Claude Code
AnthropicAnthropic's terminal agent: reads the repo, edits files, runs the tests it just broke.
Profiles a messy CSV and reports what would break a join.
First pass on an export before anyone builds on it
Silent transformation — it reports problems and proposes fixes, it does not rewrite data
Profiles a CSV: types per column, duplicate keys, empty rates, inconsistent date formats, and values that would silently drop rows in a join. The output is a report plus a proposed cleaning plan; applying it stays a separate, reviewable step.
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 data-cleaningRead 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.
Long-context writing and code work with a strong editing instinct.
Cloud software agent that works in an isolated sandbox and hands back a pull request.
A server for Snowflake that exposes schema metadata, object descriptions, and SQL execution. It also indexes Snowflake's own documentation, which matters more than i…
Exposes Databricks catalog metadata and SQL execution for a workspace. It fits analytics teams that already live in notebooks; the risk is the same as any SQL tool —…
Serves version-specific documentation for thousands of libraries, so an agent stops writing code against an API that changed two releases ago. The practical fix for …