Agent skill · marketing growth · jeremylongshore

coderabbit-performance-tuning

Improve review speed and signal using measured scope, config, cache, and review behavior without timing bands. Use when this operator task needs a current, evidence-backed CodeRabbit workflow. Trigger with "tune CodeRabbit performance".

Why this skill is useful

Provides specific configuration patterns and CI scripts for optimizing CodeRabbit performance that the AI wouldn't reliably generate on its own.

What it needs

Requires coderabbit installed locally. About 2k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.

What this skill does

CodeRabbit Review Performance Tuning Overview Optimize operator-controlled inputs and measure effects. Separate service latency, provider delay, limits, diff size, paths, tools, and guidance. Prerequisites Identify the CodeRabbit organization, Git provider, repository, plan, and accountable owner. Read references/official-docs.md and re-check any time-sensitive contract before execution. Use synthetic or read-only evidence until the approval boundary is satisfied. Preserve the repository's independent CI, security, and human-review requirements. Current Contract Path filters change scope; path instructions change guidance. Incremental reviews can pause after configured reviewed commits. Caching normally accelerates review but can be disabled. Plan limits belong to the live plans contract. Authentication Treat Git-provider sessions, CodeRabbit web sessions, CLI credentials, and CodeRabbit API keys as separate credentials. Use only an already-approved session or secret-manager reference, never print a secret, and do not place credentials in .coderabbit.yaml, source files, logs, or deliverables. Instructions 1. Capture events, files, diff size, tools, cache, limits, findings, and timing. 2. Classify delay or noise by boundary. 3. Pilot one scope, filter, instruction, profile, or incremental-review change. 4. Compare equivalent samples and roll back hidden-risk regressions. Tool Discipline Use Glob to locate candidate configuration and evidence files without widening scope. Use Grep to find relevant fields, commands, identifiers, and stale claims. Use Read to inspect the smallest required files and authoritative evidence. Use Write only for a new approved local draft or evidence artifact. Use Edit only for a bounded approved change whose rollback is known. Do not use these file tools as a substitute for authenticated CodeRabbit or provider operations. Approval Boundaries Require security or code-owner approval before exclusions, tool disablement, or shared changes. …

How to use it

Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:

@skills jeremylongshore/coderabbit-performance-tuning--50e7dc

View the source on GitHub

Browse the @skills marketplace