borghei/Claude-Skills / business-operations/procurement-optimizer
procurement-optimizer
VerifiedCut software and services spend through seat-utilisation analysis, redundant-tool detection, and renewal-timing leverage. Use when auditing SaaS spend, preparing a renewal negotiation, or hunting a budget-reduction target.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 14.3 KB |
| assets/renewal-negotiation-brief.md | markdown | 4.2 KB |
| assets/sample_spend.json | config | 5.0 KB |
| assets/spend-audit-report-template.md | markdown | 3.5 KB |
| references/saas-negotiation-levers.md | markdown | 12.8 KB |
| references/utilization-benchmarks.md | markdown | 10.1 KB |
| scripts/license_utilization_analyzer.py | script | 8.8 KB |
| scripts/savings_opportunity_ranker.py | script | 10.9 KB |
| scripts/tool_overlap_detector.py | script | 9.5 KB |
assets/spend-audit-report-template.md
View on GitHub# Software Spend Audit — <period>
**As-of date:** <YYYY-MM-DD> **Prepared by:** <name> **Headcount:** <n>
**Scope:** <which cost centres / categories are included, and what is excluded>
---
## Headline
| Figure | Amount | Note |
|--------|--------|------|
| Total annual software spend | | |
| Spend per head | | Benchmark for our profile: <range> |
| Gross annual opportunity | | Everything identified, regardless of timing |
| **Realisable this fiscal year** | | **This is the commitable number** |
| Locked this cycle | | Inside notice window on auto-renew; arrives next year |
| Effort to realise | <n> days | |
**Committed savings target: <amount>** — realisable only, never gross. Committing to a number
that includes locked contracts guarantees a miss you can see coming from the day you commit.
## Where the money is
| Category | Spend | Reclaimable | % | Tools |
|----------|-------|------------|---|-------|
| | | | | |
## Top opportunities
From `savings_opportunity_ranker.py`. Time-boxed items first — missing a renewal window
costs a full contract year.
| # | Tool | Lever | Gross | Realisable | Effort | Renewal | Owner |
|---|------|-------|-------|-----------|--------|---------|-------|
| 1 | | seat-reduction | | | | T-<n>d (<phase>) | |
## Utilisation detail
| Tool | Purchased | Assigned | Active 30d | Utilisation | Benchmark | Verdict |
|------|-----------|----------|-----------|-------------|-----------|---------|
| | | | | | | |
**Data quality note:** <state which tools used active-seat data and which used an SSO-login
proxy. An analysis built on assigned seats is not valid — say so explicitly if any tool
lacked active counts.>
## Consolidation candidates
| Category | Tools | Survivor | Displaced | Net recovery | Migration effort |
|----------|-------|----------|-----------|-------------|------------------|
| | | | | | |
Survivors are chosen by displacement cost (active users × criticality), not by licence price.
Recovery figures are net of an assumed 20% migration and retained-access cost.
**Umbrella-label warnings:** <list any categories the detector flagged as umbrella labels.
These must be re-tagged by job before their numbers are believed.>
## Renewal calendar — next 12 months
| Renewal date | Tool | Notice deadline | Auto-renew | Annual cost | Action | Owner |
|-------------|------|----------------|-----------|-------------|--------|-------|
| | | | | | | |
**Standing policy:** serve notice by default at the deadline on every auto-renewing contract.
Notice is procedural, not termination, and it is the difference between a negotiation and an
automatic renewal.
## Adoption failures
Tools where seats are assigned but unused. These are not seat-reduction problems — cutting
seats leaves the same people not using the tool.
| Tool | Assigned | Active | Adoption | Decision needed |
|------|----------|--------|----------|-----------------|
| | | | | Fix adoption / retire |
## Risks and dependencies
| Risk | Impact | Mitigation |
|------|--------|-----------|
| Seat cuts trigger emergency re-purchase at list | | 12% safety buffer applied above active count |
| Consolidation displaces a critical workflow | | Verify `has_alternative` with the owning team before acting |
| Politically protected tools excluded | | <list them; they change what is worth analysing> |
## Decisions needed
- [ ] <Decision> — owner: <name>, needed by: <date, driven by the notice deadline>
## Next audit
**Date:** <six months out> | **Same `--as-of` convention:** yes
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |