healthcare-providers-enrich

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Healthcare Providers Enrich

Fill gaps in existing practitioner lists with verified web data, 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).

借助Nimble的网页数据API，利用已验证的网页数据补全现有从业者列表中的信息缺口。

用户请求：$ARGUMENTS

执行任何命令前，请阅读

references/nimble-playbook.md

了解Claude Code的限制（无Shell状态、禁止使用

wait

、子Agent权限、沟通风格）。

Instructions

操作说明

Step 0: Preflight + WSA Discovery

步骤0：预检 + WSA发现

Sibling handoff check: Before running full preflight, check if

healthcare-providers-extract

ran earlier in this session by following the Sibling Handoff pattern from

references/nimble-playbook.md

. If same-day extract output exists, skip CLI check and profile load, and reuse WSA Layer 1/3 inventory. Only re-run Layer 2 if the specialty changed.

Otherwise, run full preflight from

references/nimble-playbook.md

(5 simultaneous Bash calls: date calc, today, CLI check, profile load, index.md load).

Also simultaneously — run WSA discovery and setup:

mkdir -p ~/.nimble/memory/{reports,healthcare-providers-enrich/checkpoints}

ls ~/.nimble/memory/healthcare-providers-enrich/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 agent get

per

references/wsa-reference.md

From the preflight results:

CLI missing or API key unset ->
```
references/profile-and-onboarding.md
```
, stop
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-enrich only records with gaps)
- Same-day repeat: if
```
last_runs.healthcare-providers-enrich
```
  is today, check for existing report at
```
~/.nimble/memory/reports/healthcare-providers-enrich-*[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.

兄弟技能交接检查：在执行完整预检前，按照

references/nimble-playbook.md

中的兄弟技能交接模式，检查本次会话中是否已运行过

healthcare-providers-extract

。若存在当日提取输出，则跳过CLI检查和配置文件加载，复用WSA第1/3层资源库。仅当专业领域发生变化时，才重新运行第2层。

否则，执行完整预检：来自

references/nimble-playbook.md

（5个并行Bash调用：日期计算、当日日期、CLI检查、配置文件加载、index.md加载）。

同时——运行WSA发现与设置：

mkdir -p ~/.nimble/memory/{reports,healthcare-providers-enrich/checkpoints}

ls ~/.nimble/memory/healthcare-providers-enrich/checkpoints/ 2>/dev/null

从
```
references/wsa-reference.md
```
运行第1层（垂直领域）和第3层（通用工具）WSA发现。第2层（会话专属）将在步骤1了解用户的专业领域后运行。

将发现的Agent按阶段分类，并按照

references/wsa-reference.md

使用

nimble agent get

进行验证。

根据预检结果：

CLI缺失或API密钥未设置 -> 跳转至
```
references/profile-and-onboarding.md
```
，停止操作
配置文件存在 -> 记录上下文信息。根据
```
references/nimble-playbook.md
```
中的智能日期窗口确定模式：
- 完整模式：首次运行或上次运行距今超过14天
- 快速刷新模式：上次运行距今不足14天（仅补全存在缺口的记录）
- 当日重复运行：若
```
last_runs.healthcare-providers-enrich
```
  为今日，检查
```
~/.nimble/memory/reports/healthcare-providers-enrich-*[today].md
```
  是否存在现有报告。若存在，询问："今日已运行过该工具。是否重新运行以获取最新数据？"
无配置文件 -> 无需担心，本技能无需完成入职流程。继续执行步骤1。

Step 1: Parse Input + Starting Questions

步骤1：解析输入 + 初始问题

Chained-from-extract shortcut: Check for a same-day extract report:

bash

ls ~/.nimble/memory/reports/healthcare-providers-extract-*$(date +%Y-%m-%d).md 2>/dev/null

If a same-day report exists, parse the

{slug}

from the filename and load

~/.nimble/memory/healthcare-providers-extract/{slug}/providers.json

. The practice domains and page URL patterns are already known — construct individual bio page URLs from the site's URL convention and skip Step 3 entirely. This avoids N unnecessary web searches. If no same-day report exists, do not reuse old

providers.json

files.

Parse

$ARGUMENTS

for input type using the Input Parsing Pattern from

references/nimble-playbook.md

. Key routing:

Extract output detected (providers.json) -> proceed to Step 2, mark Step 3 skip
CSV/Sheet/pasted data detected -> proceed to Step 2
Unclear -> ask (counts as 1 of max 2 prompts)

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

"Found N providers in your list. Quick questions:

Which fields need filling? (contact info, credentials, specialty, reviews, regulatory — or all gaps)

Healthcare vertical? (ophthalmology, dental, dermatology, general, or other)"

If input is ambiguous, use AskUserQuestion (counts as 1 of max 2 prompts):

What provider list should I enrich?

Paste provider data directly (name + any known info, one per line)

Provide a CSV file path or Google Sheet URL

Or describe what you have (e.g., "a list of 50 ophthalmologists with just names and states")

Skip questions the user already answered in their initial message.

提取结果快捷方式：检查是否存在当日提取报告：

bash

ls ~/.nimble/memory/reports/healthcare-providers-extract-*$(date +%Y-%m-%d).md 2>/dev/null

若存在当日报告，从文件名中解析

{slug}

并加载

~/.nimble/memory/healthcare-providers-extract/{slug}/providers.json

。执业机构域名和页面URL规则已明确——根据网站URL约定构建个人简介页面URL，完全跳过步骤3。这可避免不必要的N次网页搜索。若不存在当日报告，请勿复用旧的

providers.json

文件。

按照

references/nimble-playbook.md

中的输入解析模式，解析

$ARGUMENTS

以确定输入类型。核心路由规则：

检测到提取输出（providers.json）-> 继续执行步骤2，标记跳过步骤3
检测到CSV/表格/粘贴数据-> 继续执行步骤2
输入不明确-> 询问用户（计入最多2次提示的限制）

若输入明确，确认信息并提出一个引导问题（纯文本，不使用AskUserQuestion）：

