healthcare-providers-extract

The saved excerpt is a snapshot from review. The external source remains the complete and most current version.

---
name: healthcare-providers-extract
description: |
  Extracts structured practitioner data from healthcare practice websites.
  Returns names, credentials, specialties, contact info, and education for
  every provider on a practice's site.

  Use when user asks to extract, pull, or list doctors, providers, or staff
  from practice websites. Triggers: "extract doctors from", "pull providers
  from", "who are the providers at", "build a provider database", "list all
  doctors at", "scrape the team page", "get practitioner data from".

  Accepts practice URLs (pasted, CSV, Google Sheet) or discovers practices
  via Google Maps when given specialty + location. Single sites or 100+ URLs.

  Do NOT use for filling data gaps — use healthcare-providers-enrich instead.
  Do NOT use for credential validation — use healthcare-providers-verify instead.
  Do NOT use for discovering practices — use market-finder or local-places instead.
  Do NOT use for general extraction — use nimble-web-expert instead.
allowed-tools:
  - Bash(nimble:*)
  - Bash(date:*)
  - Bash(cat:*)
  - Bash(mkdir:*)
  - Bash(python3:*)
  - Bash(echo:*)
  - Bash(jq:*)
  - Bash(ls:*)
  - Bash(wc:*)
  - Read
  - Write
  - Edit
  - Glob
  - Grep
  - Agent
  - AskUserQuestion
metadata:
  author: Nimbleway
  version: 1.6.1
  category: healthcare
---

# Healthcare Providers Extract

Structured practitioner extraction from healthcare practice websites, powered by
Nimble's web data APIs.

User request: $ARGUMENTS

**Before running any commands**, read `references/nimble-playbook.md` for Claude Code
constraints (no shell state, no `&`/`wait`, sub-agent permissions, communication style).

---

## Instructions

### Step 0: Preflight + WSA Discovery

Follow the transport selection + standard preflight from `references/nimble-playbook.md` — pick CLI or MCP at session start, then run the standard preflight calls (date calc, today, profile, memory index) in parallel.

**Also simultaneously** — run WSA discovery and setup:
- `mkdir -p ~/.nimble/memory/{reports,healthcare-providers-extract/checkpoints}`
- `ls ~/.nimble/memory/healthcare-providers-extract/checkpoints/ 2>/dev/null`
- Run Layer 1 (vertical) and Layer 3 (general tools) WSA discovery from
  `references/wsa-reference.md`. Layer 2 (session-specific) runs after Step 1 when
  you know the user's specialty.

Classify discovered agents into phases and validate with `nimble extract:templates get` per
`references/wsa-reference.md`.

From the preflight results:
- CLI missing or API key unset -> `references/profile-and-onboarding.md`, stop
- Tag all `nimble` CLI calls: `nimble --client-source nimble-agent-skills <subcommand>`. MCP requests are attributed at the transport level — see `references/nimble-playbook.md`.
- Profile exists -> note it for context. Determine mode using smart date windowing
  from `references/nimble-playbook.md`:
  - **Full mode:** first run OR last run > 14 days ago
  - **Quick refresh:** last run < 14 days ago (re-extract only new/changed pages)
  - **Same-day repeat:** if `last_runs.healthcare-providers-extract` is today, check
    for existing report at `~/.nimble/memory/reports/healthcare-providers-extract-*[today].md`.
    If found, ask: "Already ran today. Run again for fresh data?"
- No profile -> that's fine. This skill doesn't require onboarding. Proceed to Step 1.

### Step 1: Parse Input & Starting Questions

Parse `$ARGUMENTS` for input type using the Input Parsing Pattern from
`references/nimble-playbook.md`. Key routing:
- **URLs detected** -> proceed to Step 3
- **Specialty + location** (no URLs) -> proceed to Step 2 (practice discovery)
- **Unclear** -> ask (counts as 1 of max 2 prompts)

**If input is clear**, confirm and ask one shaping question (plain text, not
AskUserQuestion):

> "Extracting providers from **N practice sites**. Quick questions:
> 1. Healthcare vertical? (ophthalmology, dental, dermatology, general, or other)
> 2. Quick scan (names + credentials only) or full extraction (