Agent skill · software engineering · jeremylongshore
coderabbit-common-errors
Triage missing, duplicate, noisy, or misconfigured reviews from observed pull-request and configuration evidence. Use when this operator task needs a current, evidence-backed CodeRabbit workflow. Trigger with "debug CodeRabbit reviews".
Why this skill is useful
Provides specific YAML configuration patterns and troubleshooting scripts for CodeRabbit that the AI wouldn't reliably generate on its own.
What it needs
Requires gh installed locally. Requires github account access. About 2k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
CodeRabbit Common Errors Overview Diagnose the first failing boundary instead of relying on fixed wait-time tables. Installation, feature-branch configuration, eligibility, limits, and service health require separate evidence. 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 The reviewed .coderabbit.yaml comes from the feature branch under review. The default branch is always included; basebranches adds other targets. Draft, author, title, and label controls can exclude a pull request. The YAML validator and @coderabbitai configuration are contract checks. 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 provider, PR, author, draft state, target branch, labels, and last response. 2. Read and validate feature-branch YAML plus central or organization overrides. 3. Classify installation, eligibility, configuration, limit, command-state, or service failure. 4. Apply one reversible correction and compare the response with baseline. 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. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/coderabbit-common-errors