Claude Code
AnthropicAnthropic's terminal agent: reads the repo, edits files, runs the tests it just broke.
Score a schema migration by lock time, data loss, and rollback cost.
A migration plan that will run against a production table
Greenfield databases — there is no data to lose
Scores a migration on three axes: how long it blocks writes, whether a step is recoverable, and how expensive the rollback is. A migration that scores badly on two axes should be split; the skill says which step to split out first rather than refusing the whole plan.
Clone the repository, then copy the skill folder into your agent's skills directory — ~/.claude/skills/ for Claude Code. Skills are plain files: no build step, no daemon.
npx skills add migration-riskRead the SKILL.md before you install. A good skill states when it applies, what it must not do, and how to verify the result. A skill that only lists adjectives will change the agent's tone without improving its output — skip those.
Anthropic's terminal agent: reads the repo, edits files, runs the tests it just broke.
Code assistant that answers with repository context across many repos.
Self-hosted code completion with an open-source server.
Runs SQL against a ClickHouse database with a read-only user: table listing, schema inspection, and query execution. The natural fit is event data where an agent can…
Opens a local DuckDB database and exposes SQL over it, including files as views. That makes it the cheapest way to let an agent analyse a data dump on a laptop: no w…
Reads PlanetScale databases and branches, and can run SQL against a branch. The branching model is the safety feature: point the agent at a branch, let it experiment…