Exa — Semantic Search

What it does

Exa adds semantic search capability to an agent: it performs meaning-based retrieval (not keyword matching) to return documents, passages or results similar to a query. Typical outputs are ranked text results useful for research, RAG pipelines, and content discovery.

When to use it

Use Exa when you need to find related documents by concept rather than literal terms, surface similar examples, or augment a retrieval-augmented generation workflow with semantically relevant sources. Good for ad-hoc research, summarization, and building search UIs.

What's included

• Scripts: none embedded in the skill (has_scripts=false) — integration shown via CLI workflow examples.
• References: none listed.
• Instructions: the SKILL.md includes example commands to run the skill via Refly (skill run -> get RUN_ID -> toolcalls) and shows how to extract text content from workflow toolcalls. The input schema expects a JSON object with a search_query and num_results.

Compatible agents

Inferred compatibility: Claude Code / Refly workflows and generic agent orchestration platforms that can call external skill workflows. The skill is authored for Refly's ecosystem and expects the Refly CLI/workflow runtime.