carrel-search

Query the user's local knowledge bases through the Carrel search API, fetch original text or images as needed, compose the answer, list the reference files and offer follow-up directions drawn from the knowledge graph. Use when the user asks to search the knowledge base, find evidence in the stored material, compare records, or answer from several documents together.

Try your first task

Answer a question from your knowledge base

Start a fresh conversation.

Use carrel-search to answer this question from my stored documents: <your question>. Give a concise answer grounded in the retrieved evidence, list the reference files, and identify any gaps in the evidence.

Required inputs

Replace <your question> with a concrete question about your stored documents.
A running Carrel search service with documents processed into an enabled knowledge base.
Python 3.9+ for the skill's standard-library client.
If the service is remote, configure its address and any required token through the documented environment variables or configuration file.

Suggested template by Skill Leaderboard, grounded in the linked source. Task evidence ↗

Inside SKILL.md

102 lines

Section content has not been verified for this skill yet.

Full source remains withheld under the current source-display policy. Read the author’s source ↗