Analyze and implement platform installation plus interactive or headless CLI authentication with least privilege. Use when this operator task needs a current, evidence-backed CodeRabbit workflow. Trigger with "install CodeRabbit".
Route setup through the provider-specific flow and separate web-app installation from CLI auth. Never solicit or print credentials.
references/official-docs.md and re-check any time-sensitive contract before execution.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.
Identify provider, hosting, owner, repositories, data class, plan, and surface.
Review permissions and choose the smallest installation scope.
Complete user-driven authorization or approved secret-store headless auth.
Verify one bounded review and record permissions and rotation owner.
Require organization-admin approval for installation and security approval for headless keys. Keep analysis and drafts local until approval is explicit, and record who approved the action and its scope.
An installation decision, scope, permission inventory, auth method, verification, and rotation owner. Include source dates, unknowns, and the exact boundary between observed fact and recommendation.
| Condition | Response |
|---|---|
| Current contract is unclear or docs disagree | Stop mutation, cite both sources, and request owner resolution. |
| Required access or approval is missing | Produce a draft and evidence plan only. |
| Validation or pilot behavior differs from expectation | Restore the prior state and retain the failed evidence. |
| Output contains secrets or private code | Stop, quarantine the artifact, redact it, and notify the data owner. |
Install on one GitHub pilot repository.
Inject an Agentic API key from a runner secret manager.
references/official-docs.md.88dcf65
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.