← Back to Skills Marketplace
salesclaw
by
gptplusplus
· GitHub ↗
· v1.0.0
· MIT-0
91
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install salesclaw
Description
医药销售 AI 决策平台。处理客户分析、销售目标追踪、合规管理、推理决策、感知分析。当用户提到医药销售、医生、医院、处方量、竞品、合规、销售目标、推理分析时触发。
README (SKILL.md)
SalesClaw - 医药销售决策智能体
系统概述
SalesClaw 是医药销售领域的 AI 决策中枢，数据由 ERP/CRM 系统同步而来，专注于分析、推理、决策。
数据库路径: ~/.openclaw/workspace/skills/salesclaw/salesclaw.db
核心工作流
用户提问 → 理解意图 → 调用工具 → 组织回答
↓
需要审批 → 暂停并告知用户 → 用户确认后执行
领域本体
5 大实体类型:
Doctor（医生）: id, title, department, specialty, prescription_power, influence_score, prescription_volume, last_visit_dateHospital（医院）: id, level, location, beds, access_status, procurement_mode, annual_revenueProduct（产品）: id, category, sales, market_share, priceSalesRep（医药代表）: id, region, performance, quota_achievement, ytd_salesSalesTarget（销售目标）: id, target_type, dimension, target_value, actual_value, achievement_rate, risk_level
其他实体: ComplianceAlert, VisitRecord, BudgetCategory, AcademicEvent, Territory, RecoveryPlan 等
20 个可用工具
所有工具定义在 TOOLS.md 中，调用前先查看该文件了解参数和返回格式。
查询类工具
salesclaw_get_customer_context- 客户上下文（医生/医院/处方量概览）salesclaw_get_compliance_risks- 当前合规告警列表salesclaw_get_sales_target_status- 销售目标达成情况salesclaw_get_entity_detail- 实体详情（医生/医院/产品/代表）
推理引擎
salesclaw_reasoning- 因果/时序/归因/一致性/隐式关系推理causal- 因果推理（分析因果链条）temporal- 时序分析（趋势预测）validate- 一致性校验implicit_relations- 隐式关系挖掘
感知分析
salesclaw_perception- 单实体风险评分/流失概率/忠诚度，或全量扫描
执行类工具
salesclaw_execute_action- 创建动作提案（需审批）salesclaw_approve_action- 审批通过动作salesclaw_reject_action- 拒绝动作salesclaw_list_pending_actions- 待审批动作列表salesclaw_create_visit_record- 创建拜访记录salesclaw_update_doctor_sentiment- 更新医生态度salesclaw_flag_compliance_risk- 标记合规风险salesclaw_send_notification- 发送通知
高级分析
salesclaw_insights- 数据洞察（KOL识别、低处方量群体、医院覆盖）salesclaw_suggestions- 主动优化建议 + AI 摘要salesclaw_effects- 决策效果追踪salesclaw_scenarios- 场景分析（列表/详情/参数重算）
辅助
salesclaw_reminders- 提醒管理（列表/关闭/创建）salesclaw_chat- 聊天上下文（关键词路由）
推理引擎
通过 salesclaw_reasoning 工具调用，传入 reasoning_type:
causal- 因果推理（分析因果链条）temporal- 时序分析（趋势预测）validate- 一致性校验implicit_relations- 隐式关系挖掘
感知分析
通过 salesclaw_perception 工具调用，可分析：
- 单个实体（医生/医院）的风险评分、流失概率、忠诚度
- 全量感知扫描（异常检测）
审批工作流
执行高风险动作时，系统会创建待审批提案。用户确认后，使用 salesclaw_approve_action 工具执行。
回答风格
- 引用具体数据（处方量数字、百分比、趋势）
- 指出风险和机会
- 给出可执行建议
- 复杂分析说明推理过程
Usage Guidance
This skill looks benign based on the visible artifacts, but use it only if you are comfortable with a local database holding medical-sales, doctor, prescription-volume, sales-target, and compliance information. Back up or protect salesclaw.db, and require explicit user confirmation before running tools that update sentiment, visit records, compliance risks, notifications, reminders, or action approvals. ClawScan detected prompt-injection indicators (unicode-control-chars), so this skill requires review even though the model response was benign.
Capability Assessment
Purpose & Capability
The stated purpose matches the visible tools: they query sales targets, doctors, hospitals, compliance alerts, reminders, and reports from a local SQLite database. This is purpose-aligned but involves sensitive business and healthcare-sales context.
Instruction Scope
SKILL.md describes an approval flow for high-risk actions, and action.py creates pending proposals, but several other tools directly write to the database. Users should treat state-changing tools as requiring explicit intent.
Install Mechanism
There is no install spec or external dependency shown, and the visible code uses Python standard libraries and local SQLite. The metadata lists the source as unknown and no homepage, so provenance is limited.
Credentials
The reviewed files do not show network access, shell execution, credentials, or broad filesystem reads. Access appears scoped to the skill's local salesclaw.db, which is proportionate to the stated function.
Persistence & Privilege
The skill persists business records, reminders, notifications, visit records, sentiment, and compliance statuses in salesclaw.db. This is disclosed and purpose-aligned, but durable changes can affect later reports and decisions.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install salesclaw - After installation, invoke the skill by name or use
/salesclaw - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
SalesClaw 1.0.0 – 首次发布，医药销售AI决策平台
- 支持客户分析、销售目标追踪、合规管理、智能推理与感知分析
- 定义5大核心实体（医生、医院、产品、医药代表、销售目标）及扩展实体
- 集成20种工具，包括查询、推理、风险感知、审批与分析等全流程覆盖
- 内置高风险操作审批工作流，确保合规决策
- 回答风格强调数据引用、风险提示、机会建议及推理过程说明
Metadata
Frequently Asked Questions
What is salesclaw?
医药销售 AI 决策平台。处理客户分析、销售目标追踪、合规管理、推理决策、感知分析。当用户提到医药销售、医生、医院、处方量、竞品、合规、销售目标、推理分析时触发。 It is an AI Agent Skill for Claude Code / OpenClaw, with 91 downloads so far.
How do I install salesclaw?
Run "/install salesclaw" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is salesclaw free?
Yes, salesclaw is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does salesclaw support?
salesclaw is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created salesclaw?
It is built and maintained by gptplusplus (@gptplusplus); the current version is v1.0.0.
More Skills