Find and apply the company's operational runbooks during an incident, using the internal runbook MCP server. Use when a service is degraded and you need the documented procedure rather than an improvised one.
1 skill · 1 agent · 1 MCP server
Run the repository's own formatter after the assistant edits a file, and only in repositories that already declare one. Use it to keep generated edits consistent with the project's existing formatting rules.
1 command · hooks
Review a pull request or working-tree diff against the company engineering standards, reporting correctness bugs, missing tests, and security issues with file and line references. Use before requesting human review on any change.
1 skill
Write and review dbt models following the data team's layering and naming conventions, including tests and documentation for every new model. Use when adding or changing a model in the analytics repository.
1 skill
Prepare and verify a service deployment: check the release checklist, confirm migrations are backward compatible, and produce the rollout and rollback plan. Use when shipping a backend service to staging or production.
1 skill
Draft customer-facing incident updates in the company's voice: what is affected, what is being done, and when the next update comes. Use while an incident is open and customers need to be told something.
1 skill
Check raw SQL against the data team's naming and formatting conventions. Superseded by dbt-helper, which covers the same conventions plus tests and documentation for the models the SQL belongs to.
1 skill
Standard artifact set for backend engineers: code review plus the deployment workflow. Install this when you join a backend team.
The baseline set of AI artifacts every engineer at the company gets by default. Install this first; team-specific packs build on top of it.