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

perf-theory-tester — Claude Code skill: controlled perf experiments

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.

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

What perf-theory-tester does

The skill walks the agent through a controlled experiment. It starts by confirming the baseline is clean. Then it applies a single change tied to the hypothesis and runs at least two validation passes. The code goes back to baseline before the next experiment begins.

Output follows a fixed shape: hypothesis id, a short summary of the change, metric deltas, a verdict of accept, reject or inconclusive, plus evidence — the benchmark command and the files touched. The skill treats docs/perf-requirements.md as the canonical contract to follow.

The rules are strict on purpose. One change per experiment. No parallel benchmarks. Every run leaves a record. Without that discipline, measurement noise passes for a speedup.

What it helps with

  • prove that a code change actually made things faster
  • isolate the effect of one optimization from surrounding edits
  • keep a record of the benchmark command and files for each run
  • get a clear accept or reject instead of a guess
  • reset the tree to baseline before the next attempt

Example prompts for the agent

  • Run a controlled experiment on the hypothesis that caching cuts response time, and format the result the way the skill expects
  • Take a baseline of the /api/search endpoint, apply one change, then give me a verdict with the commands and changed files
  • Check my experiment against docs/perf-requirements.md and tell me what is missing before a verdict

How to install perf-theory-tester

1Skills CLI (Vercel)

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

2Manually: put the files in place

~/.claude/skills/theory-tester/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/theory-tester/

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

Questions about perf-theory-tester

How do I install perf-theory-tester in Claude Code?

Run npx skills add composio-community/awesome-claude-plugins --skill perf-theory-tester -a claude-code. Alternatively install it as theory-tester: npx skills add composio-community/awesome-claude-plugins --skill theory-tester -a claude-code.

What does perf-theory-tester do?

It runs one perf hypothesis at a time: clean baseline, a single change, two or more validation passes, then a revert. You get accept, reject or inconclusive with supporting evidence.

How is it different from plain profiling?

It does not hunt for hot spots; it tests a hypothesis you already wrote down. One change per run and no parallel benchmarks keep the effects of separate edits from mixing.

Similar skills

Everything for Testing and QA →
improve-codebase-architecture Matt Pocock This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review. 1,163,035installs design-taste-frontend Leonxlnx This skill directs the design of public pages and work screens, then checks the result in a browser through screenshots. Use it when an interface feels generic or unfinished. CX Codex +1 678,700installs tdd Matt Pocock Guides the red-green TDD loop: ensures tests are written first, keep them at public interfaces, and avoid coupling to implementation details. 1,141,062installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. 414,180installs agent-browser vercel-labs A CLI skill for browser control: it opens pages, fills forms, clicks buttons, and tests web apps. Use it when an agent needs to act inside a website. CX Codex +1 1,200,000installs prototype Matt Pocock Creates throwaway prototypes for checking state logic or exploring UI before committing the decision to the main codebase. 986,201installs

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