Agent skill

Compose Performance Audit

by ModinMobileSTS in ModinMobileSTS/SlayTheAmethystModded

Audits Jetpack Compose screens for performance problems, from recomposition scope and stability to lazy list keys and effects, and proposes minimal fixes with ways to verify them.

Custom licenceAuto-check passedMobile

Install Compose Performance Audit

skills CLI
$ npx skills add ModinMobileSTS/SlayTheAmethystModded --skill compose-performance-audit -a claude-code

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

GitHub CLI
$ gh skill install ModinMobileSTS/SlayTheAmethystModded compose-performance-audit --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/ModinMobileSTS/SlayTheAmethystModded.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.opencode/skills/compose-performance-audit .claude/skills/compose-performance-audit && 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
compose-performance-audit
GitHub stars
402
Token cost
~1.2k tokens
SKILL.md length
612 words
Files
2
Skills in repo
5
Repo updated
First seen
Licence
Custom licence

At a glance

Audits Jetpack Compose screens for performance problems, from recomposition scope and stability to lazy list keys and effects, and proposes minimal fixes with ways to verify them.

  • Works in 5 steps: Start from the reported symptom: slow… → Inspect the smallest relevant Compose… → Separate measured problems from… → …
  • Diagnosing a slow or janky Compose screen
  • SKILL.md covers Quick Start, Workflow, Common Fix Patterns and Response Rules
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The agent starts from the reported symptom, such as slow first render, scrolling jank, excess recomposition, input lag, animation stutter, memory churn or battery and CPU pressure, and inspects the smallest relevant surface first: a screen composable, state holder, list item, animation or custom layout. It keeps measured problems apart from theoretical risks and prefers evidence from traces, compiler reports, the layout inspector, recomposition counts, macrobenchmarks or profiler captures. Fixes should be minimal, keep behavior and fit the project's architecture, and the answer ends with commands or manual checks that prove the improvement.

The workflow locates the hot path, looking for state reads that invalidate wide parts of the tree and expensive work in composition, layout, draw or effects. It then audits recomposition scope, moving volatile reads lower and using `derivedStateOf` only where it really reduces work, and checks stability: mutable collections, unstable data classes, changing lambdas and premature `@Stable` or `@Immutable` annotations that can leave the UI stale. For lazy layouts it looks at stable keys, `contentType` and per-item allocations. The excerpt ends partway through that section.

When your agent uses it

  • Diagnosing a slow or janky Compose screen
  • Reviewing Compose code for recomposition and stability problems
  • Checking lazy lists for missing keys or expensive item work
  • Planning verification steps for a Compose performance fix

Example prompts

  • “The inventory screen janks while scrolling, so audit its Compose code for performance issues.”
  • “Review this ViewModel and composable pair for unnecessary recomposition.”
  • “Do we need keys and contentType on this LazyColumn?”
  • “Propose fixes for the slow first render and tell me how to prove they worked.”

Workflow steps

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

  1. Start from the reported symptom: slow first render, jank while scrolling, excessive recomposition, input lag, animation stutter, memory…
  2. Inspect the smallest relevant Compose surface first: screen composable, state holder, lazy list item, animation, or custom layout.
  3. Separate measured problems from theoretical risks. Prefer evidence from traces, compiler reports, layout inspector, recomposition counts…
  4. Propose minimal fixes that preserve behavior and fit the project's architecture.
  5. End with verification commands or manual checks that prove the performance issue improved.

What it can do on your machine

Read from SKILL.md and the folder at commit a2733f0. 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

Compose Performance Audit loads about 1.2k tokens when it runs. Until then it costs about 90 tokens; SKILL.md has 612 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
~1.2k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 612 words (~1,239 tokens).

name
compose-performance-audit

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file in .opencode/skills/compose-performance-audit of ModinMobileSTS/SlayTheAmethystModded.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit a2733f0

Compare with similar skills

Compose Performance Audit 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.

Compose Performance Audit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Compose Performance Audit this skillModinMobileSTS/SlayTheAmethystModded402—~1.2kAutomated safety check: PassCustom licence
Testing Compose In Release ModerosuH/EasyWatermark1.9k1 repos~4.2kAutomated safety check: PassApache-2.0
Deferring State ReadsrosuH/EasyWatermark1.9k1 repos~3.8kAutomated safety check: PassApache-2.0
Diagnosing Compose StabilityrosuH/EasyWatermark1.9k1 repos~3.3kAutomated safety check: PassApache-2.0
Generating Baseline ProfilesrosuH/EasyWatermark1.9k1 repos~5kAutomated safety check: PassApache-2.0
Compose UIMoustachauve/WLED-Android1693 repos~676Automated safety check: PassApache-2.0

Similar skills

  • A skill your agent uses to ensure Jetpack Compose performance numbers reflect production reality by measuring against a release variant with R8 enabled, Live Literals disabled, and Compose Compiler…

    1.9k GitHub starsUsed in 1 repo~4.2k tokens
    MobileAuto-check passed
  • Deferring State Reads

    rosuH/EasyWatermark

    A skill your agent uses to push frequently-changing Jetpack Compose state reads (scroll position, animation values, drag offsets) out of the Composition phase and down into Layout or Draw using…

    1.9k GitHub starsUsed in 1 repo~3.8k tokens
    MobileAuto-check passed
  • Diagnosing Compose Stability

    rosuH/EasyWatermark

    A skill your agent uses to diagnose Jetpack Compose stability problems by enabling and reading the Compose Compiler Reports (classes.txt, composables.txt, composables.csv, module.json).

