Review perf

Skill diguike/book-claude-skill/examples/ch16-composition/parallel-review/review-perf

Claude Code Skill 开发指南

Install

npx -y skills add diguike/book-claude-skill --skill review-perf

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Performance-focused code review. Fork subagent for parallel execution. 性能专项审查。

SKILL.md

0.8 KB, 171 tokens by cl100k_base, as published. Nobody here has run it

Performance Review (Subagent)

You are a performance-focused reviewer. Only check for performance issues.

Checklist

N+1 database queries
Missing database indexes (large table scans)
Unnecessary re-renders (React/Vue)
Synchronous I/O in async context
Large bundle imports (import entire library for one function)
Memory leaks (unclosed connections, missing cleanup)
Inefficient algorithms (O(n^2) where O(n) is possible)

Output

Write findings to ./perf-review.json in format:

[{ "file": "...", "line": 0, "severity": "warning", "message": "..." }]

Scope

ONLY performance issues — ignore security, style, naming
If no performance issues found, write empty array

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most review quality skills give in 171 tokens

Counted across 1,048 of the 1,783 authors here whose files we hold, read 2026-08-07

Ask questions one at a timein 81 of 1048, across 64 files
Provide a recommended answer for each questionin 73 of 1048, across 50 files
Explore the codebase instead of asking answerable questionsin 66 of 1048, across 42 files
Resolve dependencies between decisions one-by-onein 42 of 1048, across 17 files
Interview the user relentlessly about the planin 38 of 1048, across 13 files
Order findings by severityin 31 of 1048
Resolve each branch of the decision treein 27 of 1048, across 5 files
Run a grilling sessionin 26 of 1048, across 5 files
Update CONTEXT.md immediately when a term is resolvedin 26 of 1048, across 11 files
Propose precise canonical terms for vague languagein 25 of 1048, across 7 files
Create documentation files lazilyin 24 of 1048, across 5 files
Assign severity to every findingin 24 of 1048

Said here and by no other author read

check for unnecessary re-renders
check for synchronous I/O in async context
check for large bundle imports
check for memory leaks
check for inefficient algorithms
write findings to perf-review.json

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.