研究销售线索与客户优先级
梳理公司背景、联系人画像与购买信号,提供研究清单及潜在客户优先级评分方法。
完整提示词
---
name: sales-research
description: 本技能提供研究销售线索的方法论和最佳实践。
---
# 销售研究
## 概述
本技能提供研究销售线索的方法论和最佳实践。涵盖公司研究、联系人画像和信号检测,以挖掘可操作的情报。
## 使用方式
当 company-researcher 和 contact-researcher 子代理执行以下操作时,会引用本技能:
- 研究新线索
- 查找公司信息
- 为个人联系人建立画像
- 检测购买信号
## 研究方法论
### 公司研究清单
1. **基础资料**
- 公司名称、行业、规模(员工数、收入)
- 总部及主要办公地点
- 成立日期、发展阶段
2. **近期动态**
- 融资公告(过去 12 个月)
- 并购活动
- 高管变动
- 产品发布
3. **技术栈**
- 已知技术(BuiltWith、StackShare)
- 招聘岗位中提及的工具
- 集成合作伙伴
4. **信号**
- 招聘岗位(扩张 = 机会)
- Glassdoor 评论(痛点)
- 新闻提及(背景信息)
- 社交媒体动态
### 联系人研究清单
1. **职业背景**
- 当前职位及任职时长
- 以往公司及职位
- 教育背景
2. **影响力指标**
- 汇报关系
- 决策权
- 预算权
3. **互动切入点**
- 最近的 LinkedIn 帖子
- 发表的文章
- 演讲活动
- 共同联系人
## 资源
- `resources/signal-indicators.md` - 购买信号分类法
- `resources/research-checklist.md` - 完整研究清单
## 脚本
- `scripts/company-enricher.py` - 从多个来源聚合公司数据
- `scripts/linkedin-parser.py` - 结构化 LinkedIn 个人资料数据
FILE:company-enricher.py
#!/usr/bin/env python3
"""
company-enricher.py - 从多个来源聚合公司数据
输入:
- company_name: 字符串
- domain: 字符串(可选)
输出:
- profile:
name: 字符串
industry: 字符串
size: 字符串
funding: 字符串
tech_stack: [字符串]
recent_news: [新闻条目]
依赖项:
- requests, beautifulsoup4
"""
# 要求:requests, beautifulsoup4
import json
from typing import Any
from dataclasses import dataclass, asdict
from datetime import datetime
@dataclass
class NewsItem:
title: str
date: str
source: str
url: str
summary: str
@dataclass
class CompanyProfile:
name: str
domain: str
industry: str
size: str
location: str
founded: str
funding: str
tech_stack: list[str]
recent_news: list[dict]
competitors: list[str]
description: str
def search_company_info(company_name: str, domain: str = None) -> dict:
"""
搜索公司基本信息。
在生产环境中,将调用 Clearbit、Crunchbase 等 API。
"""
# TODO: 实现实际的 API 调用
# 占位符返回结构
return {
"name": company_name,
"domain": domain or f"{company_name.lower().replace(' ', '')}.com",
"industry": "Technology", # 将来自 API
"size": "Unknown",
"location": "Unknown",
"founded": "Unknown",
"description": f"Information about {company_name}"
}
def search_funding_info(company_name: str) -> dict:
"""
搜索融资信息。
在生产环境中,将调用 Crunchbase、PitchBook 等。
"""
# TODO: 实现实际的 API 调用
return {
"total_funding": "Unknown",
"last_round": "Unknown",
"last_round_date": "Unknown",
"investors": []
}
def search_tech_stack(domain: str) -> list[str]:
"""
检测技术栈。
在生产环境中,将调用 BuiltWith、Wappalyzer 等。
"""
# TODO: 实现实际的 API 调用
return []
def search_recent_news(company_name: str, days: int = 90) -> list[dict]:
"""
搜索公司近期新闻。
在生产环境中,将调用新闻 API。
"""
# TODO: 实现实际的 API 调用
return []
def main(
company_name: str,
domain: str = None
) -> dict[str, Any]:
"""
从多个来源聚合公司数据。
参数:
company_name: 要研究的公司名称
domain: 公司域名(可选,将被推断)
返回:
包含行业、规模、融资、技术栈、新闻的公司画像字典
"""
# 获取公司基本信息
basic_info = search_company_info(company_name, domain)
# 获取融资信息
funding_info = search_funding_info(company_name)
# 检测技术栈
company_domain = basic_info.get("domain", domain)
tech_stack = search_tech_stack(company_domain) if company_domain else []
# 获取近期新闻
news = search_recent_news(company_name)
# 汇总公司画像
profile = CompanyProfile(
name=basic_info["name"],
