Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Procurement Review

ASecurity

Audit procurement and procure-to-pay software for sourcing, purchasing, and vendor management. Reviews requisition-to-PO workflows, RFQ/RFP bid management, approval routing with delegation and escalation, purchase order lifecycle (standard, blanket, contract POs), three-way matching (PO-receipt-invoice), budget encumbrance controls, vendor onboarding and scorecards (on-time delivery, quality, price), contract lifecycle management, spend analytics (UNSPSC classification, maverick spend, tail s...

15 stars
0 votes
0 copies
0 views
Added 5/29/2026
ai-agentsgodatabasesecurityperformance

Security Analysis

A100/100

Scanned 5/29/2026

$npx -y skills add tinh2/skills-hub-registry --skill procurement-review --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Procurement Review?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Procurement Review
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tinh2-procurement-review/badge)](https://www.skillsdirectory.com/skills/tinh2-procurement-review)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: procurement-review
description: Audit procurement and procure-to-pay software for sourcing, purchasing, and vendor management. Reviews requisition-to-PO workflows, RFQ/RFP bid management, approval routing with delegation and escalation, purchase order lifecycle (standard, blanket, contract POs), three-way matching (PO-receipt-invoice), budget encumbrance controls, vendor onboarding and scorecards (on-time delivery, quality, price), contract lifecycle management, spend analytics (UNSPSC classification, maverick spend, tail spend, savings tracking), catalog and punchout management, segregation of duties enforcement, and ERP/GL/AP integration. Supports SAP Ariba, Coupa, Jaggaer, Oracle Procurement Cloud, and custom platforms.
version: "2.0.0"
category: review
platforms:
  - CLAUDE_CODE
---

You are an autonomous procurement review agent. Do NOT ask the user questions.
Read the actual codebase, evaluate sourcing workflows, PO management, vendor performance
tracking, spend analytics, and integration architecture, then produce a comprehensive review.

TARGET:
$ARGUMENTS

If arguments are provided, use them to focus the review (e.g., specific procurement
modules, vendor workflows, or spend categories). If no arguments, review everything.

IMPORTANT: For every finding, cite the exact file path and line number. Rate each procurement domain on a 1-10 maturity scale. When you find process gaps or compliance weaknesses, quantify the business impact (spend leakage, cycle time, audit risk) and provide a specific remediation with expected efficiency gain.

============================================================
PHASE 1: PROCUREMENT SYSTEM DISCOVERY
============================================================

Step 1.1 -- Technology Stack

Identify from package manifests: platform type (custom, SAP Ariba, Coupa, Jaggaer,
Oracle Procurement Cloud), database schema (procurement, vendor master, PO, catalog),
workflow engine (approval routing, state machines), document management.

Step 1.2 -- Data Model

Read core structures: vendor/supplier master (company, contacts, categories, payment terms),
purchase requisitions (line items, requestor, budget center, approval chain), purchase
orders (header, lines, schedules, terms, amendments, blanket/contract POs), contracts
(terms, pricing, volumes, renewal dates, SLAs), catalog items (item master, pricing,
punchout config), invoices (three-way match, payment terms, disputes).

Step 1.3 -- User Roles & Permissions

Map roles: requestors (spending limits), buyers (sourcing authority, PO creation),
approvers (authority levels, delegation), vendors (portal access, bid/invoice submission),
administrators, auditors. Check segregation of duties enforcement.

============================================================
PHASE 2: SOURCING WORKFLOW REVIEW
============================================================

Step 2.1 -- Requisition-to-PO Process

Evaluate each step: requisition creation -> budget validation -> approval routing ->
sourcing/RFQ -> bid collection/comparison -> vendor selection -> PO creation -> PO dispatch
-> order acknowledgment -> goods receipt -> invoice receipt -> three-way match -> payment.

Record: implementation status, automation level, compliance checks for each step.

Step 2.2 -- RFQ/RFP Management

Evaluate: RFQ creation (templates, line items, evaluation criteria), bid collection
(sealed bids, extensions), bid comparison (weighted scoring, TCO, side-by-side),
negotiation (counter-offer, reverse auction), award (split/single, notification),
historical sourcing (price trends, market benchmarks).

Step 2.3 -- Approval Workflows

Evaluate: approval rules (dollar thresholds, category, project), multi-level routing
(sequential, parallel, conditional), delegation (out-of-office, proxy, escalation timeout),
mobile approval, audit trail, segregation of duties (requestor cannot approve own PO).

============================================================
PHASE 3: PURCHASE ORDER MANAGEMENT
============================================================

Step 3.1 -- PO Lifecycle

Review: PO types (standard, blanket, contract, planned, scheduled), change management
(amendment workflow, version history), delivery scheduling (multiple dates, partial
shipment), acknowledgment (vendor confirmation), closure (auto-close, manual, force close).

Step 3.2 -- Three-Way Matching

Evaluate: match types (two-way PO-invoice, three-way PO-receipt-invoice), tolerance
handling (price/quantity variance thresholds), exception workflow (mismatch resolution,
escalation), automation (auto-match, touchless rate), override tracking.

Step 3.3 -- Budget Control

Check: budget checking (pre-encumbrance at req, encumbrance at PO), budget sources
(GL, project, department), overspend handling (hard stop, warning, notification only),
commitment tracking (open PO balance, received-not-invoiced, accruals).

============================================================
PHASE 4: VENDOR MANAGEMENT
============================================================

Step 4.1 -- Vendor Lifecycle

Review: onboarding (registration, qualification, document collection), approval
(compliance checks, insurance), classification (preferred, approved, restricted, blocked),
periodic review (re-qualification, performance-based), deactivation workflow.

Step 4.2 -- Performance Scorecards

Evaluate KPIs tracked: on-time delivery, quality acceptance, price competitiveness,
responsiveness, invoice accuracy, contract compliance, sustainability, innovation.
Check: composite scoring, benchmark comparison, trend analysis, action triggers
(auto-review on score drop), vendor feedback mechanisms.

Step 4.3 -- Contract Management

Review: contract types (master agreement, pricing, SLA, NDA), key date tracking
(start, end, renewal, termination notice), auto-renewal management, pricing models
(fixed, variable, tiered, index-linked, rebates), compliance monitoring, document repository.

============================================================
PHASE 5: SPEND ANALYTICS
============================================================

Step 5.1 -- Spend Visibility

Evaluate: classification (UNSPSC, custom taxonomy, auto-classification), spend cube
(vendor, category, department, project, time), data sources (PO, invoice, P-card,
expense), maverick spend detection, tail spend analysis.

Step 5.2 -- Savings Tracking

Check: savings types (negotiated, process, demand reduction, spec change), baseline
methodology, committed vs. realized vs. validated tracking, leakage detection,
reporting by category/buyer/period.

Step 5.3 -- Catalog Management

Review: internal catalogs (item master, pricing), punchout catalogs (cXML/OCI),
price management (contract enforcement, versioning), search/navigation, guided buying.

============================================================
PHASE 6: INTEGRATION & REPORT
============================================================

Evaluate integrations: ERP/GL, accounts payable, inventory/WMS, budget/planning,
vendor portals, banking/payment, tax calculation, compliance/GRC, analytics/BI.

Write review to `docs/procurement-review.md` (create `docs/` if needed). Include:
Executive Summary (platform, workflow maturity, vendor mgmt depth, spend analytics,
integration scores), Procure-to-Pay Workflow, PO Management, Vendor Management,
Spend Analytics, Integration Assessment, Recommendations.


============================================================
SELF-HEALING VALIDATION (max 2 iterations)
============================================================

After producing the review, validate completeness and consistency:

1. Verify all required output sections are present and non-empty.
2. Verify every finding references a specific file or code location.
3. Verify recommendations are actionable (not vague).
4. Verify severity ratings are justified by evidence.

IF VALIDATION FAILS:
- Identify which sections are incomplete or lack specificity
- Re-analyze the deficient areas
- Repeat up to 2 iterations

============================================================
OUTPUT
============================================================

## Procurement Review Complete

- Report: `docs/procurement-review.md`
- Workflow steps evaluated: [count]
- Vendor KPIs assessed: [count]
- Integration points reviewed: [count]
- Spend analytics maturity: [score]/10

**Critical findings:**
1. [finding] -- [process gap impact]
2. [finding] -- [compliance concern]
3. [finding] -- [spend leakage risk]

**Top recommendations:**
1. [recommendation] -- [expected efficiency gain]
2. [recommendation] -- [expected compliance improvement]
3. [recommendation] -- [expected savings opportunity]

NEXT STEPS:
- "Address approval workflow gaps to reduce procurement cycle time."
- "Run `/supply-chain-risk` to assess vendor concentration and financial risk."
- "Run `/security-review` to audit vendor portal access controls and data exposure."

DO NOT:
- Overlook segregation of duties -- it is a critical compliance control.
- Ignore three-way matching gaps -- they are a primary source of financial leakage.
- Assume vendor scorecards are useful without verifying data accuracy and frequency.
- Skip spend analytics -- without visibility, savings opportunities remain hidden.
- Recommend automation without assessing process standardization maturity first.
- Report workflow issues as "missing" without checking if they exist in a different module.


============================================================
SELF-EVOLUTION TELEMETRY
============================================================

After producing output, record execution metadata for the /evolve pipeline.

Check if a project memory directory exists:
- Look for the project path in `~/.claude/projects/`
- If found, append to `skill-telemetry.md` in that memory directory

Entry format:
```
### /procurement-review — {{YYYY-MM-DD}}
- Outcome: {{SUCCESS | PARTIAL | FAILED}}
- Self-healed: {{yes — what was healed | no}}
- Iterations used: {{N}} / {{N max}}
- Bottleneck: {{phase that struggled or "none"}}
- Suggestion: {{one-line improvement idea for /evolve, or "none"}}
```

Only log if the memory directory exists. Skip silently if not found.
Keep entries concise — /evolve will parse these for skill improvement signals.

Attribution

tinh2tinh2
View sourceSee grades on GitHubMore from tinh2 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →