market-finder

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Market Finder

市场查找器

Market intelligence powered by Nimble Web Search Agents.

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).

由Nimble Web Search Agents提供支持的市场情报工具。

用户请求：$ARGUMENTS

在运行任何命令之前，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

步骤0：预检

Run the preflight pattern from

references/nimble-playbook.md

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

Also simultaneously:

mkdir -p ~/.nimble/memory/{reports,market-finder/checkpoints}

Check for existing checkpoints:

ls ~/.nimble/memory/market-finder/checkpoints/ 2>/dev/null

From the results:

CLI missing or API key unset ->
```
references/profile-and-onboarding.md
```
, stop
Profile exists -> note industry keywords if any. Apply smart date windowing from
```
references/nimble-playbook.md
```
. Market-finder tweak: in quick refresh mode, skip enrichment and only discover new metros.
No profile -> fine. Market-finder doesn't require onboarding. Proceed to Step 1.

执行

references/nimble-playbook.md

中的预检流程（5个并行Bash调用：日期计算、当前日期、CLI检查、配置文件加载、index.md加载）。

同时执行以下操作：

mkdir -p ~/.nimble/memory/{reports,market-finder/checkpoints}

检查现有检查点：

ls ~/.nimble/memory/market-finder/checkpoints/ 2>/dev/null

根据结果执行：

CLI缺失或API密钥未设置 -> 跳转至
```
references/profile-and-onboarding.md
```
，停止操作
配置文件已存在 -> 记录行业关键词（如有）。应用
```
references/nimble-playbook.md
```
中的智能日期窗口策略。市场查找器优化：快速刷新模式下，跳过信息补充步骤，仅发现新都会区。
无配置文件 -> 无需处理。市场查找器无需引导流程，直接进入步骤1。

Step 1: Parse Request & Detect Mode

步骤1：解析请求并检测模式

Parse

$ARGUMENTS

for business type, geography, qualifiers, and mode detection.

解析

$ARGUMENTS

中的企业类型、地理区域、限定条件，并进行模式检测。

Mode detection

模式检测

Check

$ARGUMENTS

for a reference list. Read

references/audit-mode.md

for the full detection signals and parsing rules.

Signal	Mode
Google Sheet URL, CSV path, or inline list of 3+ businesses	Audit
Explicit audit language ("audit my list", "compare against", "gap analysis")	Audit
No reference list provided	Discovery (default)

If a reference list is present but intent is ambiguous, ask: "Want me to audit your list against fresh discovery, or use it as a starting point?"

If audit language is detected but no reference list is provided, ask: "You mentioned auditing — please provide your list (Google Sheet URL, CSV file path, or paste inline)." Do not proceed with Audit mode until a reference list is received.

检查

$ARGUMENTS

中是否包含参考列表。详细检测信号和解析规则请阅读

references/audit-mode.md

。

信号	模式
Google表格URL、CSV路径或包含3个以上企业的内联列表	审计模式
明确的审计类表述（"audit my list"、"compare against"、"gap analysis"）	审计模式
未提供参考列表	发现模式（默认）

若存在参考列表但意图不明确，请询问："您希望我将您的列表与最新发现结果进行审计比对，还是将其作为发现起点？"

若检测到审计表述但未提供参考列表，请询问："您提到了审计操作——请提供您的列表（Google表格URL、CSV文件路径或直接粘贴内联内容）。" 在收到参考列表前，请勿进入审计模式。

Extract fields

字段提取

Field	Required	Source
Business type / vertical	Yes	User input ("dentists", "SaaS CRM tools")
Geography	Yes (except SaaS)	User input ("Florida", "Austin TX", "nationwide")
Reference list	Audit mode only	Google Sheet URL, CSV path, or inline
Qualification criteria	Optional	User input ("must have website", "10+ reviews")
Output preference	Optional	User input ("quick summary", "full dataset")

If both type and geography are clear from

$ARGUMENTS

, confirm briefly and proceed: "Finding dentists in Florida..." (or "Auditing your list against dentists in Florida..." in Audit mode)

If partial or ambiguous, ask one combined question (counts as 1 of max 2 AskUserQuestion prompts):

Use AskUserQuestion with up to 3 questions:

Vertical -- "What type of business?" with options: Healthcare, SaaS/Software, Restaurants/Food, Legal/Financial, Auto/Home Services, Other
Geography -- "What geography?" (free text or: City, State, Region, Nationwide)
Depth -- "Quick scan or comprehensive discovery?"

Skip questions already answered by

$ARGUMENTS

Depth modes (determines how much work each step does):

Depth	Discovery	Enrichment	Verification	Distribution
Quick scan	All sources, 1 pass	Skip (or top 5 only)	Top 5 entities	Offer
Comprehensive	All sources + fallback retries	Full	All entities	Offer

字段	是否必填	来源
企业类型/垂直领域	是	用户输入（如"牙医"、"SaaS CRM工具"）
地理区域	是（SaaS领域除外）	用户输入（如"佛罗里达州"、"德克萨斯州奥斯汀"、"全国范围"）
参考列表	仅审计模式需提供	Google表格URL、CSV路径或内联内容
筛选标准	可选	用户输入（如"必须拥有官网"、"10条以上评价"）
输出偏好	可选	用户输入（如"快速摘要"、"完整数据集"）

若
$ARGUMENTS
中明确包含企业类型和地理区域，请简要确认后继续："正在查找佛罗里达州的牙医..."（审计模式下表述为："正在将您的列表与佛罗里达州的牙医最新发现结果进行比对..."）

若信息不全或模糊，请合并为一个问题询问（最多占用2次AskUserQuestion提示中的1次）：

使用AskUserQuestion最多提出3个问题：

垂直领域 -- "您需要查找哪种类型的企业？"选项包括：医疗、SaaS/软件、餐饮/食品、法律/金融、汽车/家居服务、其他
地理区域 -- "目标地理区域是？"（自由文本或选项：城市、州、地区、全国范围）
深度 -- "快速扫描还是全面发现？"

跳过

$ARGUMENTS

中已明确回答的问题。

深度模式（决定各步骤的工作量）：

深度	发现环节	信息补充环节	验证环节	分发环节
快速扫描	覆盖所有来源，单次遍历	跳过（或仅处理前5个结果）	仅验证前5个实体	提供选项
全面模式	覆盖所有来源+ fallback重试	完整处理	验证所有实体	提供选项

Step 2: Vertical Detection & Preset Loading

步骤2：垂直领域检测与预设加载

Read

references/vertical-presets.md

and match the user's business type against preset trigger keywords.

Match	Action
Clear match	Load that preset's WSA routing and query pattern
Partial match	Confirm: "This looks like Healthcare. Use healthcare presets?"
No match	Use Custom preset with user's keywords
SaaS match	Switch to non-geographic pipeline (no geo-tiling)

Note which discovery WSAs and enrichment WSAs the preset specifies.

阅读

references/vertical-presets.md

，将用户输入的企业类型与预设触发关键词匹配。

匹配情况	操作
明确匹配	加载对应预设的WSA路由和查询模式
部分匹配	确认："这看起来属于医疗领域。是否使用医疗领域预设？"
无匹配	使用自定义预设，采用用户输入的关键词
匹配SaaS	切换至非地理管道（无需地理分片）

记录预设指定的发现类WSA和信息补充类WSA。

Step 3: Geographic Scoping

步骤3：地理范围划定

Skip this step for SaaS vertical (no geography needed).

Geography level	Tiling strategy
City	Single query, no tiling
Metro area	Single query per WSA
State	Tile by top 5-10 metros in the state
Region	Tile by states, then top metros per state
Nationwide	Tile by all states, then top metros per state

Estimate API calls:

metros * discovery_wsas * (1 + enrichment_ratio)

where

enrichment_ratio

is ~0.3. Follow the Scaled Execution pattern from

references/nimble-playbook.md

to choose execution tier (individual / batch / multi-batch / confirmation gate):

Estimated API calls: ~1,560 (50 states x 8 metros x 3 WSAs + enrichment)
This is a nationwide search. Proceed? [Y/n]

Derive a

slug

for checkpointing: lowercase, hyphenated, includes vertical + geo (e.g.,

dentists-florida

saas-crm-tools

hvac-nationwide

SaaS垂直领域跳过此步骤（无需地理信息）。

地理层级	分片策略
城市	单次查询，无需分片
都会区	每个WSA执行单次查询
州	按州内Top 5-10都会区分片
地区	先按州分片，再按各州Top都会区分片
全国范围	按所有州分片，再按各州Top都会区分片

估算API调用量：

都会区数量 × 发现类WSA数量 × (1 + 信息补充占比)

，其中

信息补充占比

约为0.3。遵循

references/nimble-playbook.md

中的规模化执行模式选择执行层级（单个任务/批量任务/多批任务/确认 gate）：

预估API调用量：约1,560次（50个州 × 8个都会区 × 3个WSA + 信息补充）
这是全国范围搜索。是否继续？[Y/n]

生成用于检查点的

slug

：小写、连字符分隔，包含垂直领域+地理信息（例如

dentists-florida

、

saas-crm-tools

、

hvac-nationwide

）。

Step 4: Check for Existing Checkpoint

步骤4：检查现有检查点

Follow the Checkpointing & Resume pattern from

references/memory-and-distribution.md

Check:

cat ~/.nimble/memory/market-finder/checkpoints/{slug}/discovery.json 2>/dev/null

Checkpoint found -> offer: "Found previous run ({N} entities from {date}). Resume and fill gaps, or start fresh?"
No checkpoint -> proceed to Step 5

遵循

references/memory-and-distribution.md

中的检查点与恢复模式。

执行检查：

cat ~/.nimble/memory/market-finder/checkpoints/{slug}/discovery.json 2>/dev/null

找到检查点 -> 提供选项："发现之前的运行记录（{N}个实体，创建于{date}）。是否恢复并补充缺失数据，还是重新开始？"
无检查点 -> 进入步骤5

Step 5: WSA Discovery & Execution

步骤5：WSA发现与执行

5a: Discover available WSAs

5a：发现可用WSA

For each target domain in the selected vertical preset, discover current WSAs:

bash

nimble agent list --search "{domain}" --limit 20

Run these searches simultaneously (one per target domain). From the results:

Filter by entity_type (SERP for discovery, PDP/Profile for enrichment)

Prefer

managed_by: "nimble"

over

managed_by: "community"

If no WSA found for a domain, mark it for
```
nimble search
```
fallback
If no WSAs found for ANY domain, fall back entirely to
```
nimble search
```
for all metros

Then validate each discovered WSA's input params:

bash

nimble agent get --template-name {discovered_name}

Cache the discovered WSA names + params for the rest of the run.

针对所选垂直预设中的每个目标域名，查找当前可用的WSA：

bash

nimble agent list --search "{domain}" --limit 20

并行执行这些搜索（每个目标域名一次）。根据结果：

按entity_type筛选（发现类用SERP，信息补充类用PDP/Profile）

优先选择

managed_by: "nimble"

而非

managed_by: "community"

若某域名未找到WSA，标记为需使用
```
nimble search
```
作为fallback
若所有域名均未找到WSA，则完全改用
```
nimble search
```
处理所有都会区

然后验证每个发现的WSA的输入参数：

bash

nimble agent get --template-name {discovered_name}

缓存发现的WSA名称+参数，供后续流程使用。

5b: Geographic discovery (all except SaaS)

5b：地理发现（SaaS领域除外）

For each metro in the tiling plan, run the discovered WSAs simultaneously:

bash

nimble agent run --agent {maps_wsa} --params '{...validated params...}'

bash

nimble agent run --agent {yelp_wsa} --params '{...validated params...}'

Run tertiary domain WSAs only if the preset includes them AND primary + secondary return < 10 combined unique results for that metro.

Choose execution tier per the Scaled Execution pattern in

references/nimble-playbook.md

(based on total estimated calls from Step 3).

针对分片计划中的每个都会区，并行运行已发现的WSA：

bash

nimble agent run --agent {maps_wsa} --params '{...validated params...}'

bash

nimble agent run --agent {yelp_wsa} --params '{...validated params...}'

仅当预设包含三级域名WSA，且一级+二级WSA返回的唯一结果合计少于10个时，才运行三级域名WSA。

根据步骤3估算的总调用量，遵循

references/nimble-playbook.md

中的规模化执行模式选择执行层级。

5c: SaaS discovery (non-geographic)

5c：SaaS发现（非地理模式）

SaaS skips WSA discovery. Run the two-pass search queries defined in the SaaS preset from

references/vertical-presets.md

Pass 1 -- Product discovery: G2, Capterra, general, ProductHunt, GitHub
Pass 2 -- Financial discovery: Crunchbase, funding news, market landscape

Both passes run simultaneously. Pass 2 is critical -- without it, funding and traction data will be missing or wrong.

SaaS领域跳过WSA发现步骤。运行

references/vertical-presets.md

中SaaS预设定义的两轮搜索查询：

第一轮——产品发现：G2、Capterra、通用搜索、ProductHunt、GitHub
第二轮——财务发现：Crunchbase、融资新闻、市场格局

两轮搜索并行执行。第二轮至关重要——缺少此步骤，融资和用户规模数据将缺失或不准确。

5d: Fallback

5d：Fallback方案

If no WSA was found for a target domain, or if a WSA fails for any metro:

bash

nimble search --query "[type] in [metro]" --max-results 20 --search-depth lite

After discovery:

Parse all results into a unified entity list
Deduplicate following the Entity Deduplication pattern from
```
references/nimble-playbook.md
```
: place_id -> domain -> fuzzy name + city
Track
```
source_count
```
per entity (how many WSAs/sources found it)

Save checkpoint:

~/.nimble/memory/market-finder/checkpoints/{slug}/discovery.json

若某目标域名未找到WSA，或某都会区的WSA执行失败：

bash

nimble search --query "[type] in [metro]" --max-results 20 --search-depth lite

发现完成后：

将所有结果解析为统一实体列表
遵循
```
references/nimble-playbook.md
```
中的实体去重规则去重：place_id → 域名 → 模糊名称+城市
跟踪每个实体的
```
source_count
```
（发现该实体的WSA/来源数量）

保存检查点：

~/.nimble/memory/market-finder/checkpoints/{slug}/discovery.json

Step 6: Enrichment

步骤6：信息补充

Run enrichment using the WSAs discovered in Step 5a for the preset's enrichment target domains. Prioritize entities with the highest source count first. Choose execution tier per Scaled Execution in

references/nimble-playbook.md

bash

nimble agent run --agent {enrichment_wsa} --params '{...validated params...}'

Only run enrichment WSAs that apply to the current vertical's enrichment targets (see

references/vertical-presets.md

). Skip entities without the required ID/URL for the enrichment WSA.

Save checkpoint:

~/.nimble/memory/market-finder/checkpoints/{slug}/enrichment.json

使用步骤5a中发现的、对应预设信息补充目标域名的WSA执行信息补充。优先处理

source_count

最高的实体。遵循

references/nimble-playbook.md

中的规模化执行模式选择执行层级。

bash

nimble agent run --agent {enrichment_wsa} --params '{...validated params...}'

仅运行适用于当前垂直领域信息补充目标的WSA（详见

references/vertical-presets.md

）。跳过缺少信息补充WSA所需ID/URL的实体。

保存检查点：

~/.nimble/memory/market-finder/checkpoints/{slug}/enrichment.json

Step 6b: Financial Verification (SaaS vertical)

步骤6b：财务验证（仅SaaS垂直领域）

For SaaS entities, verify funding claims before reporting. Never label a company's funding stage without a source.

For each entity in the top results (top 5 in quick scan, all in comprehensive):

bash

nimble search --query "{company name} funding raised series" --max-results 5 --search-depth lite

Source found: Use the sourced amount and date
No source found: Display "Undisclosed" -- never guess "Early stage" or "Bootstrapped"

This step prevents publishing unverified financial claims. It's fast (one search per entity, lite depth) and catches recent funding rounds that directory sites miss.

对于SaaS实体，在报告前验证融资信息。未找到来源时，切勿标注企业的融资阶段。

针对顶级结果（快速扫描模式下为前5个，全面模式下为所有实体）：

bash

nimble search --query "{company name} funding raised series" --max-results 5 --search-depth lite

找到来源：使用来源中的金额和日期
未找到来源：显示"未披露"——切勿猜测为"早期阶段"或"自举"

此步骤可避免发布未经验证的财务信息。操作快速（每个实体一次搜索，lite深度），可捕获目录网站未收录的最新融资轮次。

Step 7: Deduplication & Scoring

步骤7：去重与评分

Final deduplication: Run a final dedup pass across all phases following the Entity Deduplication pattern from

references/nimble-playbook.md

. Merge fields from multiple sources into a single record per entity.

Discovery strength scoring (skill-specific, varies by vertical):

Geographic verticals (Healthcare, Restaurants, Legal, Auto/Home, Custom):

Level	Criteria
High	3+ sources OR 2+ sources with reviews > 50
Medium	2 sources OR 1 source with reviews > 10
Low	1 source only, few/no reviews

SaaS vertical (funding + directory presence matter more than review count):

Level	Criteria
High	Verified funding > $10M OR 3+ directory sources OR 1000+ G2 reviews
Medium	Verified funding < $10M OR 2 sources OR 100+ G2 reviews
Low	1 source only, no verified funding, few reviews

Display as:

*** High

** Medium

* Low

最终去重：遵循

references/nimble-playbook.md

中的实体去重规则，对所有阶段的结果执行最终去重。将多个来源的字段合并为单个实体记录。

发现强度评分（工具专属，因垂直领域而异）：

地理类垂直领域（医疗、餐饮、法律、汽车/家居、自定义）：

等级	标准
高	3个以上来源或 2个以上来源且评价数>50
中	2个来源或 1个来源且评价数>10
低	仅1个来源，评价数极少或无

SaaS垂直领域（融资+目录收录比评价数更重要）：

等级	标准
高	已验证融资>1000万美元或 3个以上目录来源或 G2评价数>1000
中	已验证融资<1000万美元或 2个来源或 G2评价数>100
低	仅1个来源，无已验证融资，评价数极少

显示格式：

*** 高

** 中

* 低

Step 7b: Audit Comparison (Audit mode only)

步骤7b：审计比对（仅审计模式）

Skip this step in Discovery mode.

Read

references/audit-mode.md

for the full matching algorithm, normalization rules, and output template.

Parse reference list — detect format (Google Sheet / CSV / inline), extract records, normalize to
```
{name, domain, city, state, phone}
```
per the parsing rules in
```
references/audit-mode.md
```
Run three matching layers in order (domain → name+city → phone). Once an entity matches at any layer, stop. Track which layer produced the match.
Categorize every entity:
- ```
matched
```
  — in both reference list and discovery results
- ```
discovered_only
```
  — found by discovery, not in reference list
- ```
reference_only
```
  — in reference list, not found by discovery
Calculate coverage score —
```
matched / reference_count × 100
```

Proceed to Step 8 with the categorized results.

发现模式跳过此步骤。

完整匹配算法、标准化规则和输出模板请阅读

references/audit-mode.md

。

解析参考列表 — 检测格式（Google表格/CSV/内联），提取记录，按照
```
references/audit-mode.md
```
中的解析规则标准化为
```
{name, domain, city, state, phone}
```
格式
执行三层匹配（按顺序：域名 → 名称+城市 → 电话）。实体在任意层级匹配后即停止，记录匹配层级。
分类所有实体：
- ```
matched
```
  — 同时存在于参考列表和发现结果中
- ```
discovered_only
```
  — 发现结果中有，但参考列表中无
- ```
reference_only
```
  — 参考列表中有，但发现结果中无
计算覆盖率得分 —
```
matched / reference_count × 100
```

携带分类结果进入步骤8。

Step 8: Output

步骤8：输出

undefined

undefined

Market Finder: [Business Type] in [Geography]

市场查找器：[企业类型] in [地理区域]

Found [N] businesses | [Date] | Strength: [H] High, [M] Medium, [L] Low

发现[N]家企业 | [日期] | 强度分布：[H]高，[M]中，[L]低

Summary

摘要

Total discovered: [N] unique businesses across [M] metros
Geographic breakdown: [top 5 metros by count]
Source coverage: [list each source used with entity counts]

总发现数： [N]家独特企业，覆盖[M]个都会区
地理分布： [按数量排名前5的都会区]
来源覆盖： [列出每个来源及对应的实体数量]

顶级结果（高强度）

#	Name	Location	Rating	Reviews	Strength	Sources
1	Acme Dental	Miami, FL	4.8	312	*** High	Maps, Yelp, BBB
2	WidgetCo Health	Orlando, FL	4.6	89	*** High	Maps, Yelp
...

#	名称	位置	评分	评价数	强度	来源
1	Acme Dental	佛罗里达州迈阿密	4.8	312	*** 高	Maps, Yelp, BBB
2	WidgetCo Health	佛罗里达州奥兰多	4.6	89	*** 高	Maps, Yelp
...

All Results by Geography

按地理区域划分的所有结果

Miami, FL ([n] businesses)

佛罗里达州迈阿密（[n]家企业）

[Table of businesses in this metro]

[该都会区的企业表格]

Orlando, FL ([n] businesses)

佛罗里达州奥兰多（[n]家企业）

[Table of businesses in this metro] ...

[该都会区的企业表格] ...

What's Missing

缺失内容

[Data gaps: metros with low coverage, entities without websites, etc.]


**SaaS output variant** (when vertical is SaaS, replace "All Results by Geography"
with tier-based grouping):

[数据缺口：覆盖度低的都会区、无官网的实体等]


**SaaS领域输出变体**（垂直领域为SaaS时，将"按地理区域划分的所有结果"替换为基于层级的分组）：

Players by Tier

按层级划分的参与者

Pure-Play (dedicated to this vertical)

纯垂直领域（专注于该领域）

| # | 名称 | 域名 | 融资情况 | 关键指标 | 强度 | 来源 | ...

Adjacent (feature overlap from larger platforms)

相邻领域（来自大型平台的功能重叠产品）

| # | 名称 | 域名 | 融资情况 | 关键指标 | 强度 | 来源 | ...

Open Source

开源产品


**Source links are mandatory.** Every entity must have at least one clickable source
URL (Google Maps link, Yelp listing, website, BBB profile, G2 page, or GitHub repo).

**Audit output variant** (when in Audit mode, replace the Discovery output above):
Use the audit output template from `references/audit-mode.md`. Key sections: Summary
with coverage score, Matched table, Discovered Only table (expansion candidates),
Reference Only table (coverage gaps), and "What This Means" interpretation.

| # | 名称 | 仓库地址 | Star数 | 关键指标 | 强度 | 来源 | ...


**来源链接为必填项**。每个实体必须至少包含一个可点击的来源URL（Google Maps链接、Yelp列表、官网、BBB档案、G2页面或GitHub仓库）。

**审计模式输出变体**（审计模式下，替换上述发现模式输出）：
使用`references/audit-mode.md`中的审计输出模板。核心部分：包含覆盖率得分的摘要、匹配项表格、仅发现项表格（拓展候选）、仅参考项表格（覆盖缺口）以及"结果解读"部分。

Step 9: Save to Memory

步骤9：保存至内存

Make all Write calls simultaneously:

Discovery mode:

Report ->

~/.nimble/memory/reports/market-finder-{slug}-{date}.md

Entity data ->

~/.nimble/memory/market-finder/{slug}/entities.json

Audit mode:

Report ->

~/.nimble/memory/reports/market-finder-audit-{slug}-{date}.md

Structured data ->
```
~/.nimble/memory/market-finder/{slug}/audit-{date}.json
```
(all three categories with match metadata)

Both modes:

Profile -> update

last_runs.market-finder

~/.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)

并行执行所有写入操作：

发现模式：

报告 ->

~/.nimble/memory/reports/market-finder-{slug}-{date}.md

实体数据 ->

~/.nimble/memory/market-finder/{slug}/entities.json

审计模式：

报告 ->

~/.nimble/memory/reports/market-finder-audit-{slug}-{date}.md

结构化数据 ->
```
~/.nimble/memory/market-finder/{slug}/audit-{date}.json
```
（包含三个分类及匹配元数据）

两种模式通用：

配置文件 -> 更新
```
~/.nimble/business-profile.json
```
中的
```
last_runs.market-finder
```
字段（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对应的
```
index.md
```
行，在
```
log.md
```
中追加本次运行记录。
清理检查点（运行完成）或保留检查点（运行中断）

Step 10: Share & Distribute

步骤10：分享与分发

Always offer distribution -- do not skip this step. Follow

references/memory-and-distribution.md

for connector detection, sharing flow, and source links enforcement.

Notion: full results table as a dated subpage. Slack: TL;DR with total count + top 10 entities only.

必须提供分发选项——请勿跳过此步骤。遵循

references/memory-and-distribution.md

中的连接器检测、分享流程和来源链接强制规则。

Notion：将完整结果表格保存为带日期的子页面。 Slack：仅提供TL;DR摘要，包含总数量+前10个实体。

Step 11: Follow-ups

步骤11：后续操作

Discovery mode follow-ups:

"Tell me more about #N" -> show full detail for that entity
"Filter by [criteria]" -> re-filter existing results
"Expand to [new geography]" -> add metros and re-run discovery
"Export as CSV" -> generate CSV from entities.json
"Run enrichment on all" -> extend enrichment beyond top entities
"Audit against my existing list" -> switch to Audit mode with this run's results
"Looks good" -> done

Audit mode follow-ups:

"Export discovered-only as CSV for outreach?" -> CSV of expansion candidates
"Investigate reference-only gaps?" -> targeted searches for reference_only entries
"Run company-deep-dive on new discoveries?" -> deep research on discovered_only
"Re-run with a different geography?" -> audit the same list against a new area
"Looks good" -> done

Sibling skill suggestions:

Next steps:
Run
company-deep-dive
for a full 360 profile on any business from this list
Run
competitor-positioning
to compare top players in this market
Run
local-places
for neighborhood-level discovery with social enrichment and maps

发现模式后续操作：

"告诉我第[N]个实体的详情" -> 展示该实体的完整信息
"按[条件]筛选" -> 重新筛选现有结果
"拓展至[新地理区域]" -> 添加都会区并重新运行发现流程
"导出为CSV" -> 从entities.json生成CSV文件
"为所有实体执行信息补充" -> 针对所有实体拓展信息补充步骤
"与我的现有列表进行审计比对" -> 切换至审计模式，使用本次运行结果
"结果满意" -> 操作完成

审计模式后续操作：

"将仅发现项导出为CSV用于触达？" -> 生成拓展候选的CSV文件
"调查仅参考项的缺口？" -> 针对reference_only条目执行定向搜索
"对新发现的企业执行company-deep-dive？" -> 对discovered_only实体进行深度调研
"针对新地理区域重新运行审计？" -> 将同一列表与新区域的发现结果进行比对
"结果满意" -> 操作完成

关联工具建议：

下一步操作建议：
运行
company-deep-dive
获取此列表中任意企业的全方位档案
运行
competitor-positioning
对比该市场中的顶级参与者
运行
local-places
进行社区级发现，附带社交信息补充和地图功能

Sub-Agent Strategy

子Agent策略

For large jobs,

nimble agent run-batch

handles WSA parallelism server-side (see Scaled Execution in

references/nimble-playbook.md

). Sub-agents are useful for preparing batch inputs and processing results, not for running individual WSA calls.

Use

nimble-researcher

agents (

agents/nimble-researcher.md

) when:

Building metro query lists for large geographies (one agent per state)
Processing and deduplicating batch results in parallel

Follow the sub-agent spawning rules from

references/nimble-playbook.md

(bypassPermissions, batch max 4, fallback on failure).

对于大型任务，

nimble agent run-batch

在服务器端处理WSA并行执行（详见

references/nimble-playbook.md

中的规模化执行）。子Agent适用于准备批量输入和处理结果，而非运行单个WSA调用。

在以下场景使用

nimble-researcher

Agent（

agents/nimble-researcher.md

）：

为大型地理区域构建都会区查询列表（每个州分配一个Agent）
并行处理和去重批量结果

遵循

references/nimble-playbook.md

中的子Agent生成规则（bypassPermissions、批量最大4个、失败时fallback）。

Agent Teams Mode (Dual-Mode)

Agent团队模式（双模式）

Check at startup:

echo $CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS

Team mode (flag set): Spawn teammates for parallel phases:

Discovery teammate(s): Run all discovery WSAs across metro batches
Enrichment teammate: Run enrichment WSAs for top entities
Lead (you): Coordinate, scope, deduplicate, score, generate output

Solo mode (flag not set): Standard sequential flow from Steps 5-8.

启动时检查：

echo $CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS

团队模式（已设置标志）：为并行阶段生成队友：

发现队友： 跨都会区批次运行所有发现类WSA
信息补充队友： 为顶级实体运行信息补充类WSA
负责人（您）： 协调、划定范围、去重、评分、生成输出

单例模式（未设置标志）：按照步骤5-8执行标准顺序流程。

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:

WSA not found: Skip silently and rely on other discovery sources. Log which WSAs were unavailable.
Search 500/timeout: Retry once without
```
--focus
```
flag. If still failing, retry with a simplified query. Log the failure but don't skip the entire search category -- partial data is better than none.
No results for metro: "No [type] found in [metro]. Skipping to next metro." Don't abort the entire job for one empty metro.
Ambiguous business type: "Did you mean [option A] or [option B]?" (e.g., "practice" could be medical, dental, legal)
SaaS with geography: If the selected preset has no geo-tiling but the user specified a geography, offer it as a search qualifier instead.
Reference list parse failure: If Google Sheet extraction returns garbage or CSV is malformed, ask the user to paste the data inline instead.
Empty reference list: If parsed list has 0 valid records, warn and offer to switch to Discovery mode.
No matches found: If all three matching layers produce zero matches, report it — a 0% coverage score is valid and informative.

标准错误表（缺失API密钥、429、401、空结果、提取异常）请参阅

references/nimble-playbook.md

。工具专属错误处理：

未找到WSA： 静默跳过，依赖其他发现来源。记录不可用的WSA。
搜索500/超时： 不带
```
--focus
```
标志重试一次。若仍失败，使用简化查询重试。记录失败情况，但不要跳过整个搜索类别——部分数据优于无数据。
都会区无结果： "在[metro]未找到[type]。跳至下一个都会区。" 切勿因一个空都会区终止整个任务。
企业类型模糊： "您指的是[选项A]还是[选项B]？" （例如"practice"可能指医疗、牙科或法律机构）
SaaS领域指定地理区域： 若所选预设无需地理分片但用户指定了地理区域，将其作为搜索限定词。
参考列表解析失败： 若Google表格提取结果异常或CSV格式错误，请用户直接粘贴内联数据。
空参考列表： 若解析后的列表包含0条有效记录，发出警告并提供切换至发现模式的选项。
无匹配项： 若三层匹配均未找到任何匹配项，如实报告——0%覆盖率得分是有效且有价值的信息。

market-finder

Original

Translation

Market Finder

市场查找器

Instructions

操作说明

Step 0: Preflight

步骤0：预检

Step 1: Parse Request & Detect Mode

步骤1：解析请求并检测模式

Mode detection

模式检测

Extract fields

字段提取

Step 2: Vertical Detection & Preset Loading

步骤2：垂直领域检测与预设加载

Step 3: Geographic Scoping

步骤3：地理范围划定

Step 4: Check for Existing Checkpoint

步骤4：检查现有检查点

Step 5: WSA Discovery & Execution

步骤5：WSA发现与执行

5a: Discover available WSAs

5a：发现可用WSA

5b: Geographic discovery (all except SaaS)

5b：地理发现（SaaS领域除外）

5c: SaaS discovery (non-geographic)

5c：SaaS发现（非地理模式）

5d: Fallback

5d：Fallback方案

Step 6: Enrichment

步骤6：信息补充

Step 6b: Financial Verification (SaaS vertical)

步骤6b：财务验证（仅SaaS垂直领域）

Step 7: Deduplication & Scoring

步骤7：去重与评分

Step 7b: Audit Comparison (Audit mode only)

步骤7b：审计比对（仅审计模式）

Step 8: Output

步骤8：输出

Market Finder: [Business Type] in [Geography]

市场查找器：[企业类型] in [地理区域]

Summary

摘要

Top Results (High Strength)

顶级结果（高强度）

All Results by Geography

按地理区域划分的所有结果

Miami, FL ([n] businesses)

佛罗里达州迈阿密（[n]家企业）

Orlando, FL ([n] businesses)

佛罗里达州奥兰多（[n]家企业）

What's Missing

缺失内容

Players by Tier

按层级划分的参与者

Pure-Play (dedicated to this vertical)

纯垂直领域（专注于该领域）

Adjacent (feature overlap from larger platforms)

相邻领域（来自大型平台的功能重叠产品）

Open Source

开源产品

Step 9: Save to Memory

步骤9：保存至内存

Step 10: Share & Distribute

步骤10：分享与分发

Step 11: Follow-ups

步骤11：后续操作

Sub-Agent Strategy

子Agent策略

Agent Teams Mode (Dual-Mode)

Agent团队模式（双模式）

Error Handling

错误处理