From hutch
Store, query, and publish structured data via Hutch. Use when the user wants to save structured data, query collections, list what data they have, describe collection fields, search across data, or publish a collection.
How this skill is triggered — by the user, by Claude, or both
Slash command
/hutch:hutchThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Hutch stores structured data as JSON records in collections. No schema required — just store data and query it later.
Hutch stores structured data as JSON records in collections. No schema required — just store data and query it later.
Always follow this progression when answering questions about existing data:
list_collections)describe_collection)query_records)store_records — Create or upsert records. Auto-creates the collection if it doesn't exist.
{ collection: "name", data: { field: "value" } }{ collection: "name", records: [{ ... }, { ... }] }unique_key on the collection first, then use on_conflict: "merge" | "replace" | "skip" | "error"list_collections — List all collections with record countsget_collection — Get collection details (settings, schema, unique key)describe_collection — Field names, types, sample values, and stats. Always call this before querying so you know whether to use filter (exact/numeric) or search (text).query_records — Query with filter, search, sort, group_by, aggregate, time_bucket, limit, offsetsearch — Global full-text search across all collectionsupdate_collection — Update collection settings (published, unique_key, schema, display options)delete_collection — Delete an entire collectiondelete_record — Delete a single record by IDfilter): exact value match — use for structured fields (boolean, number, enum/select values)search): free text across all text fields- for descending (e.g., -created_at)count, sum, avg, min, max on fieldsCheck the describe_collection tool to know whether a field is numeric (safe for filter/comparison) or string (use search).
If the user generates structured output during a conversation — scraped data, API responses, computed tables, research results — offer to store it in Hutch so they can query it later. Example: "Would you like me to save these results to a Hutch collection so you can query them later?"
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub expeditedprojects/hutch-skill --plugin hutch