AGENT SKILL

spend-analysis

Analyses procurement spend data to find savings. Activate for: spend analysis, spend analytics, analyse spend, procurement spend, category spend, spend across sites, spend consolidation, vendor consolidation, supplier consolidation, price consistency, price inconsistency, price benchmark, market benchmark, RFQ strategy, spend report, category management, tail spend, maverick spend, buying compliance, savings pipeline, identified savings, cost reduction, procurement ROI, spend by category, spend by vendor, spend by site, packaging spend, consolidation opportunity. USE THIS when the task involves analysing WHERE money is being spent, finding price inconsistencies across sites, identifying consolidation opportunities, or benchmarking prices against market rates. NOT for: invoice reconciliation (use invoice-reconciliation), vendor risk assessment (use supplier-risk), carrier performance (use logistics-brief).

License 许可
Apache-2.0
最近更新
2026-08-25
Stars
★ 0
Forks
0

01 前言 Front Matter

name
spend-analysis
license
Apache-2.0
metadata
{ "author": "Panaversity", "version": "1.0", "plugin-commands": "/spend-analysis", "mcp-integrations": "ERP, finance system, procurement system, web search" }
description
Analyses procurement spend data to find savings. Activate for: spend analysis, spend analytics, analyse spend, procurement spend, category spend, spend across sites, spend consolidation, vendor consolidation, supplier consolidation, price consistency, price inconsistency, price benchmark, market benchmark, RFQ strategy, spend report, category management, tail spend, maverick spend, buying compliance, savings pipeline, identified savings, cost reduction, procurement ROI, spend by category, spend by vendor, spend by site, packaging spend, consolidation opportunity. USE THIS when the task involves analysing WHERE money is being spent, finding price inconsistencies across sites, identifying consolidation opportunities, or benchmarking prices against market rates. NOT for: invoice reconciliation (use invoice-reconciliation), vendor risk assessment (use supplier-risk), carrier performance (use logistics-brief).

03 SKILL.md 正文

UNIVERSAL RULES (apply to every spend task)

  • NEVER accept a vendor risk assessment that contains fabricated financial data -- label all estimates and flag where primary data is unavailable
  • ALWAYS include specific recommended actions with deadlines in every output -- observations without actions are not acceptable

MANDATORY OUTPUT HEADER

TASK:          [e.g. Category Spend Overview -- Packaging -- FY2024]
CONFIGURATION: [Loaded: supply-chain.local.md / Not configured]
DATA SOURCES:  [ERP / Finance system / Web search]

SPEND ANALYSIS WORKFLOW

Three Strategic Questions Spend Analytics Answers

Question 1: WHO are we actually buying from? -> Vendor concentration analysis; consolidation opportunity identification

Question 2: WHAT are we paying? -> Price consistency across sites/BUs; contract compliance monitoring

Question 3: WHAT SHOULD we be paying? -> Market benchmarking; renegotiation trigger identification

Analysis Types

Type 1: Category Spend Overview

DATA FROM ERP (define period: typically last 12 months):

  • Total spend by category (top level and sub-category)
  • Spend by vendor within each category
  • Spend by business unit / site / cost centre
  • PO compliance: what % of spend had a PO before the invoice?

OUTPUT:

CATEGORY SPEND OVERVIEW -- [Period]
================================================================
TOTAL SPEND ANALYSED: [X]

TOP CATEGORIES BY SPEND:
[Category]: [X] | [N] vendors | [N] BUs buying | PO compliance: [X]%

TAIL SPEND ALERT:
[X]% of spend is with vendors who each represent <0.5% of total spend.
[N] vendors account for [X]% of total spend.
Opportunity: rationalise tail to reduce transaction cost and compliance burden.

PO COMPLIANCE ISSUES:
[X]% of invoices received without prior PO (by category and BU).
Non-compliant spend: [X] -- escalate to Finance and Procurement leadership.
================================================================

Type 2: Vendor Consolidation Analysis

TARGET: categories with >3 vendors where commodity characteristics suggest consolidation would deliver price advantage without unacceptable supply risk.

CONSOLIDATION CANDIDATE CRITERIA:

  • Multiple vendors supplying same specification / same category
  • No strategic reason for multiple sources (i.e. not deliberate dual-sourcing)
  • Combined volume would be meaningful to a single preferred vendor
  • Competitive market with multiple qualified alternatives

CONSOLIDATION OUTPUT (per candidate category):

CONSOLIDATION ANALYSIS: [Category]
---------------------------------------------------------
Current state:
  Vendors:       [N] active vendors
  Total spend:   [X]
  Price range:   [low] -- [high] per [unit] -- [X]% variance
  Price winner:  [Vendor at lowest price] at [X] per unit

Consolidated state:
  Target vendor(s): [1 or 2 preferred suppliers recommended]
  Combined volume:  [X]
  Target saving:    [X]% discount estimated at consolidated volume
  Annual saving:    [X] -- [X] (range based on discount range)

Risk assessment:
  Supply continuity: [Single source risk? Mitigation?]
  Switching effort:  [Qualification, trials, tooling -- estimate]

Recommendation: [PROCEED / PROCEED WITH DUAL-SOURCE / MONITOR]
---------------------------------------------------------

Type 3: Price Consistency Check

IDENTIFY: same item or specification being purchased at different prices by different business units or sites.

DETECT WHEN:

  • Same vendor code, same item code, different unit price
  • Same item description, different vendor, significantly different price
  • Same contract but different sites paying different prices

PRICE CONSISTENCY OUTPUT:

PRICE INCONSISTENCY REPORT -- [Category] -- [Period]
---------------------------------------------------------
Item:            [Description and specification]
Vendor:          [Vendor name]

Site/BU         Price paid    Volume    Annual spend
[Site A]        [X]           [N units] [X]
[Site B]        [Y]           [N units] [X]
[Site C]        [Z]           [N units] [X]

Price variance:  [X]% between highest and lowest
Best rate:       [X] (Site [X])
Saving if all aligned to best rate: [X]/year

Action: Issue group pricing directive; notify all sites of best rate;
require contract compliance from [date]
---------------------------------------------------------

Type 4: Market Benchmark

USE WEB SEARCH MCP to identify:

  • Published market price indices (commodity categories)
  • Trade association price surveys (sector-specific)
  • Publicly available tender results (public sector categories)
  • Analyst market reports (technology, energy, logistics)

BENCHMARK OUTPUT:

MARKET BENCHMARK: [Category/Item]
---------------------------------------------------------
Your current price:   [X] per [unit]
Market range:         [low] -- [high] per [unit]
Your position:        [X]% above / below market midpoint
Data source:          [Specify source and date -- never fabricate]
Data quality:         [HIGH -- published index / MEDIUM -- survey /
                       LOW -- estimate only]

IF ABOVE MARKET: Renegotiation recommended
  Estimated saving:   [X]% -- [X]/year at current volume
  Timing:             [Contract renewal date or next review]
  Leverage:           [Market evidence + volume commitment]
---------------------------------------------------------

Savings Pipeline Format

PROCUREMENT SAVINGS PIPELINE -- [Date]
================================================================
IDENTIFIED OPPORTUNITIES:
[Category]  [Type]          [Est. Saving]  [Status]  [Owner]  [Timeline]
[Category]  Consolidation   [X]            Draft     [Name]   Q[N] 20[XX]
[Category]  Price alignment [X]            Active    [Name]   [Month]

TOTAL PIPELINE: [X]
CAPTURED YTD:   [X]
REMAINING:      [X]
================================================================

NEVER DO THESE

  • NEVER fabricate market benchmark prices -- always cite source and date; if no reliable benchmark available, label as "no reliable benchmark found"
  • NEVER recommend single-sourcing a critical category without documenting the supply continuity risk and mitigation plan
  • NEVER report "savings" without defining the baseline clearly: savings vs. prior contract / vs. market / vs. budget -- specify
  • NEVER include tail spend vendors in consolidation analysis without checking whether they supply something unique or critical

ALL OUTPUTS REQUIRE REVIEW BY A QUALIFIED PROFESSIONAL BEFORE USE IN BUSINESS DECISIONS.

04 同仓库更多 Skills

JiayiV
JiayiV/question_mixing

webmcpify

Make a web app agent-ready — propose a WebMCP tool manifest, integrate, verify in a real browser, heal; unrelated code stays untouched. Use for "webmcpify", "add WebMCP", or "expose app actions to AI agents".

★ 0
JiayiV
JiayiV/question_mixing

vardoger-analyze

Use when the user asks to personalize the GitHub Copilot CLI assistant, adapt Copilot to their style, use vardoger, or analyze their Copilot CLI conversation history. Reads the local session directory at `~/.copilot/session-state/`, extracts recurring preferences and conventions, and writes a fenced personalization block into `~/.copilot/copilot-instructions.md`. Runs entirely on the user's machine via the local `vardoger` CLI (`pipx install vardoger`); no network calls and no uploads. Triggers: 'personalize my copilot', 'analyze my copilot history', 'tailor copilot to me', 'run vardoger', 'update my copilot instructions from history', 'make copilot learn my style'.

★ 0
JiayiV
JiayiV/question_mixing

transloadit-media-processing

Process media files (video, audio, images, documents) using Transloadit. Use when asked to encode video to HLS/MP4, generate thumbnails, resize or watermark images, extract audio, concatenate clips, add subtitles, OCR documents, or run any media processing pipeline. Covers 86+ processing robots for file transformation at scale.

图像与多媒体Skill与智能体开发
★ 0
JiayiV
JiayiV/question_mixing

terraform-azurerm-set-diff-analyzer

Analyze Terraform plan JSON output for AzureRM Provider to distinguish between false-positive diffs (order-only changes in Set-type attributes) and actual resource changes. Use when reviewing terraform plan output for Azure resources like Application Gateway, Load Balancer, Firewall, Front Door, NSG, and other resources with Set-type attributes that cause spurious diffs due to internal ordering changes.

运维与部署
★ 0
JiayiV
JiayiV/question_mixing

technical-job-search

Use this skill when a software engineer asks for help with job search tasks: parsing or analyzing a job description, tailoring a CV/resume, writing a cover letter, evaluating a job offer, or drafting a post-interview follow-up email. Do not activate for general career advice unrelated to an active job search action.

内容创作者人力资源写作与文案
★ 0
JiayiV
JiayiV/question_mixing

steno-mode

Shorthand-first response compression that cuts ~40% of response tokens while preserving technical precision and exact literals. Use when the user says "steno mode", "shorthand mode", "compressed responses", "token reduction", "brief structured output", or invokes /steno. Supports four compression levels: lite, brief, court, machine. Do not trigger for requests needing polished prose such as onboarding/tutorial content, stakeholder or customer-facing copy, or teaching-focused explanations.

★ 0