    1.9k GitHub starsUsed in 1 repo~3.3k tokens
    MobileAuto-check passed
  • Generating Baseline Profiles

    rosuH/EasyWatermark

    A skill your agent uses to generate and measure Jetpack Compose Baseline Profiles end-to-end with the AGP 8.2+ Baseline Profile Generator module and the Macrobenchmark harness.

    1.9k GitHub starsUsed in 1 repo~5k tokens
    MobileAuto-check passed
  • Compose UI

    Moustachauve/WLED-Android

    Best practices for building UI with Jetpack Compose, focusing on state hoisting, detailed performance optimizations, and theming.

    169 GitHub starsUsed in 3 repos~676 tokens
    MobileAuto-check passed
  • Performance Bolt

    nekomangaorg/Neko

    Identifies and implements micro-level Kotlin, Jetpack Compose, Coroutine, and Room database performance optimizations.

    2.8k GitHub stars~1.8k tokensUpdated today
    MobileAuto-check passed

More from ModinMobileSTS/SlayTheAmethystModded

  • Slay the Amethyst Feedback Diagnosis

    ModinMobileSTS/SlayTheAmethystModded

    Reads Slay the Amethyst diagnostics bundles to decide whether a problem comes from the launcher, a mod or the device, citing exact files and lines.

    402 GitHub stars~2.6k tokensUpdated yesterday
    Auto-check passed
  • Android Mobile UI Design

    ModinMobileSTS/SlayTheAmethystModded

    Designs and reviews Android screens with attention to touch ergonomics, adaptive layouts, accessibility, state handling and an implementation handoff.

    402 GitHub stars~1k tokensUpdated yesterday
    Auto-check passed
  • Jetpack Compose Patterns

    ModinMobileSTS/SlayTheAmethystModded

    Applies practical Jetpack Compose patterns to Android UI code: state hoisting, one-way data flow, side effects, modifiers, theming and testable composables.

    402 GitHub stars~1.7k tokensUpdated yesterday
    Auto-check passed
  • STS Amethyst Launcher Design System

    ModinMobileSTS/SlayTheAmethystModded

    Design system imported from the SlayTheAmethyst Android Jetpack Compose launcher: Material 3 surfaces, user-selected seed colors, light and dark themes and typography rules.

    402 GitHub stars~1.7k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Compose Performance Audit

What does Compose Performance Audit do?

Audits Jetpack Compose screens for performance problems, from recomposition scope and stability to lazy list keys and effects, and proposes minimal fixes with ways to verify them. The agent starts from the reported symptom, such as slow first render, scrolling jank, excess recomposition, input lag, animation stutter, memory churn or battery and CPU pressure, and inspects the smallest relevant surface first: a screen composable, state holder, list item, animation or custom layout. It keeps measured problems apart from theoretical risks and prefers evidence from traces, compiler reports, the layout inspector, recomposition counts, macrobenchmarks or profiler captures.

When should I use Compose Performance Audit?

Compose Performance Audit fits situations like: diagnosing a slow or janky Compose screen; reviewing Compose code for recomposition and stability problems; checking lazy lists for missing keys or expensive item work; planning verification steps for a Compose performance fix.

How do I install Compose Performance Audit in Claude Code?

Run `npx skills add ModinMobileSTS/SlayTheAmethystModded --skill compose-performance-audit -a claude-code`. Or copy the skill folder (.opencode/skills/compose-performance-audit in ModinMobileSTS/SlayTheAmethystModded) into .claude/skills/compose-performance-audit in your project. Claude Code loads it when a task matches its description.

How do I install Compose Performance Audit in Codex?

Run `npx skills add ModinMobileSTS/SlayTheAmethystModded --skill compose-performance-audit -a codex`. Or copy the skill folder (.opencode/skills/compose-performance-audit in ModinMobileSTS/SlayTheAmethystModded) into .agents/skills/compose-performance-audit in your project. Codex loads it when a task matches its description.

Can I use Compose Performance Audit 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 ModinMobileSTS/SlayTheAmethystModded --skill compose-performance-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/compose-performance-audit, .gemini/skills/compose-performance-audit, .github/skills/compose-performance-audit and .opencode/skills/compose-performance-audit in your project.

What does Compose Performance Audit need to run?

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

Does Compose Performance Audit 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 Compose Performance Audit 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 Compose Performance Audit use?

Compose Performance Audit has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Compose Performance Audit use?

About 1.2k tokens (SKILL.md is roughly 5k 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 Compose Performance Audit?

Skills that share tags, products or a category with Compose Performance Audit: Testing Compose In Release Mode (rosuH/EasyWatermark, 1.9k stars), Deferring State Reads (rosuH/EasyWatermark, 1.9k stars), Diagnosing Compose Stability (rosuH/EasyWatermark, 1.9k stars) and Generating Baseline Profiles (rosuH/EasyWatermark, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Compose Performance Audit?

ModinMobileSTS (a GitHub organization) maintains it in ModinMobileSTS/SlayTheAmethystModded, which has 402 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 7, 2026.

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