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

perf-theory-gatherer — Claude Code skill: performance hypotheses

A skill that turns git history and code evidence into up to five hypotheses about a performance problem.

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

What perf-theory-gatherer does

You describe a scenario, and the skill walks it in order: recent git history scoped to the relevant paths, then the code paths involved, found through a repo map or grep. What comes back is a list of hypotheses, each with evidence and a confidence level of low, medium or high. Five is the ceiling.

The output shape is fixed. Every hypothesis gets an id, a short description, a file path or git change as evidence, and a confidence rating. Checking git history is mandatory before any hypothesis is written. The skill does not suggest optimizations — it only names possible causes.

It follows docs/perf-requirements.md as the canonical contract, so that file needs to exist in your repo. Without it the skill has no agreed requirements for the performance work, which is worth checking before you run it.

What it helps with

  • turn commit history into candidate causes of a slowdown
  • locate the code paths a given scenario touches
  • separate hypotheses from ready-made optimization advice
  • tie every hypothesis to a file or git change
  • cap the investigation at five prioritized hypotheses

Example prompts for the agent

  • review git history for the slow order list scenario and give me hypotheses with evidence
  • why is the report export slow — find the code paths and list up to five causes
  • check recent commits in the search module and produce hypotheses with confidence levels

How to install perf-theory-gatherer

1Skills CLI (Vercel)

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

2Manually: put the files in place

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

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

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

Questions about perf-theory-gatherer

How do I install perf-theory-gatherer in Claude?

Run npx skills add composio-community/awesome-claude-plugins --skill perf-theory-gatherer -a claude-code. The skill then lives at ~/.claude/skills/theory/SKILL.md.

What does perf-theory-gatherer do?

It reads git history and code for a scenario you name and returns up to five hypotheses about performance causes, each with evidence and a confidence rating.

Does it need docs/perf-requirements.md?

Yes, the skill treats it as the canonical contract. Without that file in the project it has no agreed requirements for the performance investigation.

Similar skills

All skills for Agent setup: memory, context, orchestration →
thinking-theory-of-constraints tjboudreaux A skill that walks your agent through theory of constraints: find the one binding stage, exploit it, then remeasure. Useful when extra capacity does not raise output. CX Codex +1 643installs django-perf-review getsentry This skill reviews Django code for N+1 queries, unbounded querysets and missing indexes. Useful before a release or when a page slows down on large tables. CX Codex +1 2,900installs web-perf cloudflare Audit Core Web Vitals, diagnose rendering bottlenecks, and inspect network dependencies directly through your agent. CX Codex +1 110,200installs 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-baseline dotnet Establishes MSBuild and .NET build performance baselines before you optimize. Measures cold, warm, and no-op build scenarios with binary logs. CX Codex +1 3,500installs 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

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-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