Agent skill · software engineering · jeremylongshore

coderabbit-debug-bundle

Assemble a minimal redacted diagnostic package for configuration, review, CLI, or provider failures. Use when this operator task needs a current, evidence-backed CodeRabbit workflow. Trigger with "build a CodeRabbit debug bundle".

Why this skill is useful

Adds executable scripts for collecting diagnostic information specific to CodeRabbit that the AI wouldn't reliably generate on its own.

What it needs

Requires gh, python3 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 Debug Bundle Overview Collect only evidence needed to reproduce the failing boundary. Preserve timestamps and provenance while excluding code, credentials, private comments, and unrelated users. 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 Feature-branch YAML, resolved config, eligibility, commands, and limit state are primary evidence. CLI failures have separate auth and network contracts. Provider permission state must be captured without tokens. Service health is evidence, not a substitute for local 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. Define symptom, time window, surface, expected behavior, and reproduction boundary. 2. Collect redacted IDs, config hash, eligibility fields, timestamps, and CI state. 3. Remove source, secrets, emails, tokens, payloads, and unrelated comments. 4. Reproduce once safely and list included and excluded evidence. 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-debug-bundle

View the source on GitHub

Browse the @skills marketplace