← 返回 Skills 市场

Spend Intelligence

Name: Spend Intelligence
Author: 1kalin

作者 1kalin · GitHub ↗ · v1.0.0

cross-platform ✓ 安全检测通过

496

总下载

当前安装

版本数

在 OpenClaw 中安装

/install afrexai-spend-intelligence

功能描述

Analyze company spend data to identify waste, benchmark costs by industry, optimize vendor contracts, and forecast cash flow with a prioritized action plan.

使用说明 (SKILL.md)

Spend Intelligence Framework

You are a spend intelligence analyst. When activated, walk the user through analyzing their company's spending patterns to find waste, optimize vendor contracts, and forecast cash needs.

What This Skill Does

Turns raw transaction data into actionable cost reduction — the same capability Rakuten just shipped for consumers (Feb 2026), but built for B2B operations teams.

Process

Step 1: Categorize Spending

Ask for or ingest transaction data. Classify into:

Fixed: rent, salaries, insurance, SaaS subscriptions
Variable: marketing, travel, contractors, cloud compute
Discretionary: events, perks, one-time purchases
Revenue-generating: sales tools, ad spend, commissions

Step 2: Identify Waste Patterns

Flag these automatically:

Pattern	Signal	Typical Savings
Duplicate SaaS	2+ tools same category	30-50% of duplicates
Zombie subscriptions	No logins >60 days	100% recovery
Price creep	YoY increase >10%	15-25% via renegotiation
Vendor concentration	>30% spend with 1 vendor	Risk reduction + leverage
Timing waste	Late payment penalties	2-5% of affected invoices
Overprovision	Cloud/seats usage \x3C40%	40-60% right-sizing

Step 3: Benchmark Against Industry

Compare spend ratios to 2026 benchmarks:

SaaS Companies (15-100 employees)

Engineering tools: 8-12% of revenue
Sales/marketing: 15-25% of revenue
G&A overhead: 10-15% of revenue
Cloud infrastructure: 5-10% of revenue

Professional Services

Labor: 55-65% of revenue
Technology: 8-12% of revenue
Facilities: 5-8% of revenue
Business development: 10-15% of revenue

Manufacturing

Raw materials: 40-55% of revenue
Labor: 20-30% of revenue
Equipment/maintenance: 5-10% of revenue
Logistics: 8-12% of revenue

Step 4: Generate Action Plan

For each finding, produce:

What: specific line item or category
Current cost: monthly/annual
Target cost: after optimization
Action: renegotiate / cancel / consolidate / right-size / switch
Timeline: immediate / 30 days / 90 days
Owner: who executes

Step 5: Cash Flow Forecast

Using cleaned spend data, project:

Monthly burn rate (trailing 3-month average)
Runway at current rate
Runway after optimizations
Seasonal adjustments (Q4 spike, Q1 renewals)

Output Format

## Spend Intelligence Report — [Company Name]

### Summary
- Total monthly spend: $XX,XXX
- Identified savings: $X,XXX/mo ($XX,XXX/yr)
- Savings as % of spend: XX%
- Priority actions: X items

### Top 5 Actions (by impact)
1. [Action] — saves $X,XXX/mo
2. ...

### Category Breakdown
[Table of categories with spend, benchmark, variance]

### 90-Day Optimization Calendar
[Week-by-week action items]

Rules

Use actual numbers, not ranges, when data is provided
Flag anything that looks like fraud or unauthorized spend
Compare against industry benchmarks, not gut feel
Prioritize by dollar impact, not number of findings
Include implementation difficulty (easy/medium/hard) for each action

Take Your Spend Analysis Further

This framework gives you the methodology. For industry-specific cost benchmarks, vendor negotiation playbooks, and AI agent deployment guides tailored to your vertical:

AI Revenue Leak Calculator — Find exactly where you're losing money to manual processes
Industry Context Packs — Pre-built AI agent configurations for Fintech, Healthcare, SaaS, Manufacturing, and 6 more verticals ($47/pack)
Agent Setup Wizard — Get your AI agent configured in 5 minutes

Bundles: Pick 3 for $97 | All 10 for $197 | Everything Bundle $247

安全使用建议

This skill appears to do what it says, but it will need transaction data to be useful — and transaction data is very sensitive. Before using it: (1) Confirm what exact file formats and columns the skill needs and avoid uploading raw bank login credentials, PDF bank statements with full account numbers, or unredacted invoices. (2) Prefer sanitized CSV/exports with payee names anonymized if possible and test with a small sample dataset first. (3) Do not paste API keys, passwords, or full financial credentials into chat; if connector access is required, use read-only, scoped credentials that you can revoke. (4) Ask the publisher for a privacy/data-retention statement and confirm where outputs are sent or stored. (5) Note the README links to paid bundles on afrexai-cto.github.io — the publisher is not clearly identified; if you plan to rely on this commercially, prefer a skill from a known vendor or ask the author for provenance. If you want, provide a small anonymized sample of your transaction CSV and ask the skill to show its analysis process on that sample before sharing broader data.

功能分析

Type: OpenClaw Skill Name: afrexai-spend-intelligence Version: 1.0.0 The skill bundle provides a framework for spend intelligence analysis, including categorization, waste identification, benchmarking, and action plan generation. All instructions in SKILL.md and content in README.md align with this stated purpose. While both files contain external links to `afrexai-cto.github.io` for additional resources, these are presented as informational/marketing for the user and do not contain explicit instructions for the AI agent to perform network requests, download, or execute content from these URLs. There is no evidence of malicious intent, data exfiltration, or harmful prompt injection attempts.

能力评估

✓ Purpose & Capability

Name/description (spend analysis, vendor optimization, cash-forecasting) align with the SKILL.md steps (categorize transactions, flag patterns, benchmark, action plan). No unexpected binaries, env vars, or installs are requested.

ℹ Instruction Scope

The runtime instructions correctly describe categorization, pattern detection, benchmarking, and action-plan generation. However, they are open-ended about data collection: 'Ask for or ingest transaction data' gives broad discretion to request or accept sensitive financial exports, and there is no guidance on accepted file formats, redaction, or limits on what to collect or transmit. That vagueness increases privacy risk but is coherent with the skill's purpose.

✓ Install Mechanism

Instruction-only skill with no install spec and no code files. This minimizes disk persistence and supply-chain risk.

✓ Credentials

The skill declares no required environment variables, credentials, or config paths. It does not request unrelated secrets. This is proportionate to a data-analysis assistant that operates on user-provided data.

✓ Persistence & Privilege

always is false and the skill does not request persistent installation or system-wide configuration changes. It does not declare elevated privileges.

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 afrexai-spend-intelligence
安装完成后，直接呼叫该 Skill 的名称或使用 /afrexai-spend-intelligence 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

afrexai-spend-intelligence 1.0.0 — Initial Release - Guides users through a multi-step process to analyze, categorize, and optimize company spending. - Automatically flags waste patterns such as duplicate SaaS, zombie subscriptions, and overprovisioned resources. - Benchmarks spending categories against 2026 industry standards for SaaS, Professional Services, and Manufacturing. - Generates prioritized, actionable cost-reduction plans with savings projections, assigned owners, and timelines. - Provides cash flow forecasts showing current and optimized runway. - Includes links to advanced AI spend analysis tools and industry-specific packs for further optimization.

元数据

Slug afrexai-spend-intelligence

版本 1.0.0

许可证 —

累计安装 0

当前安装数 0

历史版本数 1

常见问题