Skip to main content
affpapa.org
RU EN
skill CX Codex

perf-analyzer — Claude Code skill: analysis and setup

Turns profiling and experiment results into evidence-backed performance recommendations. Use it when a decision needs a traceable basis.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add composio-community/awesome-claude-plugins --skill perf-analyzer -a claude-code
npx skills add composio-community/awesome-claude-plugins --skill analyzer -a claude-code
Open on GitHub

What perf-analyzer does

The skill takes baseline data, experiment results, profiling evidence, tested hypotheses, and breaking-point results. It turns them into a concise summary, actionable recommendations, abandoned hypotheses, and next steps.

It follows docs/perf-requirements.md as the canonical contract. Recommendations may use evidence found in logs or code only. When the material is insufficient, the skill asks for the investigation to be run again. Check the source logs before relying on the conclusion.

What it helps with

  • summarize profiling results for a performance decision
  • compare experiment results with tested hypotheses
  • turn log and code evidence into concrete recommendations
  • record experiments that did not support a hypothesis
  • choose next steps after breaking-point tests

Example prompts for the agent

  • Use the skill to turn profile.log and experiment results into performance recommendations.
  • Compare the baseline with the latest experiment and identify the hypothesis that failed.
  • Review the logs and code evidence, then say whether the investigation should be rerun.

How to install perf-analyzer

1Skills CLI (Vercel)

npx skills add composio-community/awesome-claude-plugins --skill perf-analyzer -a claude-code
npx skills add composio-community/awesome-claude-plugins --skill analyzer -a claude-code

2Manually: put the files in place

~/.claude/skills/analyzer/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/analyzer/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about perf-analyzer

How do I install perf-analyzer in Claude Code?

Run npx skills add composio-community/awesome-claude-plugins --skill perf-analyzer -a claude-code, then run npx skills add composio-community/awesome-claude-plugins --skill analyzer -a claude-code. Check ~/.claude/skills/analyzer/SKILL.md afterward.

What does perf-analyzer do?

It turns performance investigation results into a summary, recommendations, abandoned hypotheses, and next steps. The skill uses evidence from logs or code.

Which platforms support perf-analyzer?

The skill is available for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode.

Similar skills

Everything for Testing and QA →
rag-perf NVIDIA RAG Runs a profiling pass and an aiperf load test against a deployed NVIDIA RAG Blueprint server, all driven by one YAML config. CX Codex +1 2,200installs perf-lighthouse tech-leads-club Runs local Lighthouse audits via CLI or Node API, parses reports, and configures performance budgets. Useful for tracking Core Web Vitals and integrating speed checks into CI. CX Codex +1 320installs web-perf cloudflare Audit Core Web Vitals, diagnose rendering bottlenecks, and inspect network dependencies directly through your agent. CX Codex +1 110,200installs tilegym-improve-cutile-kernel-perf TileGym Team Systematically profiles, tunes, and benchmarks cuTile GPU kernels in TileGym. Runs iterations on real hardware to lower latency while preserving accuracy. CX Codex +1 1,600installs high-perf-browser wondelai A Claude Code skill that traces slow page loads back to round trips: handshakes, HTTP/2 and HTTP/3, render-blocking resources and the critical rendering path. CX Codex +1 5,300installs build-perf-diagnostics dotnet This skill reads binlog timelines and Performance Summaries to show where a .NET build loses time. Handy when the slowdown has no obvious cause. CX Codex +1 3,500installs

From the same set8

perf-investigation-logger Appends structured performance investigation notes, quotes, and evidence to project logs. Keeps benchmarks and optimization decisions organized. CX Codex +1 1,600installs perf-theory-tester A skill that keeps perf experiments honest: one change per hypothesis, repeated runs, a recorded verdict. Useful when you need proof that an optimization helped. CX Codex +1 1,500installs perf-profiler Runs profilers against CPU and memory hot paths, captures flame graphs, and records file and line evidence. CX Codex +1 1,600installs perf-code-paths This skill maps likely execution paths, entrypoints, and related files for a performance scenario before profiling. Useful when the hot area is unclear. CX Codex +1 1,600installs perf-theory-gatherer A skill that turns git history and code evidence into up to five hypotheses about a performance problem. CX Codex +1 1,600installs perf-benchmarker Runs benchmarks sequentially under strict duration rules to catch performance regressions and set baseline metrics. CX Codex +1 1,600installs changelog-generator Turns git history into a user-facing changelog: sorts commits into categories and rewrites developer messages for customers. CX Codex +1 1,500installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor