Agent skill · data analytics · jeremylongshore

coderabbit-data-handling

Define code, cache, retention, export, and sensitive-path controls for a repository or organization. Use when this operator task needs a current, evidence-backed CodeRabbit workflow. Trigger with "audit CodeRabbit data handling".

Why this skill is useful

Provides specific patterns and configurations for handling sensitive data and compliance with GDPR/CCPA 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 Data Handling Overview Map what CodeRabbit may read, retain, cache, and export before changing controls. Exclusions do not replace source-control secret prevention. 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 Cached data is documented as never used for training and expiring within one week. Cached data is encrypted except for open-source projects. Organizations can disable cache or data retention. Path filters change review surfaces, not Git history or provider access. 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. Classify repositories and paths by sensitivity and contractual requirements. 2. Record installation scope, filters, cache, retention, exports, and reports. 3. Design access minimization, secret prevention, exclusions, retention, and custody. 4. Pilot on synthetic data and confirm coverage and incident ownership. 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. …

How to use it

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

@skills jeremylongshore/coderabbit-data-handling--bce2bf

View the source on GitHub

Browse the @skills marketplace