"已在您的列表中找到N位从业者。快速确认：

需要补全哪些字段？（联系信息、资质证书、专业领域、患者评价、监管信息——或所有缺口）

医疗垂直领域？（眼科、牙科、皮肤科、全科或其他）"

若输入模糊，使用AskUserQuestion（计入最多2次提示的限制）：

需要补全哪个从业者列表？

直接粘贴从业者数据（姓名 + 已知信息，每行一条）

提供CSV文件路径或Google Sheet链接

或描述您拥有的数据（例如："包含50位仅有名和所在州的眼科医生列表"）

用户在初始消息中已回答的问题可跳过。

Step 2: Analyze Existing Data

步骤2：分析现有数据

Parse the input into structured records. For each provider, identify:

Known fields — what the user already has (name, state, specialty, etc.)
Missing fields — gaps against the 5 core fields from
```
references/provider-extraction-patterns.md
```
(name, credentials, specialty, contact, education)
Enrichment targets — additional fields the user requested (reviews, regulatory, accreditation)

Early exit — no gaps: If all providers are already High confidence (5/5 fields), skip to Step 5 (WSA enrichment) or report: "All providers already have complete profiles. Want me to add supplementary data (reviews, clinical trials, accreditation) instead?"

Build a gap analysis summary:

"Analyzing N providers:

Names: N/N present

Credentials: N/N present (N missing)

Specialty: N/N present (N missing)

Contact info: N/N present (N missing)

Education: N/N present (N missing)

Starting enrichment for N providers with gaps..."

Run Layer 2 WSA discovery now that you know the specialty:

bash

nimble agent list --limit 50 --search "[specialty]"
nimble agent list --limit 50 --search "[directory-user-mentioned]"

See

references/wsa-reference.md

for session-specific discovery.

将输入解析为结构化记录。针对每位从业者，识别：

已知字段——用户已有的信息（姓名、所在州、专业领域等）
缺失字段——与
```
references/provider-extraction-patterns.md
```
中的5个核心字段（姓名、资质证书、专业领域、联系信息、教育背景）相比的缺口
补全目标——用户要求的额外字段（患者评价、监管信息、认证信息）

提前终止——无缺口：若所有从业者的信息均为高可信度（5/5字段完整），跳转至步骤5（WSA补全）或报告："所有从业者的资料已完整。是否需要补充额外数据（患者评价、临床试验、认证信息）？"

构建缺口分析摘要：

"正在分析N位从业者：

姓名：N/N 已填写

资质证书：N/N 已填写（N项缺失）

专业领域：N/N 已填写（N项缺失）

联系信息：N/N 已填写（N项缺失）

教育背景：N/N 已填写（N项缺失）

开始为N位存在信息缺口的从业者补全数据..."

现在已知专业领域，运行第2层WSA发现：

bash

nimble agent list --limit 50 --search "[specialty]"
nimble agent list --limit 50 --search "[directory-user-mentioned]"

请参阅

references/wsa-reference.md

了解会话专属发现流程。

Step 3: Web Search for Provider Identity

步骤3：网页搜索从业者身份

For each provider with gaps, find their practice website and bio page:

bash

nimble search --query "[provider name] [credentials] [location] [specialty]" --max-results 5 --search-depth lite

Search strategy:

Include all known fields in the query to disambiguate common names
Prioritize results from practice websites over directory listings
If the provider has a known practice name, add it to the query
For providers with only name + state, broaden:
```
"[name] [state] doctor"
```

Result selection: Pick the most relevant result — practice bio page > healthcare directory profile > LinkedIn. Save the selected URL for extraction.

For 10+ providers, use sub-agents (see Sub-Agent Strategy below).

Checkpoint (mandatory): You MUST write the checkpoint file before proceeding. Interrupted runs with 20+ providers waste significant API credits without resume.

bash

echo '{...}' > ~/.nimble/memory/healthcare-providers-enrich/checkpoints/{slug}/search.json

针对每位存在信息缺口的从业者，查找其执业网站和个人简介页面：

bash

nimble search --query "[provider name] [credentials] [location] [specialty]" --max-results 5 --search-depth lite

搜索策略：

查询中包含所有已知字段，以区分同名从业者
优先选择执业网站结果，而非目录列表
若从业者有已知执业机构名称，将其加入查询
仅知道姓名+所在州的从业者，扩大查询范围：
```
"[name] [state] doctor"
```

结果选择：挑选最相关的结果——执业机构个人简介页面 > 医疗目录资料 > LinkedIn。保存选中的URL用于提取。

若从业者数量超过10位，使用子Agent（详见下方子Agent策略）。

强制检查点：继续操作前必须写入检查点文件。若中断运行时从业者数量超过20位，会浪费大量API额度且无法恢复。

bash

echo '{...}' > ~/.nimble/memory/healthcare-providers-enrich/checkpoints/{slug}/search.json

Step 4: Extract Missing Fields

步骤4：提取缺失字段

Choose extraction strategy based on provider count. Follow the Scaled Execution pattern from

references/nimble-playbook.md

— it covers individual calls (1-10),

extract-batch

(11-100), and the confirmation gate for larger jobs. Use the Page Extraction with Retry pattern from the same reference for garbage detection and retry logic.

Parse extracted content for missing fields using the detection patterns from

references/provider-extraction-patterns.md

(credential regex, specialty keywords, contact patterns, education mentions).

Merge rules:

Only fill fields that are actually missing — never overwrite existing data
Track which fields were added and their source URL
If extracted data conflicts with existing data, keep the existing value and flag the conflict for user review

Checkpoint (mandatory): You MUST write the checkpoint file before proceeding.

bash

echo '{...}' > ~/.nimble/memory/healthcare-providers-enrich/checkpoints/{slug}/extraction.json

根据从业者数量选择提取策略。遵循

references/nimble-playbook.md

中的规模化执行模式——涵盖单次调用（1-10位）、

extract-batch

（11-100位），以及针对更大任务的确认环节。使用同一文档中的页面提取重试模式处理无效数据和重试逻辑。

按照

references/provider-extraction-patterns.md

中的检测模式（资质正则表达式、专业领域关键词、联系信息格式、教育背景提及）解析提取的内容，获取缺失字段。

合并规则：

仅填充实际缺失的字段——绝不覆盖现有数据
记录添加的字段及其来源URL
若提取的数据与现有数据冲突，保留现有值并标记冲突供用户审核

强制检查点：继续操作前必须写入检查点文件。

bash

echo '{...}' > ~/.nimble/memory/healthcare-providers-enrich/checkpoints/{slug}/extraction.json

Step 5: WSA Enrichment (Optional)

步骤5：WSA补全（可选）

If the user requested reviews, regulatory data, or accreditation — or if the gap analysis shows most core fields are already filled and enrichment adds more value:

Run enrichment-phase WSAs discovered in Step 0. See

references/wsa-reference.md

for the enrichment phase mapping, agent evaluation, and fallback chains.

For each practice or provider, run relevant enrichment agents simultaneously. Follow the Scaled Execution pattern from

references/nimble-playbook.md

for batching.

Merge enrichment data into provider records:

Reviews/ratings -> add as supplementary fields (not part of core 5)
Clinical trial activity -> add as supplementary field
Accreditation status -> add as supplementary field

若用户要求补充患者评价、监管数据或认证信息——或缺口分析显示大部分核心字段已完整，补全可增加更多价值：

运行步骤0中发现的补全阶段WSA。请参阅

references/wsa-reference.md

了解补全阶段映射、Agent评估和后备链条。

针对每个执业机构或从业者，同时运行相关的补全Agent。遵循

references/nimble-playbook.md

中的规模化执行模式进行批量处理。

合并补全数据至从业者记录：

患者评价/评分 -> 添加为补充字段（不属于5个核心字段）
临床试验活动 -> 添加为补充字段
认证状态 -> 添加为补充字段

Step 6: Deduplication & Confidence Scoring

步骤6：去重与可信度评分

Follow the Entity Deduplication and Entity Confidence Scoring patterns from

references/nimble-playbook.md

. Skill-specific dedup rules and the 5-field confidence criteria are in

references/provider-extraction-patterns.md

Enrichment-specific confidence: Score only the newly added fields:

High — field found and confirmed by 2+ sources
Medium — field found from 1 source
Low — field inferred or partially matched

遵循

references/nimble-playbook.md

中的实体去重和实体可信度评分模式。技能专属去重规则和5字段可信度标准位于

references/provider-extraction-patterns.md

中。

补全专属可信度：仅对新增字段评分：

高——字段已找到并经2个及以上来源确认
中——字段仅来自1个来源
低——字段为推断或部分匹配

Step 7: Output

步骤7：输出结果

Present results as an enrichment diff — showing what was added to each provider. Group by practice, sort by confidence within each group, and include a "What This Means" section at the end with actionable next steps.

markdown

undefined

以补全差异的形式展示结果——显示每位从业者新增的信息。按执业机构分组，每组内按可信度排序，末尾添加“解读”部分，提供可执行的后续步骤。

markdown

undefined

Provider Enrichment: [N] Providers Updated

从业者信息补全：[N]位从业者已更新

[Date] | [A] fields added across [P] providers | [H] High, [M] Medium, [L] Low confidence

[日期] | [A]个字段已添加至[P]位从业者 | [H]高可信度、[M]中可信度、[L]低可信度

TL;DR

摘要

Enriched [P] of [T] providers. Added [A] total fields: [breakdown by field type]. [Key finding: e.g., "Found contact info for 18 of 20 providers, 3 have clinical trials"].

已补全[T]位从业者中的[P]位。共添加[A]个字段：[按字段类型细分]。 [关键发现：例如，"为20位从业者中的18位找到了联系信息，其中3位参与临床试验"]。

Enrichment Results

补全结果

#	Name	Added Fields	Confidence	Source
1	Dr. Jane Smith	+credentials (MD, FACS), +contact ((555) 123-4567)	High	source
2	Dr. John Doe	+specialty (General Ophthalmology), +education (Wills Eye)	Medium	source
3	Dr. Alex Chen	+contact ((555) 987-6543)	Low	source

#	姓名	新增字段	可信度	来源
1	Jane Smith医生	+资质证书（MD, FACS）、+联系电话((555) 123-4567)	高	来源
2	John Doe医生	+专业领域（普通眼科）、+教育背景（Wills Eye）	中	来源
3	Alex Chen医生	+联系电话((555) 987-6543)	低	来源

Detailed Records

详细记录

Dr. Jane Smith

Jane Smith医生

Existing: Name, State (TX) Added:

Credentials: MD, FACS — source
Contact: (555) 123-4567 — source
Education: Fellowship, Bascom Palmer Eye Institute — source Confidence: High (3 fields added, 2 sources)

[Repeat per provider with additions]

原有信息：姓名、所在州（TX） 新增信息：

资质证书：MD, FACS — 来源
联系电话：(555) 123-4567 — 来源
教育背景：Bascom Palmer眼科研究所 fellowship — 来源 可信度：高（新增3个字段，来自2个来源）

[每位有新增信息的从业者重复上述格式]

Providers Not Enriched

未补全的从业者

[List providers where no additional data was found, with attempted searches]

[列出未找到任何额外数据的从业者，包含尝试过的搜索内容]

Data Quality Summary

数据质量总结

Fully enriched (5/5 fields): [N] providers
Partially enriched: [N] providers — common gaps: [list]
No new data found: [N] providers

完全补全（5/5字段）：[N]位从业者
部分补全：[N]位从业者——常见缺口：[列表]
未找到新数据：[N]位从业者

Sources

来源

[Clickable URL for every page used, grouped by provider]

[每位从业者使用的所有页面的可点击URL，按从业者分组]

What This Means

解读

[Actionable interpretation: which providers are ready to contact, which need more data, what the enrichment coverage tells you about this list's quality]


**Source links are mandatory.** Every added field must trace back to a source URL.

[可执行的分析：哪些从业者已可联系，哪些需要更多数据，补全覆盖率反映了列表的质量情况]


**必须包含来源链接**。每个新增字段必须可追溯至来源URL。

Step 8: Save to Memory

步骤8：保存至内存

Make all Write calls simultaneously:

Report ->

~/.nimble/memory/reports/healthcare-providers-enrich-{slug}-{date}.md

Enriched data ->

~/.nimble/memory/healthcare-providers-enrich/{slug}/enriched.json

Profile -> update

last_runs.healthcare-providers-enrich

~/.nimble/business-profile.json

(only if profile exists)

Follow the wiki update pattern from
```
references/memory-and-distribution.md
```
: update
```
index.md
```
rows for all affected entity files, append a
```
log.md
```
entry for this run.
Clean up checkpoint (complete run) or keep (partial run)

同时执行所有写入操作：

报告 ->

~/.nimble/memory/reports/healthcare-providers-enrich-{slug}-{date}.md

补全后的数据 ->

~/.nimble/memory/healthcare-providers-enrich/{slug}/enriched.json

配置文件 -> 在

~/.nimble/business-profile.json

中更新

last_runs.healthcare-providers-enrich

（仅当配置文件存在时）

遵循
```
references/memory-and-distribution.md
```
中的Wiki更新模式：更新所有受影响实体文件的
```
index.md
```
行，在
```
log.md
```
中追加本次运行的记录。
清理检查点（运行完成）或保留检查点（运行中断）

Step 9: Share & Distribute

步骤9：分享与分发

Always offer distribution — do not skip. Follow

references/memory-and-distribution.md

for connector detection and sharing flow.

Notion: full enrichment report as a dated subpage. Slack: TL;DR with enrichment summary and field counts only.

必须提供分发选项——不可跳过。遵循

references/memory-and-distribution.md

中的连接器检测和分享流程。

Notion：将完整补全报告保存为带日期的子页面。 Slack：仅发送摘要信息，包含补全总结和字段统计。

Step 10: Follow-ups

步骤10：后续操作

"Tell me more about Dr. X" -> show full enriched profile
"Export as CSV" -> generate CSV with original + enriched fields
"Enrich more fields" -> re-run with expanded field targets
"Which providers still have gaps?" -> filter to incomplete records

Sibling skill suggestions:

Next steps:
Run
healthcare-providers-verify
to validate the enriched credentials and license status
Run
healthcare-providers-extract
to discover more providers from practice websites
Run
market-finder
to find additional practices in this area

"告诉我更多关于X医生的信息" -> 展示完整的补全后资料
"导出为CSV" -> 生成包含原始字段和补全字段的CSV文件
"补全更多字段" -> 扩大字段目标范围重新运行
"哪些从业者仍有信息缺口？" -> 筛选出未完整的记录

兄弟技能建议：

后续步骤：
运行
healthcare-providers-verify
验证补全后的资质证书和执照状态
运行
healthcare-providers-extract
从执业网站发现更多从业者
运行
market-finder
查找该地区的其他执业机构

Sub-Agent Strategy

子Agent策略

For batch enrichment (10+ providers), use

nimble-researcher

agents (

agents/nimble-researcher.md

) to parallelize search and extraction.

Follow the sub-agent spawning rules from

references/nimble-playbook.md

(bypassPermissions, batch max 4, explicit Bash instruction, fallback on failure).

Spawn pattern: One agent per batch of 5 providers. Each agent runs Steps 3-4 for its assigned providers and returns enriched records. Tell each agent to use

nimble extract-batch

for its assigned URLs rather than individual

nimble extract

calls — one batch call per agent is faster and more reliable than sequential calls.

Small batch optimization: If fewer than 10 providers, run directly from the main context instead of spawning agents.

Fallback: If any agent fails, run those enrichments directly from the main context. Never leave gaps in the output.

针对批量补全（10位及以上从业者），使用

nimble-researcher

Agent（

agents/nimble-researcher.md

）并行处理搜索和提取。

遵循

references/nimble-playbook.md

中的子Agent生成规则（bypassPermissions、最大批量4个、明确Bash指令、失败后备方案）。

生成模式：每5位从业者分配1个Agent。每个Agent为其分配的从业者运行步骤3-4，返回补全后的记录。告知每个Agent对分配的URL使用

nimble extract-batch

，而非单独的

nimble extract

调用——每个Agent调用1次批量接口比顺序调用更快更可靠。

小批量优化：若从业者数量少于10位，直接在主上下文运行，无需生成Agent。

后备方案：若任何Agent失败，直接在主上下文运行该部分补全任务。输出结果中绝不能存在缺口。

Error Handling

错误处理

See

references/nimble-playbook.md

for the standard error table (missing API key, 429, 401, empty results, extraction garbage). Skill-specific errors:

No search results for provider: "Couldn't find a web presence for [name] in [state]. The name may be too common or the provider may not have an online presence. Want me to try with additional context (practice name, specialty)?"
Ambiguous provider match: "Found multiple providers named [name] in [state]. Can you confirm which one? [list top 3 with practice names]"
All extractions returned garbage: "The provider websites appear to be heavily JavaScript-rendered. Retrying with browser rendering..." (auto-retry with
```
--render
```
per the shared pattern)
CSV/Sheet parse error: "Couldn't parse the input file. Expected columns with provider names and at least one identifier (state, specialty, or practice). Can you paste the data directly instead?"
No gaps detected: Handled in Step 2 (early exit to WSA enrichment or report).

请参阅

references/nimble-playbook.md

中的标准错误表（缺失API密钥、429错误、401错误、空结果、无效提取数据）。技能专属错误：

未找到从业者搜索结果："无法在[所在州]找到[name]的网络信息。该姓名可能过于常见，或从业者无线上曝光。是否需要尝试添加更多上下文（执业机构名称、专业领域）？"
从业者匹配模糊："在[所在州]找到多位名为[name]的从业者。能否确认是哪一位？[列出前3位及其执业机构名称]"
所有提取结果均无效："从业者网站似乎大量使用JavaScript渲染。正在尝试使用浏览器渲染重试..."（按照共享模式自动使用
```
--render
```
重试）
CSV/表格解析错误："无法解析输入文件。预期包含从业者姓名和至少一个标识符（所在州、专业领域或执业机构）的列。能否直接粘贴数据？"
未检测到信息缺口：已在步骤2处理（提前终止至WSA补全或报告）。