domain=basic_info["domain"],
industry=basic_info["industry"],
size=basic_info["size"],
location=basic_info["location"],
founded=basic_info["founded"],
funding=funding_info.get("total_funding", "Unknown"),
tech_stack=tech_stack,
recent_news=news,
competitors=[], # 将从行业分析中丰富
description=basic_info["description"]
)
return {
"profile": asdict(profile),
"funding_details": funding_info,
"enriched_at": datetime.now().isoformat(),
"sources_checked": ["company_info", "funding", "tech_stack", "news"]
}
if __name__ == "__main__":
import sys
# 示例用法
result = main(
company_name="DataFlow Systems",
domain="dataflow.io"
)
print(json.dumps(result, indent=2))
FILE:linkedin-parser.py
#!/usr/bin/env python3
"""
linkedin-parser.py - 结构化 LinkedIn 个人资料数据
输入:
- profile_url: 字符串
- 或 name + company: 字符串
输出:
- contact:
name: 字符串
title: 字符串
tenure: 字符串
previous_roles: [角色对象]
mutual_connections: [字符串]
recent_activity: [帖子摘要]
依赖项:
- requests
"""
# 要求:requests
import json
from typing import Any
from dataclasses import dataclass, asdict
from datetime import datetime
@dataclass
class PreviousRole:
title: str
company: str
duration: str
description: str
@dataclass
class RecentPost:
date: str
content_preview: str
engagement: int
topic: str
@dataclass
class ContactProfile:
name: str
title: str
company: str
location: str
tenure: str
previous_roles: list[dict]
education: list[str]
mutual_connections: list[str]
recent_activity: list[dict]
profile_url: str
headline: str
def search_linkedin_profile(name: str = None, company: str = None, profile_url: str = None) -> dict:
"""
搜索 LinkedIn 个人资料信息。
在生产环境中,将使用 LinkedIn API 或 Sales Navigator。
"""
# TODO: 实现实际的 LinkedIn API 集成
# 注意:LinkedIn 的 API 有严格的服务条款
return {
"found": False,
"name": name or "Unknown",
"title": "Unknown",
"company": company or "Unknown",
"location": "Unknown",
"headline": "",
"tenure": "Unknown",
"profile_url": profile_url or ""
}
def get_career_history(profile_data: dict) -> list[dict]:
"""
从个人资料中提取职业历史。
"""
# TODO: 实现职业经历提取
return []
def get_mutual_connections(profile_data: dict, user_network: list = None) -> list[str]:
"""
查找共同联系人。
"""
# TODO: 实现共同联系人检测
return []
def get_recent_activity(profile_data: dict, days: int = 30) -> list[dict]:
"""
获取最近的帖子和活动。
"""
# TODO: 实现活动提取
return []
def main(
name: str = None,
company: str = None,
profile_url: str = None
) -> dict[str, Any]:
"""
为销售准备结构化 LinkedIn 个人资料数据。
参数:
name: 人员姓名
company: 他们就职的公司
profile_url: 直接的 LinkedIn 个人资料 URL
返回:
包含结构化联系人资料的字典
"""
if not profile_url and not (name and company):
return {"error": "请提供 profile_url 或 name + company"}
# 搜索个人资料
profile_data = search_linkedin_profile(
name=name,
company=company,
profile_url=profile_url
)
if not profile_data.get("found"):
return {
"found": False,
"name": name or "Unknown",
"company": company or "Unknown",
"message": "未找到个人资料或访问受限",
"suggestions": [
"尝试直接在 LinkedIn 上搜索",
"检查是否有其他拼写方式",
"确认此人是否仍在该公司工作"
]
}
# 获取职业历史
previous_roles = get_career_history(profile_data)
# 查找共同联系人
mutual_connections = get_mutual_connections(profile_data)
# 获取最近活动
recent_activity = get_recent_activity(profile_data)
# 汇总联系人资料
contact = ContactProfile(
name=profile_data["name"],
title=profile_data["title"],
company=profile_data["company"],
location=profile_data["location"],
tenure=profile_data["tenure"],
previous_roles=previous_roles,
education=[], # 将从个人资料中提取
mutual_connections=mutual_connections,
recent_activity=recent_activity,
profile_url=profile_data["profile_url"],
headline=profile_data["headline"]
)
return {
"found": True,
"contact": asdict(contact),
"research_date": datetime.now().isoformat(),
"data_completeness": calculate_completeness(contact)
}
def calculate_completeness(contact: ContactProfile) -> dict:
"""计算个人资料数据的完整程度。"""
fields = {
"basic_info": bool(contact.name and contact.title and contact.company),
"career_history": len(contact.previous_roles) > 0,
"mutual_connections": len(contact.mutual_connections) > 0,
"recent_activity": len(contact.recent_activity) > 0,
"education": len(contact.education) > 0
}
complete_count = sum(fields.values())
return {
"fields": fields,
"score": f"{complete_count}/{len(fields)}",
"percentage": int((complete_count / len(fields)) * 100)
}
if __name__ == "__main__":
import sys
# 示例用法
result = main(
name="Sarah Chen",
company="DataFlow Systems"
)
print(json.dumps(result, indent=2))
FILE:priority-scorer.py
#!/usr/bin/env python3
"""
priority-scorer.py - 计算并排序潜在客户优先级
输入:
- prospects: [包含信号的潜在客户对象]
- weights: {deal_size, timing, warmth, signals}
输出:
- ranked: [包含分数和推理的潜在客户]
依赖:
- (无 - 纯 Python)
"""
import json
from typing import Any
from dataclasses import dataclass
# 默认评分权重
DEFAULT_WEIGHTS = {
"deal_size": 0.25,
"timing": 0.30,
"warmth": 0.20,
"signals": 0.25
}
# 信号评分映射
SIGNAL_SCORES = {
# 高意向信号
"recent_funding": 10,
"leadership_change": 8,
"job_postings_relevant": 9,
"expansion_news": 7,
"competitor_mention": 6,
# 中等意向信号
"general_hiring": 4,
"industry_event": 3,
"content_engagement": 3,
# 关系信号
"mutual_connection": 5,
"previous_contact": 6,
"referred_lead": 8,
# 负面信号
"recent_layoffs": -3,
"budget_freeze_mentioned": -5,
"competitor_selected": -7,
}
@dataclass
class ScoredProspect:
company: str
contact: str
call_time: str
raw_score: float
normalized_score: int
priority_rank: int
score_breakdown: dict
reasoning: str
is_followup: bool
def score_deal_size(prospect: dict) -> tuple[float, str]:
"""基于预估交易规模进行评分。"""
size_indicators = prospect.get("size_indicators", {})
employee_count = size_indicators.get("employees", 0)
revenue_estimate = size_indicators.get("revenue", 0)
# 基于公司规模的简单评分
if employee_count > 1000 or revenue_estimate > 100_000_000:
return 10.0, "Enterprise-scale opportunity"
elif employee_count > 200 or revenue_estimate > 20_000_000:
return 7.0, "Mid-market opportunity"
elif employee_count > 50:
return 5.0, "SMB opportunity"
else:
return 3.0, "Small business"
def score_timing(prospect: dict) -> tuple[float, str]:
"""基于时间信号进行评分。"""
timing_signals = prospect.get("timing_signals", [])
score = 5.0 # 基础分
reasons = []
for signal in timing_signals:
if signal == "budget_cycle_q4":
score += 3
reasons.append("Q4 budget planning")
elif signal == "contract_expiring":
score += 4
reasons.append("Contract expiring soon")
elif signal == "active_evaluation":
score += 5
reasons.append("Actively evaluating")
elif signal == "just_funded":
score += 3
reasons.append("Recently funded")
return min(score, 10.0), "; ".join(reasons) if reasons else "Standard timing"
def score_warmth(prospect: dict) -> tuple[float, str]:
"""基于关系亲密度进行评分。"""
relationship = prospect.get("relationship", {})
if relationship.get("is_followup"):
last_outcome = relationship.get("last_outcome", "neutral")
if last_outcome == "positive":
return 9.0, "Warm follow-up (positive last contact)"
elif last_outcome == "neutral":
return 7.0, "Follow-up (neutral last contact)"
else:
return 5.0, "Follow-up (needs re-engagement)"
if relationship.get("referred"):
return 8.0, "Referred lead"
if relationship.get("mutual_connections", 0) > 0:
return 6.0, f"{relationship['mutual_connections']} mutual connections"
if relationship.get("inbound"):
return 7.0, "Inbound interest"
return 4.0, "Cold outreach"
def score_signals(prospect: dict) -> tuple[float, str]:
"""基于检测到的购买信号进行评分。"""
signals = prospect.get("signals", [])
total_score = 0
signal_reasons = []
for signal in signals:
signal_score = SIGNAL_SCORES.get(signal, 0)
total_score += signal_score
if signal_score > 0:
signal_reasons.append(signal.replace("_", " "))
# 归一化到 0-10 分数
normalized = min(max(total_score / 2, 0), 10)
reason = f"信号:{', '.join(signal_reasons)}" if signal_reasons else "无强信号"
return normalized, reason
def calculate_priority_score(
prospect: dict,
weights: dict = None
) -> ScoredProspect:
"""计算潜在客户的总体优先级分数。"""
weights = weights or DEFAULT_WEIGHTS
# 计算各组件分数
deal_score, deal_reason = score_deal_size(prospect)
timing_score, timing_reason = score_timing(prospect)
warmth_score, warmth_reason = score_warmth(prospect)
signal_score, signal_reason = score_signals(prospect)
# 加权总分
raw_score = (
deal_score * weights["deal_size"] +
timing_score * weights["timing"] +
warmth_score * weights["warmth"] +
signal_score * weights["signals"]
)
# 汇总理由
reasons = []
if timing_score >= 8:
reasons.append(timing_reason)
if signal_score >= 7:
reasons.append(signal_reason)
if warmth_score >= 7:
reasons.append(warmth_reason)
if deal_score >= 8:
reasons.append(deal_reason)
return ScoredProspect(
company=prospect.get("company", "Unknown"),
contact=prospect.get("contact", "Unknown"),
call_time=prospect.get("call_time", "Unknown"),
raw_score=round(raw_score, 2),
normalized_score=int(raw_score * 10),
priority_rank=0, # 排序后设置
score_breakdown={
"deal_size": {"score": deal_score, "reason": deal_reason},
"timing": {"score": timing_score, "reason": timing_reason},
"warmth": {"score": warmth_score, "reason": warmth_reason},
"signals": {"score": signal_score, "reason": signal_reason}
},
reasoning="; ".join(reasons) if reasons else "标准优先级",
is_followup=prospect.get("relationship", {}).get("is_followup", False)
)
def main(
prospects: list[dict],
weights: dict = None
) -> dict[str, Any]:
"""
计算并排序潜在客户的优先级。
参数:
prospects: 包含信号的潜在客户对象列表
weights: 可选的评分组件自定义权重
返回:
包含排序后潜在客户和评分详情的字典
"""
weights = weights or DEFAULT_WEIGHTS
# 对所有潜在客户评分
scored = [calculate_priority_score(p, weights) for p in prospects]
# 按原始分数降序排序
scored.sort(key=lambda x: x.raw_score, reverse=True)
# 分配排名
for i, prospect in enumerate(scored, 1):
prospect.priority_rank = i
# 转换为字典以便 JSON 序列化
ranked = []
for s in scored:
ranked.append({
"company": s.company,
"contact": s.contact,
"call_time": s.call_time,
"priority_rank": s.priority_rank,
"score": s.normalized_score,
"reasoning": s.reasoning,
"is_followup": s.is_followup,
"breakdown": s.score_breakdown
})
return {
"ranked": ranked,
"weights_used": weights,
"total_prospects": len(prospects)
}
if __name__ == "__main__":
import sys
# 示例用法
example_prospects = [
{
"company": "DataFlow Systems",
"contact": "Sarah Chen",
"call_time": "2pm",
"size_indicators": {"employees": 200, "revenue": 25_000_000},
"timing_signals": ["just_funded", "active_evaluation"],
"signals": ["recent_funding", "job_postings_relevant"],
"relationship": {"is_followup": False, "mutual_connections": 2}
},
{
"company": "Acme Manufacturing",
"contact": "Tom Bradley",
"call_time": "10am",
"size_indicators": {"employees": 500},
"timing_signals": ["contract_expiring"],
"signals": [],
"relationship": {"is_followup": True, "last_outcome": "neutral"}
},
{
"company": "FirstRate Financial",
"contact": "Linda Thompson",
"call_time": "4pm",
"size_indicators": {"employees": 300},
"timing_signals": [],
"signals": [],
"relationship": {"is_followup": False}
}
]
result = main(prospects=example_prospects)
print(json.dumps(result, indent=2))
## 高意向信号
### 职位发布
- **发布 3 个以上相关职位** = 正在推进主动举措,已有预算分配
- **在你的领域招聘高级职位** = 战略重点
- **紧急语言(“ASAP”、“立即”)** = 痛点紧迫
- **提及特定工具** = 对竞品或品类有认知
### 财务事件
- **B 轮及以上融资** = 拥有增长资金,购买力强
- **准备上市(IPO)** = 需要运营成熟度
- **宣布收购** = 即将面临整合挑战
- **营收里程碑新闻稿** = 有可用预算
### 领导层变动
- **你的领域内新任 CXO** = 正处于 90 天优先事项设定期
- **新任 CRO/CMO** = 很可能正在评估技术栈
- **创始人转任 CEO** = 正在推动运营专业化
## 中等意向信号
### 扩张信号
- **开设新办公室** = 存在基础设施需求
- **国际化扩张** = 本地化与合规需求
- **新产品发布** = 面临扩展挑战
- **赢得重要客户** = 交付压力增大
### 技术信号
- **发布 RFP** = 正处于活跃采购流程
- **提及供应商评审** = 正在比价选型
- **技术栈变更** = 存在集成机会
- **对遗留系统抱怨** = 有现代化需求
### 内容信号
- **发布与你主题相关的博客文章** = 正在自我教育
- **参加网络研讨会** = 兴趣已确认
- **下载白皮书** = 已意识到问题
- **在会议上发言** = 追求思想领导力与曝光度
## 低意向信号(培育中)
### 一般性活动
- **参加行业活动** = 市场参与者
- **常规招聘** = 公司在增长
- **正面新闻报道** = 公司健康
- **社交媒体活跃** = 领导层积极参与
## 信号评分
| 信号类型 | 分数 | 行动 |
|-------------|-------|--------|
| 职位发布(相关) | +3 | 优先触达 |
| 近期融资 | +3 | 在对话中引用 |
| 领导层变动 | +2 | 时效性机会 |
| 扩张新闻 | +2 | 从增长角度切入 |
| 负面评价 | +2 | 从痛点角度切入 |
| 内容参与 | +1 | 纳入培育流程 |
| 无信号 | 0 | 聚焦探索发现 |可替换内容
- [字符串]
- [新闻条目]
- [str]
- [dict]
- [str, Any]
- ["name"]
- ["domain"]
- ["industry"]
- ["size"]
- ["location"]
- ["founded"]
- ["description"]
- [角色对象]
- [帖子摘要]
- ["title"]
- ["company"]
- ["tenure"]
- ["profile_url"]
- ["headline"]
- [包含信号的潜在客户对象]
- [包含分数和推理的潜在客户]
- [float, str]
- ['mutual_connections']
- ["deal_size"]
- ["timing"]
- ["warmth"]
- ["signals"]
- ["just_funded", "active_evaluation"]
- ["contract_expiring"]
分类与标签
商业营销、销售线索、公司研究、联系人画像、购买信号、客户排序