Is the Auditing Compose Performance skill free?

Yes. The skill itself is free from skydoves/compose-performance-skills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Auditing Compose Performance SkillProof Score?

8.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 5/5.

How do I install Auditing Compose Performance?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Auditing Compose Performance with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Auditing Compose Performance

Orchestrates a four-phase Jetpack Compose performance audit across 25 focused skills

by skydoves · skydoves/compose-performance-skills

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.0/10
Tested: Jul 21, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · e48ab3a

Fetched SKILL.md at audit/auditing-compose-performance/; frontmatter parses with name+description. Spot-checked 3 referenced sibling SKILL.md files plus INDEX.md via raw fetch, all HTTP 200. Read scripts/install-skills.sh: clean idempotent symlink logic (nested category layout means a plain clone won't surface skills, so the script or a targeted cp is required), no curl|sh, base64, or exfiltration. Could NOT run Phase 1: the mandated deliverable is a before/after Macrobenchmark report from a release+R8 build on a physical Android device, none runnable here, so no skill-followed artifact was produced to compare against a baseline.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 5/10
Docs & honesty 5/5

What Auditing Compose Performance does

Orchestrator skill for an end-to-end Jetpack Compose performance audit; it sequences 25 focused skills through a Measure to Diagnose to Fix to Verify loop and produces a written report with before/after Macrobenchmark numbers. Triggers on broad symptoms like "the app feels sluggish", a perf-sprint kickoff, a pre-release perf gate, or when the developer has no specific symptom yet. Running the audit requires a physical Android device and a release + R8 Gradle build for the measurement phases.

How to install Auditing Compose Performance

git clone --depth 1 https://github.com/skydoves/compose-performance-skills.git /tmp/auditing-compose-performance-src
mkdir -p ~/.claude/skills
cp -R /tmp/auditing-compose-performance-src/audit/auditing-compose-performance ~/.claude/skills/auditing-compose-performance
# This is an ORCHESTRATOR: it cross-links 25 sibling skills via ../../ relative paths.
# The copy above installs only the orchestrator; its cross-links to sibling skills will 404.
# To install the full library with working cross-links, run the repo's install script instead:
#   /tmp/auditing-compose-performance-src/scripts/install-skills.sh
# It symlinks all 26 skill folders (flat layout) into ~/.claude/skills/. Restart Claude Code after.
# To actually RUN an audit you also need: a physical Android device, ./gradlew assembleRelease,
# a Macrobenchmark module, Compose Compiler 1.5.5+, Kotlin 2.0.20+, AGP 8.2+.

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Auditing Compose Performance

/auditing-compose-performance Orchestrates a four-phase Jetpack Compose performance audit across 25 focused skills

It also activates on plain-language prompts like these:

Audit why our Compose app feels sluggish
Run a performance sprint on our Android app
Find what's causing rough scrolling in Compose

Frequently asked questions

Is the Auditing Compose Performance skill free?: Yes. The skill itself is free from skydoves/compose-performance-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Auditing Compose Performance work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Works with setup. Fetched SKILL.md at audit/auditing-compose-performance/; frontmatter parses with name+description. Spot-checked 3 referenced sibling SKILL.md files plus INDEX.md via raw fetch, all HTTP 200. Read scripts/install-skills.sh: clean idempotent symlink logic (nested category layout means a plain clone won't surface skills, so the script or a targeted cp is required), no curl|sh, base64, or exfiltration. Could NOT run Phase 1: the mandated deliverable is a before/after Macrobenchmark report from a release+R8 build on a physical Android device, none runnable here, so no skill-followed artifact was produced to compare against a baseline.
What is the Auditing Compose Performance SkillProof Score?: 8.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 5/5.
How do I install Auditing Compose Performance?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Auditing Compose Performance with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.