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

performance-benchmark-specialist — Claude Code skill: shell tool

Sets up benchmarks for shell tools: warmup runs, statistics, and target checks like <100ms and >90% cache hit rate.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add manutej/luxor-claude-marketplace --skill performance-benchmark-specialist -a claude-code
Open on GitHub

What performance-benchmark-specialist does

The skill lays out a benchmark structure for shell scripts: warmup, a batch of runs, min/max/mean/median/stddev, then a baseline-versus-optimized comparison. Results land in CSV, and target values get asserted automatically. Handy when you changed a script and need to know whether it actually got faster.

Inside is a bench-helpers.sh library with millisecond timing, warmup, run and statistics functions, plus a benchmark template. Targets come from the unix-goto project: cached navigation under 100ms, bookmark lookup under 10ms, cache hit rate above 90%, cache build under 5s.

It is not for application profiling, production monitoring or load testing web services — those need their own tools. A one-off measurement is fine with plain time. The source text is cut off, so the full set of library functions cannot be verified from it.

What it helps with

  • measure a shell script before and after optimization
  • compute min, max, mean, median and stddev across runs
  • check whether a command stays under the 100ms target
  • generate a test workspace with folders
  • save benchmark results to CSV and compare against baseline

Example prompts for the agent

  • Write a benchmark for my navigation script: warmup, 10 runs, statistics and a 100ms target check
  • Compare the baseline and optimized versions of my bookmark lookup command and report the speedup
  • Create a medium workspace and benchmark the cache, then save the results to CSV

How to install performance-benchmark-specialist

1Skills CLI (Vercel)

npx skills add manutej/luxor-claude-marketplace --skill performance-benchmark-specialist -a claude-code

2Manually: put the files in place

~/.claude/skills/performance-benchmark-specialist/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/performance-benchmark-specialist/

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

Questions about performance-benchmark-specialist

How do I install performance-benchmark-specialist in Claude?

Run npx skills add manutej/luxor-claude-marketplace --skill performance-benchmark-specialist -a claude-code. The skill lands at ~/.claude/skills/performance-benchmark-specialist/SKILL.md.

What does performance-benchmark-specialist do?

It describes how to build benchmarks for shell tools: warmup, repeated runs, min/max/mean/median/stddev statistics, baseline comparison and automatic target checks.

Which performance targets does it check?

Cached navigation under 100ms, bookmark lookup under 10ms, cache hit rate above 90% and cache build under 5s.

Similar skills

All skills for Testing and QA →
golang-benchmark samber This skill helps write and run Go benchmarks, inspect profiles, and compare measurements. Use it when tracking regressions or investigating a hot path. CX Codex +1 39,500installs V3 Performance Optimization ruvnet Skill for optimizing claude-flow v3 with Flash Attention, HNSW indexing, and comprehensive benchmarking. Achieves 150–12,500x search improvement and 50–75% memory reduction. CX Codex +1 1,100installs m10-performance actionbook System guidance for agents to optimize Rust code systematically, focusing on profiling and memory allocation control. CX Codex +1 3,600installs go-performance cxuu A skill that points your agent at Go hot paths: strconv over fmt, capacity hints for slices and maps, strings.Builder in loops. CX Codex +1 1,200installs bash-scripting sickn33 A structured workflow for building shell scripts with defensive patterns, error handling, ShellCheck, and Bats tests. CX Codex +1 2,400installs cost-benchmark ruvnet Runs corpus benchmarks to evaluate booster performance and compare spend against Gemini or Claude baselines. Generates verifiable cost tables before releases. CX Codex +1 679installs

From the same set31

database-management-patterns A reference skill for PostgreSQL and MongoDB work: schema design, indexing, transactions, replication and sharding. CX Codex +1 466installs react-development A skill that feeds your coding agent React patterns: components, hooks, state and effects, taken from the official react.dev docs. CX Codex +1 464installs tailwind-css A Tailwind CSS skill covering utility classes, responsive variants, dark mode and production optimization. Handy when you build UI and want to stay in your markup. CX Codex +1 461installs vector-database-management A skill for Pinecone, Weaviate and Chroma: indexes, embeddings, similarity search and RAG. Useful when you need semantic search in a project. CX Codex +1 459installs PostgreSQL Database Administration A PostgreSQL administration skill: schema design, indexing, backups and query tuning. Useful when the agent writes SQL for a ticketing system or reporting. CX Codex +1 452installs langchain-orchestration A LangChain reference skill for your coding agent: chains, agents, memory, RAG and orchestration. Useful when the agent writes LangChain code and should stick to working patterns. CX Codex +1 451installs graphql-api-development A skill that walks your agent through GraphQL API design on graphql-js: schema, resolvers, queries, mutations, subscriptions, auth. Useful when REST stops fitting. CX Codex +1 447installs microservices-patterns A microservices skill covering service mesh, circuit breakers, traffic splitting and Istio. Useful when services fail in cascades or you need a canary release. CX Codex +1 446installs

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