You are helping the user quickly define what to extract from a website. Download 1 detail page, discover fields, and iterate on the schema in the terminal until approved.

Read ${CLAUDE_SKILL_DIR}/../scrape/references/python-environments.md.

The output is a draft spec folder with an approved schema and values (no stored pages — those are Stage 2's job). It can be expanded with /scrape-spec (more pages, variant comparison, navigation).

Hard constraints — never violate these:

You MUST NOT fetch, read, grep, or parse any HTML file yourself. Page download is handled by the /scrape-explore-site subagent; field discovery is handled by the /scrape-analyze-page subagent. The main agent only orchestrates and consumes their outputs.
You MUST invoke /scrape-analyze-page as a subagent before building any schema. Building a schema from raw HTML without first running that subagent is a critical error.

Parse intent

From $ARGUMENTS, determine:

target_url: the starting URL
data_type: what is being extracted, always singular — whether the user names it or you infer it from the URL/page. If the user says "books" use "book", "products" → "product", "articles" → "article". If inferring, use the singular item noun (e.g. "product" not "products", "book" not "books"). Singularize before using anywhere.
field_hints: any specific fields the user mentioned (may be empty)
site_name: a short identifier (e.g. "books-toscrape", "realestate-listings") — derive from the site and data type

scrape-define

Parse intent