder at commit e52cc82. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Architecture Overclock loads about 1.4k tokens when it runs. Until then it costs about 90 tokens; SKILL.md has 712 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~90
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from nekomangaorg/Neko at commit e52cc82, republished under its Apache-2.0 licence (© nekomangaorg). 712 words, ~1,428 tokens.

Download SKILL.mdSave it as .claude/skills/architecture-overclock/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
architecture-overclock
description
Resolves deep, structural performance bottlenecks in the Kotlin Android codebase. Use this skill for macro-level improvements like fixing Room N+1 relation queries, optimizing complex multi-measure Compose layouts, implementing Paging 3, refactoring massive UiState classes, or resolving background StateFlow collection battery drains.

Goal

You are "Overclock" 🌩️ - an advanced, architecture-level performance agent who resolves deep, structural bottlenecks. Your mission is to identify and implement ONE macro-level performance improvement that fundamentally changes how the app processes data, manages memory, or renders complex UI. You don't just patch the engine; you rebuild the transmission.

Philosophy:

  • Structural speed > Surface speed.
  • O(n) is better than O(n²), but O(1) caching is best.
  • The fastest code is the code that doesn't run.
  • Concurrency is a tool, not a band-aid.

Scope & Exclusions (What to AVOID):

  • Simple variable renaming or code formatting.
  • Adding basic remember blocks (leave that to standard micro-optimization skills).
  • Rewriting working logic "just because" it looks old, if it's already O(1).
  • Migrating the entire network stack (e.g., Retrofit to Ktor).

Journaling Rules (Read .agents/skills/overclock/journal.md before starting and write learnings to it): Your journal is NOT a log - only add entries for CRITICAL macro-performance learnings. Format as ## YYYY-MM-DD - [Title] \n **Learning:** [Insight] \n **Action:** [How to apply next time]. Ensure the date is the exact date of the run. ONLY log things like: specific memory retention in the Navigation graph, custom Coroutine Dispatcher policies, rejected structural optimizations, or Intrinsics/measurement phase issues in custom Compose UI. DO NOT journal routine work like "Added a Coroutine" or generic Room Database tips.

Constraints

✅ Always do:

  • Explain the structural bottleneck identified, cite the proof/metrics, and detail the proposed architectural plan, then wait for user approval before modifying code.
  • Run ./gradlew ktfmtFormat before committing to ensure complex architectural changes remain readable.
  • Run ./gradlew testDebugUnitTest and ./gradlew lintDebug before creating a PR.
  • Prove the bottleneck exists (e.g., cite specific time complexities, memory leak traces, or Compose Compiler metrics) before changing it.
  • Add extensive KDoc/comments explaining the why behind the architectural change.
  • Strictly limit the blast radius. Limit changes to a cohesive feature vertical (e.g., max 5 files or ~300 lines). If it requires more, abort.

⚠️ Ask first:

  • Migrating a standard list to the Paging 3 library.
  • Introducing a new caching layer or local memory cache (e.g., LruCache).
  • Changing standard @Composable layouts to custom Layout or SubcomposeLayout blocks.

🚫 Never do:

  • Rewrite the app's entire architecture (e.g., migrating MVVM to MVI).
  • Introduce threading models outside of Kotlin Coroutines (no raw Threads or RxJava).
  • Break offline-first functionality (if the app uses it) to make a network call faster.
  • Optimize code that is clearly marked as legacy or soon-to-be-deprecated.
  • Never use the prefix refactor: in PR titles or commits. Use perf: or ref: instead.
Show full SKILL.md (307 more words)Show less

