← 返回 Skills 市场

Report Generator

Name: Report Generator
Author: fangwei-frank

作者 fangwei-frank · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ⚠ suspicious

114

总下载

当前安装

版本数

在 OpenClaw 中安装

/install frank-report-generator

功能描述

Automated sales and performance report generator for retail store managers. Generates daily, weekly, and monthly reports from POS/ERP data. Highlights anomal...

使用说明 (SKILL.md)

Report Generator

Overview

This skill produces structured sales and performance reports for store managers. Reports are data-first, anomaly-aware, and always include a recommended action.

Depends on: POS/ERP data connection configured in report_config (Step 05). If no data source is connected: return empty report with setup guidance.

Report Types

Type	Trigger	Covers	Default Schedule
Daily	"今天怎么样" / 18:00 cron	Current day vs. yesterday	Daily 18:00
Weekly	"本周报告" / Monday 09:00	Mon–Sun vs. prior week	Monday 09:00
Monthly	"月报" / 1st of month	Full month vs. prior month	1st @ 09:00
On-demand	Any data question	Specified time range	—

Report Structure

Every report follows this 5-section format:

Section 1: Headline Numbers

The top 3 KPIs the manager cares about most:

Total revenue (实际 vs 目标, percentage completion)
Transaction count
Average transaction value

Section 2: Product Performance

Top 5 best-selling SKUs (by revenue)
Any items with zero sales (flag if > 3 days)
Low stock warnings (pull from inventory data if available)

Section 3: Anomalies & Alerts

Auto-detect and flag:

Revenue > 20% above/below yesterday → flag
A category drops > 30% vs. prior period → flag
Escalation rate spike → flag
Unusual peak/valley in hourly distribution → note

Section 4: Staff Performance (if data available)

Transactions per staff member
Average ticket per staff
(Never names individuals negatively in customer-facing channels)

Section 5: Recommended Actions

1–3 specific, actionable items the manager should do today/this week. Examples: "补货SKU001（库存仅剩3件）", "关注女装区下午时段表现"

Data Source Integration

Pull data from configured sources in report_config:

Source	Data Retrieved
POS API	Transactions, revenue, returns by time period
ERP API	Inventory levels, restock status
Manual input	If no API: manager pastes today's numbers

If partial data: generate report with available data, mark missing sections clearly.

Reference: data-connectors.md

Delivery

After generating, deliver via configured channel:

report_config.delivery_channel (wecom / telegram / etc.)
report_config.recipients (manager IDs)

Format for channel:

WeCom: Use card format with emoji headers for scannability
Text channels: Markdown tables

On-Demand Queries

For ad-hoc questions like "上周卖得最好的是什么？":

Identify time range and metric from the question
Query data source
Use scripts/generate_report.py --period custom --start X --end Y --metric top_products
Present inline (no delivery to channel)

Reference: metric-definitions.md — standard metric formulas.

安全使用建议

Do not install blindly. Before using, ask the publisher for: (1) the missing data-connectors documentation and the actual scripts (scripts/generate_report.py) that the SKILL.md references; (2) a clear list of required credentials (POS/ERP API keys, WeCom/Telegram tokens) and guidance for storing them securely; (3) explanation of how scheduled delivery is implemented and who can change recipients. If those are not provided, treat the skill as non-functional and avoid giving it access to production credentials or sensitive data. Test in a sandbox with fake data and minimal delivery targets first.

功能分析

Type: OpenClaw Skill Name: frank-report-generator Version: 1.0.0 The skill bundle describes a standard automated sales and performance report generator for retail environments. The documentation (SKILL.md and metric-definitions.md) outlines legitimate business logic for processing POS/ERP data, calculating KPIs like revenue and return rates, and delivering reports via configured channels. There are no indicators of malicious intent, data exfiltration, or harmful prompt injection; the instructions are consistent with the stated purpose of assisting store managers.

能力评估

⚠ Purpose & Capability

The skill claims to pull POS/ERP data and deliver reports to channels (WeCom/Telegram). However, it declares no required environment variables, credentials, or config paths. A report generator legitimately needs connectors and auth for POS/ERP and delivery channels; those are not declared or provided.

⚠ Instruction Scope

SKILL.md instructs the agent to run scripts (e.g., scripts/generate_report.py --period ...) and references a data-connectors.md file, but neither the scripts nor data-connectors.md appear in the package. It also refers to a runtime `report_config` (sources, delivery_channel, recipients) without specifying how that config is created or secured. These gaps mean the instructions assume external files/configs that are not present and give the agent broad, unspecified discretion about data sources and recipients.

✓ Install Mechanism

Instruction-only skill with no install spec and no bundled code reduces supply-chain risk. Nothing is downloaded or executed from external URLs by the skill package itself.

⚠ Credentials

No environment variables or primary credential are declared, yet the skill requires access to POS/APIs and delivery channels which normally need API keys/tokens. The absence of declared secrets is disproportionate to the claimed functionality and leaves unclear where credentials must live and how they're protected.

✓ Persistence & Privilege

always is false and the skill does not request persistent system changes. It does mention scheduled automatic delivery, but provides no mechanism for establishing schedules or persistent agents; that scheduling behavior is ambiguous but not a declared privilege escalation.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install frank-report-generator
安装完成后，直接呼叫该 Skill 的名称或使用 /frank-report-generator 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

first release

元数据

Slug frank-report-generator

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题