LLM Skills
~/catalog/debugging & maintenance//perf-theory-gatherer

Perf Theory Gatherer

/perf-theory-gatherer

Generate hypotheses for performance bottlenecks and regressions. You MUST read `docs/perf-requirements.md` before outputting hypotheses.

ComposioHQComposioHQ
1.9k
May 1, 2026
// skill content

--- name: perf-theory-gatherer description: Generate top performance hypotheses after reviewing Git history and current metrics. tools: Read, Bash(git:), Bash(node:), Bash(npm:), Bash(pnpm:), Bash(yarn:), Bash(cargo:), Bash(go:), Bash(pytest:), Bash(python:), Bash(mvn:), Bash(gradle:*) model: opus --- # Perf Theory Gatherer Generate hypotheses for performance bottlenecks and regressions. You MUST read docs/perf-requirements.md before outputting hypotheses. You MUST execute the perf-theory-gatherer skill to produce hypotheses. Do not bypass the skill. This agent should only add agent-specific context (scenario, repo scope) and then run the skill.

// original public source
ComposioHQ/awesome-claude-plugins
/perf/agents/perf-theory-gatherer.md
License: License not specified. Review the repository before reusing it.
Independent project, not affiliated with Anthropic. This skill remains the property of its original author.
// install this skill
Paste this command in your terminal at the root of your project:
mkdir -p .claude/commands && curl -o ".claude/commands/perf-theory-gatherer.md" "https://raw.githubusercontent.com/ComposioHQ/awesome-claude-plugins/master/perf/agents/perf-theory-gatherer.md"
Then in Claude Code, type /perf-theory-gatherer to activate it.
open_in_newOpen original source
// save
Save available after sign in.
loginSign in to save
// information
CreatorComposioHQ
Stars 1.9k
UpdatedMay 1, 2026
Format.md
AccessFree
// similar

Skills Debugging & maintenance

View allarrow_forward