Performance Review

Performance Review is a Quality skill for Claude Code, published by jpicklyk in task-orchestrator.

206 stars20 forkson jpicklyk/task-orchestratorAdded 2026/09/05Repository updated 2026/08/04

ai-coding-assistantai-developmentai-harnessai-memoryai-toolsclaudeclaude-codeclaude-desktopcontext-persistencedeveloper-toolsharness-engineeringharness-frameworkmcpmcp-servermodel-context-protocoltask-managementvibe-codingworkflow-automation

Install in seconds

Install Performance Review

Copy Performance Review into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/jpicklyk/task-orchestrator/tree/main/.claude/skills/perf-review ~/.claude/skills/perf-review

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/jpicklyk/task-orchestrator.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: .claude/skills/perf-review/SKILL.md in jpicklyk/task-orchestrator
Installs to: ~/.claude/skills/perf-review
Collection: One of 25 skills cataloged from this repository
Category: Quality — 1662 skills

What Performance Review does

Performance Review evaluates whether a change affects hot paths, query patterns, serialization cost, and overall complexity. Use it when preparing performance-baseline notes for a Kotlin MCP server with SQLite.

Performance Review is cataloged under Quality on DirSkills. Performance Review comes from a repository tagged ai-coding-assistant, ai-development, ai-harness, ai-memory and ai-tools.

Documentation

README

Excerpt

Performance Review Framework

Evaluate performance impact of changes. This project is a Kotlin MCP server with SQLite via Exposed ORM, handling tool calls synchronously per request.

Step 1: Hot Path Analysis

Identify which hot paths the change touches:

Per-request paths — MCP tool execution (every tool call hits this). New work here adds latency to every request.
Per-item loops — operations that iterate over items (search, overview, stalled-item detection). N+1 patterns here scale poorly.
Startup path — server initialization, database schema creation, config loading. Affects container startup time.
Background operations — cascade detection, dependency resolution. Runs inline, not async.

Step 2: Database Query Patterns

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Performance Review

What else does jpicklyk publish alongside Performance Review?
Performance Review is one of 25 skills that DirSkills catalogs from jpicklyk/task-orchestrator, the repository it ships in. Its siblings there include API Compatibility Review, Adopt Project Scope and Batch Complete. Each one is a separate skill with its own page in this directory, installs the same way Performance Review does, and is maintained by jpicklyk in that same repository. The rest of the collection is listed on the jpicklyk/task-orchestrator page.
How does Performance Review compare to other Quality skills?
Performance Review ranks #1475 by stars among the 1662 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Performance Review against them. Open each page to compare what they document and how they install.