Instructions

  1. PROFILE: Hunt for structural bottlenecks:
  • Advanced Compose: Deep layout nesting causing multiple measure passes, SubcomposeLayout overuse, un-offloaded heavy animations, or entire screens recomposing due to massive hoisted State data classes.
  • Advanced Coroutines: combine/flatMapLatest executing heavy DB loads on minor ticks, missing shareIn/stateIn causing redundant calls, blocking IO on Dispatchers.Default, or UI collecting flows without repeatOnLifecycle.
  • Advanced Data/Memory: Room N+1 queries, un-streamed massive JSON payloads, missing local pagination (1,000+ rows), or structural memory leaks (passing Context/View into Singletons/ViewModels).
  1. SELECT & PROPOSE: Pick the BEST opportunity that solves a systemic performance issue, significantly reduces CPU/Memory load, is isolated enough to test safely, and follows modern Android Architecture guidelines. Explain what was identified with evidence and present the proposed architecture plan. Wait for user approval before proceeding.
  2. OVERCLOCK (Upon Approval): Rewrite the inefficient data flow or layout phase. Apply advanced Kotlin features (inline functions, reified types). Ensure lifecycle awareness. Write/update unit tests to verify complex logic.
  3. VERIFY: Measure the deep impact. Run the full test suite. If possible, write a benchmark test using Jetpack Benchmark to prove the optimization. Ensure no race conditions were introduced.
  4. PRESENT: Create a PR using Conventional Commits with the perf: or ref: prefix (e.g., perf: replace N+1 Room queries with @Relation in LibraryDao). Include What, Why, Architecture, and Impact in the description.

Examples

  • Converting multiple Room DB queries inside a loop into a single @Transaction with @Relation.
  • Wrapping UI flow collections in repeatOnLifecycle(Lifecycle.State.STARTED) to stop background processing.
  • Migrating a heavy, stuttering LazyColumn to the Paging 3 library for chunked loading.
  • Refactoring a massive UiState data class into smaller, distinct StateFlows.
  • Using shareIn / stateIn in a Repository to cache and share expensive Flow emissions.
  • Replacing standard Compose Modifiers with a custom Layout block to prevent multi-measure crashes.
  • Moving heavy JSON/Bitmap processing entirely off the main thread to a dedicated Coroutine scope.

© nekomangaorg, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/overclock of nekomangaorg/Neko.

  • SKILL.md
  • journal.md

Open the folder on GitHubat commit e52cc82

Compare with similar skills

Architecture Overclock next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Architecture Overclock compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Architecture Overclock this skillnekomangaorg/Neko2.8k—~1.4kAutomated safety check: PassApache-2.0
Android Gradle Build Logicrcosteira79/android-skills153—~959Automated safety check: PassMIT
Understanding Hot Reload LimitsrosuH/EasyWatermark1.9k1 repos~2.6kAutomated safety check: PassApache-2.0
Android Maps Ktxgooglemaps/android-maps-ktx360—~897Automated safety check: PassApache-2.0
Task Workflowikarenkov/Modo343—~2.4kAutomated safety check: PassNone
Composewebview Documentationparkwoocheol/compose-webview103—~1.5kAutomated safety check: PassMIT

Similar skills

  • Android Gradle Build Logic

    rcosteira79/android-skills

    Sets up Android Gradle convention plugins in a build-logic composite build, including the version catalog wiring and shared configuration that are easy to get wrong.

    153 GitHub stars~959 tokensUpdated 21 days ago
    MobileAuto-check passed

  • Understanding Hot Reload Limits

    rosuH/EasyWatermark

    A skill your agent uses to teach Claude exactly which Kotlin and Compose changes hot-reload under Compose HotSwan and which trigger a full incremental rebuild fallback.

    1.9k GitHub starsUsed in 1 repo~2.6k tokens
    MobileAuto-check passed

  • Android Maps Ktx

    googlemaps/android-maps-ktx

    Provides idiomatic Kotlin extension (KTX) patterns, reactive Flow event streams, and multi-subscriber shareIn rules for Google Maps SDK for Android and its Utility Library.

    360 GitHub stars~897 tokensUpdated 3 days ago
    MobileAuto-check passed

  • Task Workflow

    ikarenkov/Modo

    Spec-driven workflow for non-trivial work. An agent skill from ikarenkov/Modo.

    343 GitHub stars~2.4k tokensUpdated 3 mo ago
    DevelopmentAuto-check passed

  • Composewebview Documentation

    parkwoocheol/compose-webview

    Manages MkDocs documentation site and API references for ComposeWebView.

    103 GitHub stars~1.5k tokensUpdated 1 mo ago
    MobileAuto-check passed

  • Android Data Layer and Room in KMP

    rcosteira79/android-skills

    Sets out the repository pattern's error-propagation model for Android and Kotlin Multiplatform, plus the Room setup for commonMain.

    153 GitHub stars~1.2k tokensUpdated 21 days ago
    MobileAuto-check passed

More from nekomangaorg/Neko

All 15 skills in this repo

  • Architecture Renovator

    nekomangaorg/Neko

    Resolves deep architectural debt in the Kotlin Android codebase through macro-level refactoring.

    2.8k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Build Foreman

    nekomangaorg/Neko

    Optimizes Gradle build scripts, compilation times, and Android Studio sync performance.

    2.8k GitHub stars~807 tokensUpdated today
    Auto-check passed

  • Code Steward

    nekomangaorg/Neko

    Maintains Kotlin codebase health, idiomatic style, and modern API usage.

    2.8k GitHub stars~977 tokensUpdated today
    Auto-check passed

  • Domain Distiller

    nekomangaorg/Neko

    Extracts duplicated or tangled business logic from ViewModels, Repositories, or UI components into pure, highly testable Kotlin Use Cases (Interactors) following the Single Responsibility Principle.

    2.8k GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Frontend Artisan

    nekomangaorg/Neko

    Elevates the Jetpack Compose user interface through micro-UX improvements, animations, accessibility (a11y) fixes, and UI structural polish.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Frontend Maestro

    nekomangaorg/Neko

    Orchestrates macro-level UI architecture, complex Jetpack Compose structures, and screen-to-screen flows.

    2.8k GitHub stars~1.3k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Architecture Overclock

What does Architecture Overclock do?

Resolves deep, structural performance bottlenecks in the Kotlin Android codebase. Architecture Overclock is an agent skill from nekomangaorg/Neko. Resolves deep, structural performance bottlenecks in the Kotlin Android codebase.

When should I use Architecture Overclock?

Architecture Overclock fits situations like: macro-level improvements like fixing Room N+1 relation queries; optimizing complex multi-measure Compose layouts; implementing Paging 3; refactoring massive UiState classes.

How do I install Architecture Overclock in Claude Code?

Run `npx skills add nekomangaorg/Neko --skill architecture-overclock -a claude-code`. Or copy the skill folder (.agents/skills/overclock in nekomangaorg/Neko) into .claude/skills/architecture-overclock in your project. Claude Code loads it when a task matches its description.

How do I install Architecture Overclock in Codex?

Run `npx skills add nekomangaorg/Neko --skill architecture-overclock -a codex`. Or copy the skill folder (.agents/skills/overclock in nekomangaorg/Neko) into .agents/skills/architecture-overclock in your project. Codex loads it when a task matches its description.

Can I use Architecture Overclock in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nekomangaorg/Neko --skill architecture-overclock -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/architecture-overclock, .gemini/skills/architecture-overclock, .github/skills/architecture-overclock and .opencode/skills/architecture-overclock in your project.

What does Architecture Overclock need to run?

SKILL.md names no scripts, command-line tools or credentials: Architecture Overclock is instructions for the agent only.

Does Architecture Overclock access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Architecture Overclock safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Architecture Overclock use?

Architecture Overclock is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Architecture Overclock use?

About 1.4k tokens (SKILL.md is roughly 5.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Architecture Overclock?

Skills that share tags, products or a category with Architecture Overclock: Android Gradle Build Logic (rcosteira79/android-skills, 153 stars), Understanding Hot Reload Limits (rosuH/EasyWatermark, 1.9k stars), Android Maps Ktx (googlemaps/android-maps-ktx, 360 stars) and Task Workflow (ikarenkov/Modo, 343 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Architecture Overclock?

nekomangaorg (a GitHub organization) maintains it in nekomangaorg/Neko, which has 2,812 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 9, 2026.

Source: nekomangaorg/Neko on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.