Claude MarketplacesSubmit
composiohq avatar

Perf Theory Gatherer

composiohq/awesome-claude-pluginsOfficial

When you need to figure out why something is slow but don't want to guess, this skill forces a structured approach. It digs through git history and maps out relevant code paths before generating up to five performance hypotheses, each tagged with evidence and a confidence level. The key constraint is useful: it won't let you jump straight to optimization suggestions. You get theories backed by actual commits and file references, not hunches. It follows a documented contract in perf-requirements.md, so if you're working with a team that needs reproducible performance investigation, this keeps everyone on the same methodology.

GitHub stars
1.7K
last updated
May 1, 2026
View on GitHub

Install

$ npx -y skills add composiohq/awesome-claude-plugins --skill perf-theory-gatherer --agent claude-code

Installs into .claude/skills of the current project.

Files

perf-theory-gatherer

Generate performance hypotheses for a specific scenario.

Follow docs/perf-requirements.md as the canonical contract.

Required Steps

  1. Review recent git history (scope to relevant paths when possible).
  2. Identify code paths involved in the scenario (repo-map or grep).
  3. Produce up to 5 hypotheses with evidence + confidence.

Output Format

hypotheses:
  - id: H1
    hypothesis: <short description>
    evidence: <file/path or git change>
    confidence: low|medium|high
  - id: H2
    ...

Constraints

  • MUST check git history before hypothesizing.
  • No optimization suggestions; only hypotheses.
  • Keep to 5 hypotheses maximum.
SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Details

Repository
github.com/composiohq/awesome-claude-plugins
First seen
Jun 11, 2026

More from composiohq/awesome-claude-plugins

All 23

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs