Visit Analyzer is a private-domain B2B sales assistant that processes chat logs and call recordings to generate structured project portraits and H5 analytics dashboards.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install visit-analyzer
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install visit-analyzer using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Visit Analyzer?
The Visit Analyzer is a sophisticated sales intelligence tool developed as a part of Openclaw Skills to help B2B organizations manage and evaluate private-domain client interactions. By interpreting conversational intent, retrieving transcripts from phone call records, or scraping daily WeChat notification flows, this engine automatically generates comprehensive portraits of ongoing sales projects. It maps raw communication data into the standard Lead to Cash (LTC) pipeline to assess progress, define upcoming follow-up tasks, identify potential threats, and capture commitments made by both the sales representative and the client.
Designed for ultimate workflow efficiency, the skill operates completely in the background without outputting distracting intermediate statuses. Instead, it provides a direct H5 interactive link with visual charts showing current sales progress and actionable strategy sheets. By deploying the Visit Analyzer within Openclaw Skills, sales teams secure robust data isolation policies where information is strictly locked to individual employees and projects, minimizing data leaks while maximizing productivity.
Visit Analyzer Use Cases
- Automatically tracking B2B pipelines and current LTC sales stages based on natural client-representative conversations.
- Synthesizing unstructured daily WeChat notifications and scattered call recordings into cohesive chronological records.
- Extracting client commitments, delivery requests, and pricing negotiations without requiring manual sales notes.
- Running automated risk assessments on high-value corporate negotiations to flag early warning signs of deal loss or competitor interference.
How Visit Analyzer Works
- Silent Session Handling: Upon activation, the skill executes a multi-layer verification strategy to check and automatically renew the employee's authorization token cached locally inside
.token-cache.jsonusing python3 modules. - Semantic Intent Extraction: Interprets natural commands like 'Analyze my chat history with company X' to extract keywords, target client contacts, project labels, and preferred channels (audio recordings vs WeChat).
- Customer Resolution & Validation: References the backend client database to locate matches; if naming conflicts arise, it serves an interactive choice menu to prevent database clutter.
- Layered Content Filtering: Implements a zero-overhead, 4-tier filtering hierarchy (checking age scope, title patterns, and small-batch file scanning) to fetch target text without stressing server I/O.
- Sales Intel Compilation: Passes compiled dialogue aggregates to a B2B sales analyzer that structures text into 5 distinct vectors: sales stages, strategy actions, client intent, promises, and level risk matrices.
- Secure Database Ingestion: Submits structured JSON payloads securely to the server with data row isolation locked down by the combination of
employee_code,company_name, andproject_name. - Visualization Delivery: requests a temporary exchange code from the server and outputs a clean Markdown summary along with a secure, interactive H5 URL.
Visit Analyzer Setup
Prerequisites
Make sure your environment has curl, jq, and python3 installed before executing this skill inside the workspace.
Authentication Configuration
The skill relies on a localized authentication cache. It will prompt for your employee credentials on first use and handle future session renewals silently.
# Initial Setup Directory
mkdir -p ~/.openclaw/workspace/scripts
# Fast API Base URL definition used internally
FASTAPI_BASE_URL="http://47.116.49.218:8000/api/v1"
Date Utilities Support
Because macOS does not support standard date -d and date -Iseconds syntax, cross-platform calculations utilize internal Python execution lines:
# ISO Timestamp Generator
iso_now() { python3 -c "from datetime import datetime, timezone; print(datetime.now(timezone.utc).isoformat())"; }
Visit Analyzer Data Schema & Taxonomy
Database Schema Reference
This schema lists the standard relational schema maintained automatically by backend ingestion endpoints once Visit Analyzer submits analytical data.
| Field Name | Data Type | Key Type | Description |
|---|---|---|---|
id |
INTEGER | PRIMARY KEY | Unique Project Portrait record identifier. |
employee_code |
VARCHAR | INDEX | Employee identifier used as a partition boundary. |
company_name |
VARCHAR | INDEX | Standardized corporate client name. |
project_name |
VARCHAR | INDEX | Project identifier; defaults to company name if empty. |
contact_name |
VARCHAR | - | Client representative name. |
transcript_file_path |
VARCHAR | - | Absolute path to call transcription or virtual WeChat URI. |
visit_date |
VARCHAR | - | Raw chronological date of the interaction (YYYY-MM-DD). |
data_source |
VARCHAR | - | Records source origin (e.g., WeChat, Phone Recording). |
sales_stage |
JSON TEXT | - | Structured LTC pipeline milestones and percentage. |
follow_up_strategies |
JSON TEXT | - | Extracted target tasks, icons, and categories. |
customer_insights |
JSON TEXT | - | Summarized client demands and requests. |
commitments |
JSON TEXT | - | Tracked corporate and client promises. |
risk_assessment |
JSON TEXT | - | Identified transaction threats categorized by severity. |
raw_analysis |
TEXT | - | Original unparsed output returned from LLM. |
visit_summary |
TEXT | - | Under-100-character snapshot for easy viewing. |
created_at |
DATETIME | - | Generation timestamp. |
updated_at |
DATETIME | - | Last modification timestamp. |
Visit Analyzer Advanced Features
- Incremental Channel Merging: Allows seamless, incremental aggregation of phone call logs and WeChat chat logs under the same project record.
- Zero-Footprint Execution: Operates completely in the background without generating intermediate console outputs or unnecessary text blocks.
- Strict Row-Level Security: Isolates customer datasets securely based on unique employee-project key pairs, preventing cross-tenant visibility.
- Optimized Directory Scanning: Prevents CPU spikes and slow read execution times by abandoning raw disk-wide searches in favor of an optimized, time-based 4-stage filtering mechanism.
- H5 Authorization Exchange Code: Swaps long-lived session secrets for short-lived token strings during dashboard navigation to protect critical client CRM databases.
SKILL.md
Loading
Related Openclaw Skills
Super Mario Innovation & Brand Strategy Skill
An AI-powered business and design coach based on the story of Nintendo's rise to global dominance, helping you build resilient brands and simple, elegant products.
Auto-Grading and Multi-Document Review Skill
An automated document review and grading agent designed for comprehensive, multi-dimensional academic thesis verification and cross-document validation.
Dochost Publish
A powerful skill that allows AI agents to instantly publish Markdown or HTML content into live, shareable dochost.io web pages.
Jianwei Strategic Double-Engine Insight System
Jianwei is a sophisticated strategic analysis skill powered by a double-engine architecture that generates, validates, and audits business hypotheses through rigorous frameworks.
ArchUnit Architecture Guard
Protect your Java and Kotlin project structures from architectural drift and erosion with the ArchUnit Architecture Guard from Openclaw Skills.
Job Search — Serbia & Remote (job-search-belgrade)
An intelligent AI coding agent skill that scrapes regional and remote job boards, cross-references findings against your PDF resume, and outputs sorted listings with fit scores directly in your terminal or via SMTP email digests.
Featured*
